{
  "data": {
    "a": {
      "slug": "boxes-dev",
      "name": "boxes.dev",
      "vendor": "Boxes, Inc.",
      "vendorUrl": "https://boxes.dev",
      "company": "boxes.dev",
      "kind": "mcp",
      "category": "agent-harnesses",
      "summary": "boxes.dev runs Claude Code and Codex on cloud Linux devboxes that copy a developer's environment. Tasks start from the desktop and mobile apps, the `dvb` CLI, Slack, Linear, schedules, an automation API or a remote MCP server.",
      "url": "https://www.anchorterminal.com/tools/boxes-dev",
      "markdownUrl": "https://www.anchorterminal.com/tools/boxes-dev.md",
      "slimMarkdownUrl": "https://www.anchorterminal.com/tools/boxes-dev.min.md",
      "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/boxes-dev.json",
      "dns": "boxes-dev.grade.anchorterminal.com",
      "license": "Proprietary. The service runs under the Common Paper Cloud Service Agreement 2.1, and the `@boxes-dev/cli` package is marked UNLICENSED",
      "transports": [
        "streamable-http",
        "http"
      ],
      "remoteUrl": "https://api.boxes.dev/mcp",
      "packages": [
        {
          "registry": "npm",
          "name": "@boxes-dev/cli"
        }
      ],
      "auth": "mixed",
      "authNotes": "The remote MCP server uses OAuth through mcp.boxes.dev, with scopes `threads:read`, `threads:write`, `events:subscribe` and `settings:write` and a per-project grant chosen by the user. Automation endpoints use a bearer secret generated per automation in the desktop app. Account sign-in is Google or Apple.",
      "pricing": "freemium",
      "pricingNotes": "Trial free with 20 box-hours. Starter $19, Pro $99 and Max $249 a seat a month with 50, 300 and 750 box-hours, then $0.40 a box-hour. A box-hour is one hour awake on a 4 vCPU, 8 GiB devbox. Sleeping devboxes are free. Some teams must add a payment method before the trial.",
      "priceSummary": "$0.40 / unit",
      "where": "hosted",
      "x402": {
        "level": "no",
        "evidence": "No x402, MPP or L402 on the pricing, plans, automation API or MCP connection pages (checked 2026-11-18). Paid plans bill a payment method on file monthly.",
        "endpoints": []
      },
      "toolCount": null,
      "popularity": {
        "githubStars": null,
        "npmWeekly": null,
        "pypiWeekly": null,
        "asOf": "2026-11-18"
      },
      "docsUrl": "https://boxes.dev/help",
      "llmsTxt": "https://boxes.dev/llms.txt",
      "capabilities": [
        "agent.harness",
        "agent.multi-agent",
        "sandbox.persist"
      ],
      "tags": [
        "hosted",
        "cloud-agent",
        "closed-source",
        "mcp",
        "remote-mcp",
        "oauth",
        "llms-txt",
        "cli",
        "free-tier",
        "idempotency",
        "yc"
      ],
      "lastRelease": "2026-11-17",
      "graded": true,
      "anchor": {
        "graded": true,
        "score": 53.2,
        "grade": "D",
        "agentReady": false,
        "rank": 1055,
        "ranked": true,
        "rankOf": 1557,
        "categoryRank": 45,
        "methodology": "1.0",
        "run": "2026-10-01",
        "scores": {
          "ergonomics": 60,
          "maintenance": 48,
          "payments": 50,
          "reliability": 32,
          "schema": 57,
          "security": 69,
          "transparency": 60
        },
        "assessment": {
          "confidence": "medium",
          "date": "2026-11-18"
        },
        "negative": 0,
        "warnings": [
          {
            "kind": "operator-unidentified",
            "name": "Operator not identified",
            "text": "Boxes' terms name Boxes, Inc. under California law with only an email address for notices, and no place of registration, registration number or street address. OpenCorporates refused our reader (403), so no register entry was found.",
            "deduct": 0,
            "capGrade": "B",
            "since": "2026-11-18",
            "sources": [
              "https://boxes.dev/terms",
              "https://boxes.dev/privacy"
            ]
          }
        ],
        "verdict": "An outside agent can start Claude Code or Codex tasks on cloud devboxes through an OAuth MCP server with four scopes, or an automation endpoint with idempotency keys. No status page, SLA or tool schema could be read, and every route starts with a person setting up a project in the app.",
        "bestFor": "Developers who want Claude Code or Codex running on cloud copies of their dev environment, started from Slack, Linear, a schedule, an API call or another assistant.",
        "strengths": [
          "OAuth MCP server with four scopes and a per-project grant, and approvals stay in the boxes.dev apps",
          "Automation runs take an `Idempotency-Key` and return the original run on a retry",
          "Named error codes for capacity and unavailable targets, with the action to take",
          "Public plan prices and $0.40 per box-hour for extra usage, with a 20 box-hour trial",
          "Valid security.txt and a disclosure policy with safe harbour"
        ],
        "weaknesses": [
          "No status page, incident history or SLA found",
          "No OpenAPI document, and the MCP tool list needs an OAuth token to read",
          "Every route needs a person to sign up and set up a project in the desktop app first",
          "The API status endpoint reports launch progress only, not the agent's result",
          "No changelog and no deprecation policy for the API or MCP server"
        ],
        "agentNotes": [
          "Send a new `Idempotency-Key` for each intended run, and the same key and body when you retry an uncertain request",
          "Wait for status `thread_ready` before you use a returned `devboxId` as a target",
          "If you get 409 `active_fork_limit_reached`, free an awake devbox or wait. The plan's awake-devbox cap is full",
          "Read the thread in boxes.dev for the agent's answer. The status URL does not return it",
          "Ask for `threads:read` only unless the task needs to start agents or change settings"
        ],
        "metrics": {
          "kind": "remote",
          "measured": false
        },
        "reviewCount": 0,
        "avgRating": 0,
        "history": [
          {
            "basis": "public evidence",
            "confidence": "medium",
            "grade": "D",
            "methodology": "1.0",
            "run": "2026-10-01",
            "runLabel": "October 2026 research run",
            "score": 53.2
          }
        ],
        "editorialScores": {
          "ergonomics": 60,
          "maintenance": 48,
          "payments": 50,
          "reliability": 32,
          "schema": 57,
          "security": 69,
          "transparency": 54
        },
        "provenanceScore": 66,
        "checked": {
          "categories": {
            "ergonomics": "2026-11-18",
            "maintenance": "2026-11-18",
            "payments": "2026-11-18",
            "reliability": "2026-11-18",
            "schema": "2026-11-18",
            "security": "2026-11-18",
            "transparency": "2026-11-18"
          },
          "last": "2026-11-18",
          "oldest": "2026-11-18",
          "stale": false,
          "staleAfterDays": 90
        }
      },
      "connect": {
        "install": "npm install -g @boxes-dev/cli \u0026\u0026 dvb setup",
        "claudeCode": "claude mcp add boxes-dev --transport http https://api.boxes.dev/mcp",
        "config": {
          "mcpServers": {
            "boxes-dev": {
              "url": "https://api.boxes.dev/mcp"
            }
          }
        }
      },
      "letme": {
        "capability": "https://letme.dev/agent.harness",
        "tool": "https://letme.dev/boxes-dev"
      },
      "area": "frameworks",
      "unitPrices": [
        {
          "item": "Box-hour beyond the plan allowance",
          "unit": "compute-unit",
          "usd": 0.4,
          "note": "One hour awake on a 4 vCPU, 8 GiB devbox. Larger devboxes use more box-hours an hour"
        },
        {
          "item": "Pro plan",
          "unit": "seat-month",
          "usd": 99,
          "note": "300 box-hours included per seat"
        }
      ],
      "provenance": {
        "legalEntity": "Boxes, Inc.",
        "domain": "boxes.dev",
        "domainRegistered": "",
        "endpointOnVendorDomain": true,
        "terms": "https://boxes.dev/terms",
        "privacy": "https://boxes.dev/privacy",
        "statusPage": "",
        "changelog": "",
        "securityTxt": "valid",
        "checked": "2026-11-18",
        "notes": [
          "boxes.dev/robots.txt allows all agents. api.boxes.dev/robots.txt answered 404, so it publishes no rules. trust.boxes.dev/robots.txt answered 200 with no rules.",
          "The terms (last updated 20 October 2026) adopt the Common Paper Cloud Service Agreement Standard Terms 2.1, delete its machine-learning section, choose California law and give founders@boxes.dev as the notice address.",
          "The privacy policy is dated 21 October 2026. Contact privacy@boxes.dev.",
          "security.txt names security@boxes.dev, points to boxes.dev/security and expires on 2 June 2027.",
          "No status page found. The domain's registration date was not looked up."
        ],
        "score": 66
      },
      "pageJsonUrl": "https://www.anchorterminal.com/tools/boxes-dev.json",
      "live": {
        "slug": "boxes-dev",
        "probe": {
          "target": "https://api.boxes.dev/mcp",
          "method": "mcp-initialize",
          "lastAt": "2026-11-18T22:43:10.131601145Z",
          "lastOk": true,
          "lastStatus": 401,
          "lastMs": 731,
          "lastNote": "asks for credentials",
          "authRequired": true,
          "uptime24h": 100,
          "uptime30d": 100,
          "p50ms24h": 539,
          "p95ms24h": 1740,
          "samples24h": 11,
          "samples30d": 11,
          "days": [
            {
              "date": "2026-11-18",
              "probes": 11,
              "ok": 11
            }
          ],
          "since": "2026-11-18T21:37:40.384341882Z"
        },
        "updatedAt": "2026-11-18T22:43:10.131601145Z"
      },
      "streak": {
        "days": 0,
        "from": "2026-11-18",
        "sinceWatching": true,
        "best": 0
      }
    },
    "answer": "Crush and boxes.dev score within a point of each other on agent readiness, 53.3 (D) and 53.2 (D). boxes.dev leads on agent ergonomics and security \u0026 auth.",
    "b": {
      "slug": "crush",
      "name": "Crush",
      "vendor": "Charm",
      "vendorUrl": "https://charm.land",
      "company": "charm.land",
      "kind": "harness",
      "category": "agent-harnesses",
      "summary": "Terminal coding agent from Charm, written in Go, that works with the model of the owner's choice. It has a TUI, a one-shot `crush run` mode, LSP context, MCP servers, Agent Skills and an optional local client-server mode.",
      "url": "https://www.anchorterminal.com/tools/crush",
      "markdownUrl": "https://www.anchorterminal.com/tools/crush.md",
      "slimMarkdownUrl": "https://www.anchorterminal.com/tools/crush.min.md",
      "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/crush.json",
      "dns": "crush.grade.anchorterminal.com",
      "repo": "https://github.com/charmbracelet/crush",
      "license": "FSL-1.1-MIT (source-available, each release converts to MIT two years after it is made available)",
      "transports": [],
      "packages": [
        {
          "registry": "npm",
          "name": "@charmland/crush"
        },
        {
          "registry": "go",
          "name": "github.com/charmbracelet/crush"
        }
      ],
      "auth": "mixed",
      "authNotes": "No Charm account is needed. Provider keys come from environment variables such as `ANTHROPIC_API_KEY` or `OPENAI_API_KEY`, the model picker or a `crushrc`, local models need none, and Charm's Hyper provider uses a device login. `crush server` has no authentication and listens on a per-user Unix socket by default.",
      "pricing": "freemium",
      "pricingNotes": "The CLI is free to use under FSL-1.1-MIT. You pay your model provider, or Charm's Hyper subscription, which the README says has a free tier. Hyper's public provider file lists per-million-token figures for 22 models. Plan prices sit in a script-rendered app and weren't read.",
      "priceSummary": "Freemium",
      "where": "local",
      "x402": {
        "level": "no",
        "evidence": "No x402, MPP or L402 in the README, the docs folder or the source (checked 2026-10-18).",
        "endpoints": []
      },
      "toolCount": null,
      "popularity": {
        "githubStars": 29000,
        "npmWeekly": 5594,
        "pypiWeekly": null,
        "asOf": "2026-10-18"
      },
      "docsUrl": "https://github.com/charmbracelet/crush#readme",
      "capabilities": [
        "agent.harness",
        "agent.mcp-client",
        "agent.multi-agent"
      ],
      "tags": [
        "harness",
        "coding-agent",
        "cli",
        "source-available",
        "go",
        "mcp",
        "telemetry-default-on",
        "pre-1.0",
        "freemium",
        "no-card",
        "local"
      ],
      "lastRelease": "2026-10-29",
      "graded": true,
      "anchor": {
        "graded": true,
        "score": 53.3,
        "grade": "D",
        "agentReady": false,
        "rank": 1047,
        "ranked": true,
        "rankOf": 1557,
        "categoryRank": 44,
        "methodology": "1.0",
        "run": "2026-10-01",
        "scores": {
          "ergonomics": 52,
          "maintenance": 82,
          "payments": 83,
          "reliability": 52,
          "schema": 65,
          "security": 41,
          "transparency": 59
        },
        "assessment": {
          "confidence": "medium",
          "date": "2026-11-04"
        },
        "negative": -6,
        "negativeNotes": [
          "23 October 2026. Released fix of a described flaw with no advisory found. v0.98.2 carried 1dbd303a, which says write, edit and multiedit created parent directories before the permission prompt, so \"An agent could mkdir -p anywhere on the machine with no consent\". OSV lists no advisory for Crush, so 3 is deducted (https://github.com/charmbracelet/crush/commit/1dbd303a).",
          "30 October 2026. Fix in no release. fd40067e, merged to main on 30 October and carried only by the `nightly` pre-release, says an \"allow for this session\" approval of one shell command \"stood in for every command run in that directory afterwards, however dangerous, with no further prompt\". v0.99.0 (29 October) still keys session grants on tool, action and path. 3 is deducted until a release carries it (https://github.com/charmbracelet/crush/commit/fd40067e)."
        ],
        "verdict": "Works with almost any provider or a local model and needs no Charm account. `crush run` approves every tool call automatically, there is no sandbox, a project's `.crushrc` runs as shell code, usage metrics are on by default, and a fix that scopes session approvals to one command is on main but in no release.",
        "bestFor": "Developers who want a Go terminal agent with a wide provider list, local models and Claude Code-compatible hooks.",
        "strengths": [
          "Any OpenAI- or Anthropic-compatible provider, Bedrock, Vertex, Azure and local models through Ollama, llama.cpp, LM Studio or LiteLLM, with no Charm account",
          "PreToolUse hooks, compatible with Claude Code's format, can block or rewrite tool calls",
          "Releases cosign-signed, with CodeQL, Grype and govulncheck in CI",
          "19 releases from 7 August to 29 October 2026, the latest v0.99.0 on 29 October",
          "Built for macOS, Linux, Windows, Android and three BSDs, with packages for npm, Homebrew, Winget, Scoop, apt, yum and Nix"
        ],
        "weaknesses": [
          "`crush run` approves every permission request automatically, which the README doesn't mention",
          "No sandbox, only a refusal list of shell commands, and permission fixes merged on 30 October 2026 are in no release yet",
          "A project's `.crushrc` and `$(...)` in `crush.json` run as code when Crush starts",
          "Usage metrics are on by default and are linked to the Hyper account after a Hyper login",
          "No JSON output, turn limit or cost limit for `crush run`, and the client-server API is opt-in and has no authentication"
        ],
        "agentNotes": [
          "Add `permissions deny` rules or a PreToolUse hook before `crush run`. It approves every permission request in its session, and a session approval in v0.99.0 covers later commands in the same directory",
          "Read `.crushrc`, `crushrc` and `crush.json` in a cloned repository before running Crush there. They execute as shell code at startup",
          "Set `CRUSH_DISABLE_METRICS=1` or `DO_NOT_TRACK=1` to stop usage metrics to data.charm.land",
          "Wrap `crush run` in your own timeout. It has no turn, time or cost limit flag",
          "Configure a provider by environment variable or `crushrc` first. With none, `crush run` exits with an error asking for interactive setup"
        ],
        "metrics": {
          "kind": "local",
          "measured": false
        },
        "reviewCount": 4,
        "avgRating": 2.3,
        "history": [
          {
            "basis": "public evidence",
            "confidence": "medium",
            "grade": "D",
            "methodology": "1.0",
            "run": "2026-10-01",
            "runLabel": "October 2026 research run",
            "score": 53.3
          }
        ],
        "editorialScores": {
          "ergonomics": 52,
          "maintenance": 82,
          "payments": 83,
          "reliability": 52,
          "schema": 65,
          "security": 41,
          "transparency": 49
        },
        "provenanceScore": 69,
        "checked": {
          "categories": {
            "ergonomics": "2026-11-04",
            "maintenance": "2026-11-04",
            "payments": "2026-11-04",
            "reliability": "2026-11-04",
            "schema": "2026-11-04",
            "security": "2026-11-04",
            "transparency": "2026-11-04"
          },
          "last": "2026-11-04",
          "lastMoved": "2026-11-13",
          "oldest": "2026-11-04",
          "stale": false,
          "staleAfterDays": 90
        }
      },
      "connect": {
        "install": "npm install -g @charmland/crush   # or: brew install charmbracelet/tap/crush",
        "headless": {
          "command": "crush run --quiet \"$TASK\"",
          "env": {
            "CRUSH_DISABLE_METRICS": "1"
          }
        }
      },
      "letme": {
        "capability": "https://letme.dev/agent.harness",
        "tool": "https://letme.dev/crush"
      },
      "area": "frameworks",
      "unitPrices": [
        {
          "item": "Hyper, qwen3.8-max (default large model), input",
          "unit": "1m-tokens",
          "usd": 2,
          "note": "output $6, from Hyper's public provider file"
        },
        {
          "item": "Hyper, deepseek-v4.1-flash (default small model), input",
          "unit": "1m-tokens",
          "usd": 0.33,
          "note": "output $1.31, from Hyper's public provider file"
        }
      ],
      "provenance": {
        "legalEntity": "Charmbracelet, Inc.",
        "domain": "charm.land",
        "domainRegistered": "2023-08-17",
        "endpointOnVendorDomain": null,
        "terms": "",
        "privacy": "",
        "statusPage": "",
        "changelog": "https://github.com/charmbracelet/crush/releases",
        "securityTxt": "none",
        "checked": "2026-10-18",
        "notes": [
          "LICENSE.md and the charm.land footer name Charmbracelet, Inc.",
          "charm.land/privacy, charm.land/terms and charm.land/.well-known/security.txt return Charm's not-found page. Hyper links Terms of Service and a Privacy Policy at hyper.charm.land/legal, which render by script and weren't read.",
          "The organisation's SECURITY.md gives vt100@charm.sh for reports. The crush repository has no SECURITY.md of its own.",
          "Release notes are generated from commit messages on GitHub releases. There is no CHANGELOG file in the repository."
        ],
        "score": 69
      },
      "pageJsonUrl": "https://www.anchorterminal.com/tools/crush.json",
      "live": {
        "slug": "crush",
        "versions": [
          {
            "registry": "github",
            "name": "charmbracelet/crush",
            "version": "v0.101.0",
            "released": "2026-11-12",
            "seenAt": "2026-11-18T17:40:25.478881065Z"
          },
          {
            "registry": "npm",
            "name": "@charmland/crush",
            "version": "0.101.0",
            "seenAt": "2026-11-18T17:40:24.585842975Z"
          }
        ],
        "githubStars": 29121,
        "npmWeekly": 11262,
        "securityTxt": {
          "url": "https://charm.land/.well-known/security.txt",
          "state": "none",
          "checkedAt": "2026-11-18T16:30:26.761205583Z"
        },
        "domain": {
          "domain": "charm.land",
          "registered": "2023-08-17",
          "source": "https://rdap.identitydigital.services/rdap/domain/charm.land",
          "checkedAt": "2026-11-15T15:34:13.303336682Z"
        },
        "github": {
          "repo": "charmbracelet/crush",
          "checkedAt": "2026-11-16T11:49:55.126050052Z",
          "stars": 29101,
          "archived": false,
          "issuesEnabled": true,
          "pushedAt": "2026-11-16T00:49:54Z",
          "openIssues": 300,
          "openPRs": 253,
          "issuesOpened90d": 168,
          "issuesClosed90d": 257,
          "prsMerged90d": 229,
          "ci": {
            "branch": "main",
            "runs": 50,
            "success": 47,
            "failure": 0,
            "other": 3,
            "latest": "success",
            "latestAt": "2026-11-15T18:45:19Z"
          },
          "replies": {
            "sampled": 25,
            "unanswered": 20,
            "medianDays": 0.9
          }
        },
        "updatedAt": "2026-11-18T17:40:25.478881065Z"
      }
    },
    "edges": [
      {
        "by": 34,
        "category": "maintenance",
        "leads": "crush",
        "name": "Maintenance \u0026 community",
        "reasons": {
          "a": "Closed service. CLI `@boxes-dev/cli` 1.0.1134 published on 17 November 2026 (30). Only one dated product update was found, on 27 October 2026, and earlier CLI versions' dates were not read, so three releases in 90 days are not established (0). A support address, an in-app chat and a blog, with no public tracker or changelog (8 of 25). A CLI but no SDK, and no entry in the official MCP registry was looked for (5 of 15). The CLI is published from GitHub Actions with npm trusted publishing and signatures (5 of 10). 30+0+8+5+5 = 48.",
          "b": "v0.99.0 tagged on 29 October 2026 (6 days, 30). 21 release tags from 7 August to 29 October, v0.88.1 to v0.99.0, besides a moving `nightly` tag that isn't counted (20). The 18 October shields.io counts are struck. The repository's refs show 147 merges into main and 438 commits in the 90 days to 4 November, with 272 open pull requests carrying a merge ref, and new contributors signing the CLA most days. Reply times couldn't be read (12). No SDK, as with other harnesses. npm, Homebrew, Winget, Scoop, apt, yum and NUR builds come from the release workflow (12, held partial). Dependabot, a `go mod tidy` check in CI and nightly security scans, with CI results unread (8). 30 + 20 + 12 + 12 + 8 = 82."
        },
        "scores": {
          "a": 48,
          "b": 82
        }
      },
      {
        "by": 33,
        "category": "payments",
        "leads": "crush",
        "name": "Payments \u0026 pricing",
        "reasons": {
          "a": "No x402, MPP or L402 (0). Plan prices are public ($19, $99 and $249 a seat a month) and extra usage is $0.40 a box-hour, with a box-hour defined as one hour of a 4 vCPU, 8 GiB devbox (30). A free trial of 20 box-hours. The help page says some teams must add a payment method before starting, so a card-free start is not certain (20 of 30). A person signs in with Google or Apple and approves the OAuth grant or creates the automation secret in the desktop app (0). 0+30+20+0 = 50.",
          "b": "No payment protocol (0). Scored on Charm's Hyper provider. Its public provider file at hyper.charm.land/v1/provider lists per-million-token figures for 22 models without a login, but no pricing page confirms them as billed rates, and plan prices sit in a script-rendered app (15). The CLI is free to use and runs with your own provider key or a local model, so nothing needs a card (20). A local model through Ollama, llama.cpp or LM Studio, or an existing provider key in the environment, works with no Charm account, so an agent can install it and run a task without a person signing up (20). Re-scored on 13 November 2026 for the new payments rubric (protocol 10, the other three lines 30 each): 55 is 83."
        },
        "scores": {
          "a": 50,
          "b": 83
        }
      },
      {
        "by": 28,
        "category": "security",
        "leads": "boxes-dev",
        "name": "Security \u0026 auth",
        "reasons": {
          "a": "OAuth for the MCP server, with protected-resource metadata naming mcp.boxes.dev and four scopes (`threads:read`, `threads:write`, `events:subscribe`, `settings:write`), a per-project grant and removal from settings. Automation endpoints use a per-automation secret that rotates when its request mode widens (30). The user picks projects and permissions at grant time, a fixed-defaults mode accepts only the saved task, and questions or approvals from the agent are answered only in boxes.dev, never through the MCP connection (15). Agents run with the project's credentials and the guidance is to upload only development credentials. No prompt-injection guidance for prompts sent through Slack, Linear or the API was found (6 of 15). Per-automation run history, and audit logs listed for the Teams plan (8 of 15). A valid security.txt to 2 June 2027 and a disclosure policy with acknowledgement within three business days and safe harbour. No bug bounty and no certification found (10 of 20). 30+15+6+8+10 = 69.",
          "b": "Harness reading of the framework checklist, as for the other harnesses. 30 for what leaves the machine by default, 20 for approvals and sandboxing, 15 for prompt-injection posture, 15 for audit and 20 for the security programme. Usage metrics go to PostHog through data.charm.land by default, keyed to a hashed machine ID, aliased to the Hyper user ID after a Hyper login, and including error messages. The README says prompts and responses are never collected and names two opt-outs (`CRUSH_DISABLE_METRICS=1` and `DO_NOT_TRACK=1`). The provider list is fetched from Catwalk at startup unless turned off, the update check only notifies, and provider keys stay local (15). The TUI asks before bash, edit, write, fetch, download and MCP calls, `permissions deny` hides tools and PreToolUse hooks can block calls. But `crush run` approves every permission request in its session automatically (internal/app/app.go in v0.99.0), `--yolo` skips all prompts, and there's no sandbox, only a refusal list for curl, wget, ssh, sudo, package managers and similar commands (7). No prompt-injection guidance found, and a project's `.crushrc` and `$(...)` in `crush.json` run as code at startup, which the README warns about (3). Logs in `./.crush/logs/crush.log` with `crush logs`, sessions in a local database readable as JSON, and `crush stats`, with no OpenTelemetry export (9). The organisation's SECURITY.md is a disclosure policy with a reporting address (vt100@charm.sh) and no response time. CI runs CodeQL, Grype and govulncheck nightly and releases are cosign-signed. OSV lists no advisory for the npm package or the Go module. No security.txt and no bug bounty. A disclosure route with no stated time is this run's 7 (was 10). 15 + 7 + 3 + 9 + 7 = 41."
        },
        "scores": {
          "a": 69,
          "b": 41
        }
      },
      {
        "by": 20,
        "category": "reliability",
        "leads": "crush",
        "name": "Reliability",
        "reasons": {
          "a": "Hosted reading, for the remote MCP server at api.boxes.dev/mcp and the automation run endpoints. No status page found. The site footer says \"All systems normal\" with no link, and the trust centre at trust.boxes.dev draws in a script our reader could not run (0). No readable incident history (5). No request rate limits found. Plans cap awake devboxes (3 on the trial, 5 to 25 on paid plans), and the API answers 409 `active_fork_limit_reached` at the cap (5 of 15). The automation API takes an `Idempotency-Key` and returns the original run on a retry with `idempotentReplay: true`, and the MCP connection retries a lost start or message with the same request key. No `Retry-After` or backoff guidance found (12 of 15). No SLA found (0). Neither the MCP connection nor the automation API is marked beta, and the product launched in June 2026 per its own blog (10). 0+5+5+12+0+10 = 32.",
          "b": "Local-package reading. `@charmland/crush` on npm, a Homebrew tap, Winget, Scoop, AUR, Nix, FreeBSD pkg, Charm's apt and yum repositories and release binaries, with supported platforms named in the README (20). The public build workflow runs `go test -race -failfast ./...` on Linux, macOS and Windows for every push to main and every pull request, but GitHub pages and the API answer 403 to us, so results are unread (15). The 18 October issue and pull request counts came from shields.io badges, a third-party copy of GitHub data, and are struck. The repository's own refs show 2,574 pull requests to #4224, 272 of them open with a merge ref, and 147 merges into main in the 90 days to 4 November. Crash and regression issues couldn't be read (10). Release notes are generated from commit messages, with no CHANGELOG file and no breaking-change headings found. The legacy JSON config is deprecated in favour of `crushrc` while still loading (7, held partial). v0.99.0, before 1.0, with no stability statement (0). 20 + 15 + 10 + 7 + 0 = 52."
        },
        "scores": {
          "a": 32,
          "b": 52
        }
      },
      {
        "by": 8,
        "category": "schema",
        "leads": "crush",
        "name": "Schema \u0026 documentation",
        "reasons": {
          "a": "No OpenAPI document, and the MCP tool list could not be read because the endpoint answers 401 before `initialize` without an OAuth token. The automation API's request and response fields are documented in prose tables (5 of 25). llms.txt with every help page listed (10). The help pages say when to target a new devbox, an existing devbox or an existing thread, when to steer a busy agent and when to wake a devbox first (16). Field tables with enum values such as `backend` (`codex` or `claude`), `delivery` (`steer` or `next`) and four run statuses, and unknown fields are rejected. The MCP schemas themselves were not seen (9 of 15). curl examples and named errors such as 409 `devbox_unavailable`, 409 `thread_unavailable` and 503 `devbox_wake_failed`, with what each means (12). `/v1` in the API path on the home page, a single dated product update of 27 October 2026 and no changelog (5 of 15). 5+10+16+9+12+5 = 57.",
          "b": "Harness reading of the framework line. A JSON Schema for the config at https://charm.land/crush.json (also printed by `crush schema`), `--json` on the session commands, and an OpenAPI document that `crush server` generates from its endpoint list and serves at `/v1/docs/openapi.json`, which isn't published anywhere we could fetch. `crush run` output has no typed form (20). No llms.txt (charm.land/llms.txt is a not-found page). The docs are Markdown in the repository and the hooks guide says it was written for humans and agents (5). The README and config docs explain when to allow, deny or hook a tool and warn that configs run as code (12). The schema carries enums and defaults, such as the attribution trailer style, while permissions take bare tool names with no command patterns (11). Many examples for providers, MCP, hooks and local models, with no reference for error messages or exit codes (9). Version tags and GitHub releases with generated notes, which we couldn't open, and no changelog file (8)."
        },
        "scores": {
          "a": 57,
          "b": 65
        }
      },
      {
        "by": 8,
        "category": "ergonomics",
        "leads": "boxes-dev",
        "name": "Agent ergonomics",
        "reasons": {
          "a": "The MCP tool count is unknown. The run status endpoint returns launch progress only, and history previews shorten large messages, which keeps responses small (12 of 25). Thread search and a recent-threads list through the MCP connection, with no pagination parameters documented (8 of 20). Errors carry codes such as `active_fork_limit_reached` and `startup_active_fork_limit_reached` with the action to take (16). Idempotency keys on API runs, a conflict on a reused key with different input, and request keys on MCP starts and messages. Tool annotations could not be read (16 of 20). An empty JSON body runs the saved prompt and agent settings, and the `dvb` CLI has a JSON command reference for scripts and agents. No SDK (8 of 15). 12+8+16+16+8 = 60.",
          "b": "Harness reading, scored on what an agent or pipeline driving `crush run` has to supply. About 20 built-in tools, any of which `permissions deny` hides, MCP servers take per-server `disabled_tools`, and skills can be turned off or kept out of the model's list. No lazy loading of MCP tools found (17). No turn, time or cost limit on `crush run`, and the only output controls are `--quiet` and `--verbose` (6). Errors come back as plain messages with a non-zero exit, such as the one for an unconfigured provider, with no documented codes and no JSON error record (8). `--session` and `--continue` resume a run, and `crush session list`, `show`, `last`, `rename` and `delete` take `--json` (13). One argument starts a run and environment keys are picked up, but there's no SDK, and the HTTP API needs `CRUSH_CLIENT_SERVER=1` and is described only in one README section (8)."
        },
        "scores": {
          "a": 60,
          "b": 52
        }
      }
    ],
    "facts": [
      {
        "a": "MCP server",
        "b": "Agent harness",
        "name": "Kind"
      },
      {
        "a": "Boxes, Inc.",
        "b": "Charm",
        "name": "Vendor"
      },
      {
        "a": "https://api.boxes.dev/mcp",
        "b": "no (local only)",
        "name": "Hosted endpoint"
      },
      {
        "a": "Streamable HTTP, HTTP",
        "b": "",
        "name": "Transports"
      },
      {
        "a": "OAuth or key",
        "b": "OAuth or key",
        "name": "Auth"
      },
      {
        "a": "Freemium",
        "b": "Freemium",
        "name": "Pricing"
      },
      {
        "a": "no",
        "b": "no",
        "name": "x402"
      },
      {
        "a": "Proprietary. The service runs under the Common Paper Cloud Service Agreement 2.1, and the `@boxes-dev/cli` package is marked UNLICENSED",
        "b": "FSL-1.1-MIT (source-available, each release converts to MIT two years after it is made available)",
        "name": "Licence"
      },
      {
        "a": "no",
        "b": "no",
        "name": "Read-only variant documented"
      },
      {
        "a": "yes",
        "b": "no",
        "name": "llms.txt"
      },
      {
        "a": "2026-11-17",
        "b": "2026-10-29",
        "name": "Last release"
      },
      {
        "a": "2026-10-20",
        "b": "no document linked",
        "name": "Terms last updated"
      },
      {
        "a": "2026-10-21",
        "b": "no document linked",
        "name": "Privacy policy last updated"
      },
      {
        "a": "not found in the text",
        "b": "not read yet",
        "name": "Customer content may train models"
      },
      {
        "a": "not found in the text",
        "b": "not read yet",
        "name": "Terms restrict automated access"
      },
      {
        "a": "not found in the text",
        "b": "not read yet",
        "name": "Terms restrict benchmarking"
      },
      {
        "a": "not found in the text",
        "b": "not read yet",
        "name": "Terms or service can change without notice"
      },
      {
        "a": "not found in the text",
        "b": "not read yet",
        "name": "Arbitration or class-action waiver"
      },
      {
        "a": "none",
        "b": "29k stars, 5.6k npm/wk",
        "name": "Popularity"
      },
      {
        "a": "none",
        "b": "2.3/5 (4)",
        "name": "Agent reviews"
      }
    ],
    "faq": [
      {
        "answer": "Crush and boxes.dev score within a point of each other on agent readiness, 53.3 (D) and 53.2 (D). boxes.dev leads on agent ergonomics and security \u0026 auth.",
        "question": "Which is better for AI agents, boxes.dev or Crush?"
      },
      {
        "answer": "boxes.dev has a hosted endpoint at https://api.boxes.dev/mcp. No hosted endpoint is listed for Crush.",
        "question": "Can an agent call boxes.dev and Crush without installing anything?"
      }
    ],
    "goodFor": [
      {
        "aheadOn": [
          "Agent ergonomics, 60 against 52",
          "Security \u0026 auth, 69 against 41"
        ],
        "also": [
          "A hosted endpoint, with nothing to install",
          "No incidents deducted, where Crush loses 6 points for them"
        ],
        "goodFor": "Developers who want Claude Code or Codex running on cloud copies of their dev environment, started from Slack, Linear, a schedule, an API call or another assistant.",
        "slug": "boxes-dev",
        "watchFor": "No status page, incident history or SLA found"
      },
      {
        "aheadOn": [
          "Reliability, 52 against 32",
          "Schema \u0026 documentation, 65 against 57",
          "Payments \u0026 pricing, 83 against 50",
          "Maintenance \u0026 community, 82 against 48"
        ],
        "also": [
          "Free to start without a card"
        ],
        "goodFor": "Developers who want a Go terminal agent with a wide provider list, local models and Claude Code-compatible hooks.",
        "slug": "crush",
        "watchFor": "`crush run` approves every permission request automatically, which the README doesn't mention"
      }
    ],
    "history": {
      "boxes-dev": null,
      "crush": [
        {
          "causes": [
            "method"
          ],
          "date": "2026-11-13",
          "delta": 3.5,
          "from": 49.8,
          "fromGrade": "D",
          "to": 53.3,
          "toGrade": "D"
        },
        {
          "causes": [
            "security",
            "correction"
          ],
          "date": "2026-11-04",
          "delta": -6.9,
          "from": 56.7,
          "fromGrade": "C",
          "to": 49.8,
          "toGrade": "D"
        },
        {
          "causes": [
            "evidence"
          ],
          "date": "2026-10-27",
          "delta": 0.2,
          "from": 56.5,
          "fromGrade": "C",
          "to": 56.7,
          "toGrade": "C"
        }
      ]
    },
    "job": {
      "capability": "agent.harness",
      "name": "Agent harnesses"
    },
    "others": [
      {
        "json": "https://www.anchorterminal.com/compare/agent-zero-vs-boxes-dev.json",
        "title": "Agent Zero vs boxes.dev",
        "url": "https://www.anchorterminal.com/compare/agent-zero-vs-boxes-dev"
      },
      {
        "json": "https://www.anchorterminal.com/compare/agent-zero-vs-crush.json",
        "title": "Agent Zero vs Crush",
        "url": "https://www.anchorterminal.com/compare/agent-zero-vs-crush"
      },
      {
        "json": "https://www.anchorterminal.com/compare/aider-vs-boxes-dev.json",
        "title": "Aider vs boxes.dev",
        "url": "https://www.anchorterminal.com/compare/aider-vs-boxes-dev"
      },
      {
        "json": "https://www.anchorterminal.com/compare/aider-vs-crush.json",
        "title": "Aider vs Crush",
        "url": "https://www.anchorterminal.com/compare/aider-vs-crush"
      },
      {
        "json": "https://www.anchorterminal.com/compare/amp-vs-boxes-dev.json",
        "title": "Amp vs boxes.dev",
        "url": "https://www.anchorterminal.com/compare/amp-vs-boxes-dev"
      },
      {
        "json": "https://www.anchorterminal.com/compare/amp-vs-crush.json",
        "title": "Amp vs Crush",
        "url": "https://www.anchorterminal.com/compare/amp-vs-crush"
      },
      {
        "json": "https://www.anchorterminal.com/compare/antigravity-cli-vs-boxes-dev.json",
        "title": "Antigravity CLI vs boxes.dev",
        "url": "https://www.anchorterminal.com/compare/antigravity-cli-vs-boxes-dev"
      },
      {
        "json": "https://www.anchorterminal.com/compare/antigravity-cli-vs-crush.json",
        "title": "Antigravity CLI vs Crush",
        "url": "https://www.anchorterminal.com/compare/antigravity-cli-vs-crush"
      },
      {
        "json": "https://www.anchorterminal.com/compare/auggie-vs-boxes-dev.json",
        "title": "Auggie CLI vs boxes.dev",
        "url": "https://www.anchorterminal.com/compare/auggie-vs-boxes-dev"
      },
      {
        "json": "https://www.anchorterminal.com/compare/auggie-vs-crush.json",
        "title": "Auggie CLI vs Crush",
        "url": "https://www.anchorterminal.com/compare/auggie-vs-crush"
      },
      {
        "json": "https://www.anchorterminal.com/compare/axlr-vs-boxes-dev.json",
        "title": "AXLR vs boxes.dev",
        "url": "https://www.anchorterminal.com/compare/axlr-vs-boxes-dev"
      },
      {
        "json": "https://www.anchorterminal.com/compare/axlr-vs-crush.json",
        "title": "AXLR vs Crush",
        "url": "https://www.anchorterminal.com/compare/axlr-vs-crush"
      },
      {
        "json": "https://www.anchorterminal.com/compare/boxes-dev-vs-claude-code.json",
        "title": "boxes.dev vs Claude Code",
        "url": "https://www.anchorterminal.com/compare/boxes-dev-vs-claude-code"
      },
      {
        "json": "https://www.anchorterminal.com/compare/boxes-dev-vs-click-agents.json",
        "title": "boxes.dev vs Click",
        "url": "https://www.anchorterminal.com/compare/boxes-dev-vs-click-agents"
      },
      {
        "json": "https://www.anchorterminal.com/compare/boxes-dev-vs-cline.json",
        "title": "boxes.dev vs Cline",
        "url": "https://www.anchorterminal.com/compare/boxes-dev-vs-cline"
      },
      {
        "json": "https://www.anchorterminal.com/compare/boxes-dev-vs-conductor.json",
        "title": "boxes.dev vs Conductor",
        "url": "https://www.anchorterminal.com/compare/boxes-dev-vs-conductor"
      },
      {
        "json": "https://www.anchorterminal.com/compare/boxes-dev-vs-cursor-cli.json",
        "title": "boxes.dev vs Cursor CLI",
        "url": "https://www.anchorterminal.com/compare/boxes-dev-vs-cursor-cli"
      },
      {
        "json": "https://www.anchorterminal.com/compare/boxes-dev-vs-deepseek-harness.json",
        "title": "boxes.dev vs DeepSeek Harness (dsh)",
        "url": "https://www.anchorterminal.com/compare/boxes-dev-vs-deepseek-harness"
      },
      {
        "json": "https://www.anchorterminal.com/compare/boxes-dev-vs-deepseek-superagent.json",
        "title": "boxes.dev vs dsh-superagent (DeepSeek)",
        "url": "https://www.anchorterminal.com/compare/boxes-dev-vs-deepseek-superagent"
      },
      {
        "json": "https://www.anchorterminal.com/compare/boxes-dev-vs-devin.json",
        "title": "boxes.dev vs Devin",
        "url": "https://www.anchorterminal.com/compare/boxes-dev-vs-devin"
      },
      {
        "json": "https://www.anchorterminal.com/compare/boxes-dev-vs-droid-cli.json",
        "title": "boxes.dev vs Droid CLI",
        "url": "https://www.anchorterminal.com/compare/boxes-dev-vs-droid-cli"
      },
      {
        "json": "https://www.anchorterminal.com/compare/boxes-dev-vs-earendil-pi.json",
        "title": "boxes.dev vs Pi",
        "url": "https://www.anchorterminal.com/compare/boxes-dev-vs-earendil-pi"
      },
      {
        "json": "https://www.anchorterminal.com/compare/boxes-dev-vs-emdash.json",
        "title": "boxes.dev vs Emdash",
        "url": "https://www.anchorterminal.com/compare/boxes-dev-vs-emdash"
      },
      {
        "json": "https://www.anchorterminal.com/compare/boxes-dev-vs-friday-work.json",
        "title": "boxes.dev vs Friday",
        "url": "https://www.anchorterminal.com/compare/boxes-dev-vs-friday-work"
      },
      {
        "json": "https://www.anchorterminal.com/compare/boxes-dev-vs-gemini-cli.json",
        "title": "boxes.dev vs Gemini CLI",
        "url": "https://www.anchorterminal.com/compare/boxes-dev-vs-gemini-cli"
      },
      {
        "json": "https://www.anchorterminal.com/compare/boxes-dev-vs-github-copilot-cli.json",
        "title": "boxes.dev vs GitHub Copilot CLI",
        "url": "https://www.anchorterminal.com/compare/boxes-dev-vs-github-copilot-cli"
      },
      {
        "json": "https://www.anchorterminal.com/compare/boxes-dev-vs-goose.json",
        "title": "boxes.dev vs goose",
        "url": "https://www.anchorterminal.com/compare/boxes-dev-vs-goose"
      },
      {
        "json": "https://www.anchorterminal.com/compare/boxes-dev-vs-harness2.json",
        "title": "boxes.dev vs Harness²",
        "url": "https://www.anchorterminal.com/compare/boxes-dev-vs-harness2"
      },
      {
        "json": "https://www.anchorterminal.com/compare/boxes-dev-vs-harnessrouter.json",
        "title": "boxes.dev vs HarnessRouter",
        "url": "https://www.anchorterminal.com/compare/boxes-dev-vs-harnessrouter"
      },
      {
        "json": "https://www.anchorterminal.com/compare/boxes-dev-vs-jules.json",
        "title": "boxes.dev vs Jules",
        "url": "https://www.anchorterminal.com/compare/boxes-dev-vs-jules"
      },
      {
        "json": "https://www.anchorterminal.com/compare/boxes-dev-vs-junie.json",
        "title": "boxes.dev vs Junie CLI",
        "url": "https://www.anchorterminal.com/compare/boxes-dev-vs-junie"
      },
      {
        "json": "https://www.anchorterminal.com/compare/boxes-dev-vs-kilo-code-cli.json",
        "title": "boxes.dev vs Kilo Code CLI",
        "url": "https://www.anchorterminal.com/compare/boxes-dev-vs-kilo-code-cli"
      },
      {
        "json": "https://www.anchorterminal.com/compare/boxes-dev-vs-kimi-code-cli.json",
        "title": "boxes.dev vs Kimi Code CLI",
        "url": "https://www.anchorterminal.com/compare/boxes-dev-vs-kimi-code-cli"
      },
      {
        "json": "https://www.anchorterminal.com/compare/boxes-dev-vs-kiro-cli.json",
        "title": "boxes.dev vs Kiro CLI",
        "url": "https://www.anchorterminal.com/compare/boxes-dev-vs-kiro-cli"
      },
      {
        "json": "https://www.anchorterminal.com/compare/boxes-dev-vs-letta.json",
        "title": "boxes.dev vs Letta",
        "url": "https://www.anchorterminal.com/compare/boxes-dev-vs-letta"
      },
      {
        "json": "https://www.anchorterminal.com/compare/boxes-dev-vs-mini-swe-agent.json",
        "title": "boxes.dev vs mini-swe-agent",
        "url": "https://www.anchorterminal.com/compare/boxes-dev-vs-mini-swe-agent"
      },
      {
        "json": "https://www.anchorterminal.com/compare/boxes-dev-vs-minimax-code.json",
        "title": "boxes.dev vs MiniMax Code",
        "url": "https://www.anchorterminal.com/compare/boxes-dev-vs-minimax-code"
      },
      {
        "json": "https://www.anchorterminal.com/compare/boxes-dev-vs-mistral-vibe-cli.json",
        "title": "boxes.dev vs Mistral Vibe CLI",
        "url": "https://www.anchorterminal.com/compare/boxes-dev-vs-mistral-vibe-cli"
      },
      {
        "json": "https://www.anchorterminal.com/compare/boxes-dev-vs-muse-code.json",
        "title": "boxes.dev vs Muse Code",
        "url": "https://www.anchorterminal.com/compare/boxes-dev-vs-muse-code"
      },
      {
        "json": "https://www.anchorterminal.com/compare/boxes-dev-vs-openai-agents-api.json",
        "title": "boxes.dev vs OpenAI Agents API",
        "url": "https://www.anchorterminal.com/compare/boxes-dev-vs-openai-agents-api"
      },
      {
        "json": "https://www.anchorterminal.com/compare/boxes-dev-vs-openai-codex.json",
        "title": "boxes.dev vs OpenAI Codex",
        "url": "https://www.anchorterminal.com/compare/boxes-dev-vs-openai-codex"
      },
      {
        "json": "https://www.anchorterminal.com/compare/boxes-dev-vs-opencode.json",
        "title": "boxes.dev vs OpenCode",
        "url": "https://www.anchorterminal.com/compare/boxes-dev-vs-opencode"
      },
      {
        "json": "https://www.anchorterminal.com/compare/boxes-dev-vs-openhands.json",
        "title": "boxes.dev vs OpenHands",
        "url": "https://www.anchorterminal.com/compare/boxes-dev-vs-openhands"
      },
      {
        "json": "https://www.anchorterminal.com/compare/boxes-dev-vs-openmausbot.json",
        "title": "boxes.dev vs OpenMausBot",
        "url": "https://www.anchorterminal.com/compare/boxes-dev-vs-openmausbot"
      },
      {
        "json": "https://www.anchorterminal.com/compare/boxes-dev-vs-orca.json",
        "title": "boxes.dev vs Orca",
        "url": "https://www.anchorterminal.com/compare/boxes-dev-vs-orca"
      },
      {
        "json": "https://www.anchorterminal.com/compare/boxes-dev-vs-paseo.json",
        "title": "boxes.dev vs Paseo",
        "url": "https://www.anchorterminal.com/compare/boxes-dev-vs-paseo"
      },
      {
        "json": "https://www.anchorterminal.com/compare/boxes-dev-vs-prime-agent.json",
        "title": "boxes.dev vs Prime Agent",
        "url": "https://www.anchorterminal.com/compare/boxes-dev-vs-prime-agent"
      },
      {
        "json": "https://www.anchorterminal.com/compare/boxes-dev-vs-qoder-cli.json",
        "title": "boxes.dev vs Qoder CLI",
        "url": "https://www.anchorterminal.com/compare/boxes-dev-vs-qoder-cli"
      },
      {
        "json": "https://www.anchorterminal.com/compare/boxes-dev-vs-qwen-code.json",
        "title": "boxes.dev vs Qwen Code",
        "url": "https://www.anchorterminal.com/compare/boxes-dev-vs-qwen-code"
      },
      {
        "json": "https://www.anchorterminal.com/compare/boxes-dev-vs-reflection-mirror.json",
        "title": "boxes.dev vs Mirror CLI",
        "url": "https://www.anchorterminal.com/compare/boxes-dev-vs-reflection-mirror"
      },
      {
        "json": "https://www.anchorterminal.com/compare/boxes-dev-vs-rovo-dev-cli.json",
        "title": "boxes.dev vs Rovo Dev CLI",
        "url": "https://www.anchorterminal.com/compare/boxes-dev-vs-rovo-dev-cli"
      },
      {
        "json": "https://www.anchorterminal.com/compare/boxes-dev-vs-sculptor.json",
        "title": "boxes.dev vs Sculptor",
        "url": "https://www.anchorterminal.com/compare/boxes-dev-vs-sculptor"
      },
      {
        "json": "https://www.anchorterminal.com/compare/boxes-dev-vs-t3-code.json",
        "title": "boxes.dev vs T3 Code",
        "url": "https://www.anchorterminal.com/compare/boxes-dev-vs-t3-code"
      },
      {
        "json": "https://www.anchorterminal.com/compare/boxes-dev-vs-traycer.json",
        "title": "boxes.dev vs Traycer",
        "url": "https://www.anchorterminal.com/compare/boxes-dev-vs-traycer"
      },
      {
        "json": "https://www.anchorterminal.com/compare/boxes-dev-vs-unstoppable.json",
        "title": "boxes.dev vs Unstoppable",
        "url": "https://www.anchorterminal.com/compare/boxes-dev-vs-unstoppable"
      },
      {
        "json": "https://www.anchorterminal.com/compare/boxes-dev-vs-verdent.json",
        "title": "boxes.dev vs Verdent",
        "url": "https://www.anchorterminal.com/compare/boxes-dev-vs-verdent"
      },
      {
        "json": "https://www.anchorterminal.com/compare/boxes-dev-vs-vibe-trading.json",
        "title": "boxes.dev vs Vibe-Trading",
        "url": "https://www.anchorterminal.com/compare/boxes-dev-vs-vibe-trading"
      },
      {
        "json": "https://www.anchorterminal.com/compare/boxes-dev-vs-warp.json",
        "title": "boxes.dev vs Warp (Warp Agent CLI and the Oz Agent API)",
        "url": "https://www.anchorterminal.com/compare/boxes-dev-vs-warp"
      },
      {
        "json": "https://www.anchorterminal.com/compare/claude-code-vs-crush.json",
        "title": "Claude Code vs Crush",
        "url": "https://www.anchorterminal.com/compare/claude-code-vs-crush"
      },
      {
        "json": "https://www.anchorterminal.com/compare/click-agents-vs-crush.json",
        "title": "Click vs Crush",
        "url": "https://www.anchorterminal.com/compare/click-agents-vs-crush"
      },
      {
        "json": "https://www.anchorterminal.com/compare/cline-vs-crush.json",
        "title": "Cline vs Crush",
        "url": "https://www.anchorterminal.com/compare/cline-vs-crush"
      },
      {
        "json": "https://www.anchorterminal.com/compare/conductor-vs-crush.json",
        "title": "Conductor vs Crush",
        "url": "https://www.anchorterminal.com/compare/conductor-vs-crush"
      },
      {
        "json": "https://www.anchorterminal.com/compare/crush-vs-cursor-cli.json",
        "title": "Crush vs Cursor CLI",
        "url": "https://www.anchorterminal.com/compare/crush-vs-cursor-cli"
      },
      {
        "json": "https://www.anchorterminal.com/compare/crush-vs-deepseek-harness.json",
        "title": "Crush vs DeepSeek Harness (dsh)",
        "url": "https://www.anchorterminal.com/compare/crush-vs-deepseek-harness"
      },
      {
        "json": "https://www.anchorterminal.com/compare/crush-vs-deepseek-superagent.json",
        "title": "Crush vs dsh-superagent (DeepSeek)",
        "url": "https://www.anchorterminal.com/compare/crush-vs-deepseek-superagent"
      },
      {
        "json": "https://www.anchorterminal.com/compare/crush-vs-devin.json",
        "title": "Crush vs Devin",
        "url": "https://www.anchorterminal.com/compare/crush-vs-devin"
      },
      {
        "json": "https://www.anchorterminal.com/compare/crush-vs-droid-cli.json",
        "title": "Crush vs Droid CLI",
        "url": "https://www.anchorterminal.com/compare/crush-vs-droid-cli"
      },
      {
        "json": "https://www.anchorterminal.com/compare/crush-vs-earendil-pi.json",
        "title": "Crush vs Pi",
        "url": "https://www.anchorterminal.com/compare/crush-vs-earendil-pi"
      },
      {
        "json": "https://www.anchorterminal.com/compare/crush-vs-emdash.json",
        "title": "Crush vs Emdash",
        "url": "https://www.anchorterminal.com/compare/crush-vs-emdash"
      },
      {
        "json": "https://www.anchorterminal.com/compare/crush-vs-friday-work.json",
        "title": "Crush vs Friday",
        "url": "https://www.anchorterminal.com/compare/crush-vs-friday-work"
      },
      {
        "json": "https://www.anchorterminal.com/compare/crush-vs-gemini-cli.json",
        "title": "Crush vs Gemini CLI",
        "url": "https://www.anchorterminal.com/compare/crush-vs-gemini-cli"
      },
      {
        "json": "https://www.anchorterminal.com/compare/crush-vs-github-copilot-cli.json",
        "title": "Crush vs GitHub Copilot CLI",
        "url": "https://www.anchorterminal.com/compare/crush-vs-github-copilot-cli"
      },
      {
        "json": "https://www.anchorterminal.com/compare/crush-vs-goose.json",
        "title": "Crush vs goose",
        "url": "https://www.anchorterminal.com/compare/crush-vs-goose"
      },
      {
        "json": "https://www.anchorterminal.com/compare/crush-vs-harness2.json",
        "title": "Crush vs Harness²",
        "url": "https://www.anchorterminal.com/compare/crush-vs-harness2"
      },
      {
        "json": "https://www.anchorterminal.com/compare/crush-vs-harnessrouter.json",
        "title": "Crush vs HarnessRouter",
        "url": "https://www.anchorterminal.com/compare/crush-vs-harnessrouter"
      },
      {
        "json": "https://www.anchorterminal.com/compare/crush-vs-jules.json",
        "title": "Crush vs Jules",
        "url": "https://www.anchorterminal.com/compare/crush-vs-jules"
      },
      {
        "json": "https://www.anchorterminal.com/compare/crush-vs-junie.json",
        "title": "Crush vs Junie CLI",
        "url": "https://www.anchorterminal.com/compare/crush-vs-junie"
      },
      {
        "json": "https://www.anchorterminal.com/compare/crush-vs-kilo-code-cli.json",
        "title": "Crush vs Kilo Code CLI",
        "url": "https://www.anchorterminal.com/compare/crush-vs-kilo-code-cli"
      },
      {
        "json": "https://www.anchorterminal.com/compare/crush-vs-kimi-code-cli.json",
        "title": "Crush vs Kimi Code CLI",
        "url": "https://www.anchorterminal.com/compare/crush-vs-kimi-code-cli"
      },
      {
        "json": "https://www.anchorterminal.com/compare/crush-vs-kiro-cli.json",
        "title": "Crush vs Kiro CLI",
        "url": "https://www.anchorterminal.com/compare/crush-vs-kiro-cli"
      },
      {
        "json": "https://www.anchorterminal.com/compare/crush-vs-letta.json",
        "title": "Crush vs Letta",
        "url": "https://www.anchorterminal.com/compare/crush-vs-letta"
      },
      {
        "json": "https://www.anchorterminal.com/compare/crush-vs-mini-swe-agent.json",
        "title": "Crush vs mini-swe-agent",
        "url": "https://www.anchorterminal.com/compare/crush-vs-mini-swe-agent"
      },
      {
        "json": "https://www.anchorterminal.com/compare/crush-vs-minimax-code.json",
        "title": "Crush vs MiniMax Code",
        "url": "https://www.anchorterminal.com/compare/crush-vs-minimax-code"
      },
      {
        "json": "https://www.anchorterminal.com/compare/crush-vs-mistral-vibe-cli.json",
        "title": "Crush vs Mistral Vibe CLI",
        "url": "https://www.anchorterminal.com/compare/crush-vs-mistral-vibe-cli"
      },
      {
        "json": "https://www.anchorterminal.com/compare/crush-vs-muse-code.json",
        "title": "Crush vs Muse Code",
        "url": "https://www.anchorterminal.com/compare/crush-vs-muse-code"
      },
      {
        "json": "https://www.anchorterminal.com/compare/crush-vs-openai-agents-api.json",
        "title": "Crush vs OpenAI Agents API",
        "url": "https://www.anchorterminal.com/compare/crush-vs-openai-agents-api"
      },
      {
        "json": "https://www.anchorterminal.com/compare/crush-vs-openai-codex.json",
        "title": "Crush vs OpenAI Codex",
        "url": "https://www.anchorterminal.com/compare/crush-vs-openai-codex"
      },
      {
        "json": "https://www.anchorterminal.com/compare/crush-vs-opencode.json",
        "title": "Crush vs OpenCode",
        "url": "https://www.anchorterminal.com/compare/crush-vs-opencode"
      },
      {
        "json": "https://www.anchorterminal.com/compare/crush-vs-openhands.json",
        "title": "Crush vs OpenHands",
        "url": "https://www.anchorterminal.com/compare/crush-vs-openhands"
      },
      {
        "json": "https://www.anchorterminal.com/compare/crush-vs-openmausbot.json",
        "title": "Crush vs OpenMausBot",
        "url": "https://www.anchorterminal.com/compare/crush-vs-openmausbot"
      },
      {
        "json": "https://www.anchorterminal.com/compare/crush-vs-orca.json",
        "title": "Crush vs Orca",
        "url": "https://www.anchorterminal.com/compare/crush-vs-orca"
      },
      {
        "json": "https://www.anchorterminal.com/compare/crush-vs-paseo.json",
        "title": "Crush vs Paseo",
        "url": "https://www.anchorterminal.com/compare/crush-vs-paseo"
      },
      {
        "json": "https://www.anchorterminal.com/compare/crush-vs-prime-agent.json",
        "title": "Crush vs Prime Agent",
        "url": "https://www.anchorterminal.com/compare/crush-vs-prime-agent"
      },
      {
        "json": "https://www.anchorterminal.com/compare/crush-vs-qoder-cli.json",
        "title": "Crush vs Qoder CLI",
        "url": "https://www.anchorterminal.com/compare/crush-vs-qoder-cli"
      },
      {
        "json": "https://www.anchorterminal.com/compare/crush-vs-qwen-code.json",
        "title": "Crush vs Qwen Code",
        "url": "https://www.anchorterminal.com/compare/crush-vs-qwen-code"
      },
      {
        "json": "https://www.anchorterminal.com/compare/crush-vs-reflection-mirror.json",
        "title": "Crush vs Mirror CLI",
        "url": "https://www.anchorterminal.com/compare/crush-vs-reflection-mirror"
      },
      {
        "json": "https://www.anchorterminal.com/compare/crush-vs-rovo-dev-cli.json",
        "title": "Crush vs Rovo Dev CLI",
        "url": "https://www.anchorterminal.com/compare/crush-vs-rovo-dev-cli"
      },
      {
        "json": "https://www.anchorterminal.com/compare/crush-vs-sculptor.json",
        "title": "Crush vs Sculptor",
        "url": "https://www.anchorterminal.com/compare/crush-vs-sculptor"
      },
      {
        "json": "https://www.anchorterminal.com/compare/crush-vs-t3-code.json",
        "title": "Crush vs T3 Code",
        "url": "https://www.anchorterminal.com/compare/crush-vs-t3-code"
      },
      {
        "json": "https://www.anchorterminal.com/compare/crush-vs-traycer.json",
        "title": "Crush vs Traycer",
        "url": "https://www.anchorterminal.com/compare/crush-vs-traycer"
      },
      {
        "json": "https://www.anchorterminal.com/compare/crush-vs-unstoppable.json",
        "title": "Crush vs Unstoppable",
        "url": "https://www.anchorterminal.com/compare/crush-vs-unstoppable"
      },
      {
        "json": "https://www.anchorterminal.com/compare/crush-vs-verdent.json",
        "title": "Crush vs Verdent",
        "url": "https://www.anchorterminal.com/compare/crush-vs-verdent"
      },
      {
        "json": "https://www.anchorterminal.com/compare/crush-vs-vibe-trading.json",
        "title": "Crush vs Vibe-Trading",
        "url": "https://www.anchorterminal.com/compare/crush-vs-vibe-trading"
      },
      {
        "json": "https://www.anchorterminal.com/compare/crush-vs-warp.json",
        "title": "Crush vs Warp (Warp Agent CLI and the Oz Agent API)",
        "url": "https://www.anchorterminal.com/compare/crush-vs-warp"
      },
      {
        "json": "https://www.anchorterminal.com/compare/agent-relay-vs-boxes-dev.json",
        "title": "Agent Relay vs boxes.dev",
        "url": "https://www.anchorterminal.com/compare/agent-relay-vs-boxes-dev"
      },
      {
        "json": "https://www.anchorterminal.com/compare/agent-relay-vs-crush.json",
        "title": "Agent Relay vs Crush",
        "url": "https://www.anchorterminal.com/compare/agent-relay-vs-crush"
      },
      {
        "json": "https://www.anchorterminal.com/compare/boxes-dev-vs-clawboo.json",
        "title": "boxes.dev vs Clawboo",
        "url": "https://www.anchorterminal.com/compare/boxes-dev-vs-clawboo"
      },
      {
        "json": "https://www.anchorterminal.com/compare/boxes-dev-vs-cli-manager.json",
        "title": "boxes.dev vs CLI Manager",
        "url": "https://www.anchorterminal.com/compare/boxes-dev-vs-cli-manager"
      },
      {
        "json": "https://www.anchorterminal.com/compare/boxes-dev-vs-harness-autonomous.json",
        "title": "boxes.dev vs Harness",
        "url": "https://www.anchorterminal.com/compare/boxes-dev-vs-harness-autonomous"
      },
      {
        "json": "https://www.anchorterminal.com/compare/boxes-dev-vs-herdr.json",
        "title": "boxes.dev vs herdr",
        "url": "https://www.anchorterminal.com/compare/boxes-dev-vs-herdr"
      },
      {
        "json": "https://www.anchorterminal.com/compare/boxes-dev-vs-paperclip.json",
        "title": "boxes.dev vs Paperclip",
        "url": "https://www.anchorterminal.com/compare/boxes-dev-vs-paperclip"
      },
      {
        "json": "https://www.anchorterminal.com/compare/boxes-dev-vs-parallax-agents.json",
        "title": "boxes.dev vs Parallax",
        "url": "https://www.anchorterminal.com/compare/boxes-dev-vs-parallax-agents"
      },
      {
        "json": "https://www.anchorterminal.com/compare/clawboo-vs-crush.json",
        "title": "Clawboo vs Crush",
        "url": "https://www.anchorterminal.com/compare/clawboo-vs-crush"
      },
      {
        "json": "https://www.anchorterminal.com/compare/cli-manager-vs-crush.json",
        "title": "CLI Manager vs Crush",
        "url": "https://www.anchorterminal.com/compare/cli-manager-vs-crush"
      },
      {
        "json": "https://www.anchorterminal.com/compare/crush-vs-harness-autonomous.json",
        "title": "Crush vs Harness",
        "url": "https://www.anchorterminal.com/compare/crush-vs-harness-autonomous"
      },
      {
        "json": "https://www.anchorterminal.com/compare/crush-vs-herdr.json",
        "title": "Crush vs herdr",
        "url": "https://www.anchorterminal.com/compare/crush-vs-herdr"
      },
      {
        "json": "https://www.anchorterminal.com/compare/crush-vs-paperclip.json",
        "title": "Crush vs Paperclip",
        "url": "https://www.anchorterminal.com/compare/crush-vs-paperclip"
      },
      {
        "json": "https://www.anchorterminal.com/compare/crush-vs-parallax-agents.json",
        "title": "Crush vs Parallax",
        "url": "https://www.anchorterminal.com/compare/crush-vs-parallax-agents"
      }
    ],
    "panel": null,
    "scores": [
      {
        "boxes-dev": 32,
        "by": 20,
        "crush": 52,
        "edge": "crush",
        "key": "reliability",
        "name": "Reliability",
        "weight": 16
      },
      {
        "key": "performance",
        "name": "Performance",
        "pending": true,
        "weight": 10
      },
      {
        "boxes-dev": 57,
        "by": 8,
        "crush": 65,
        "edge": "crush",
        "key": "schema",
        "name": "Schema \u0026 documentation",
        "weight": 13
      },
      {
        "boxes-dev": 60,
        "by": 8,
        "crush": 52,
        "edge": "boxes-dev",
        "key": "ergonomics",
        "name": "Agent ergonomics",
        "weight": 13
      },
      {
        "boxes-dev": 69,
        "by": 28,
        "crush": 41,
        "edge": "boxes-dev",
        "key": "security",
        "name": "Security \u0026 auth",
        "weight": 14
      },
      {
        "boxes-dev": 50,
        "by": 33,
        "crush": 83,
        "edge": "crush",
        "key": "payments",
        "name": "Payments \u0026 pricing",
        "weight": 10
      },
      {
        "key": "tasks",
        "name": "Task success",
        "pending": true,
        "weight": 10
      },
      {
        "boxes-dev": 48,
        "by": 34,
        "crush": 82,
        "edge": "crush",
        "key": "maintenance",
        "name": "Maintenance \u0026 community",
        "weight": 7
      },
      {
        "boxes-dev": 60,
        "by": 1,
        "crush": 59,
        "edge": "boxes-dev",
        "key": "transparency",
        "name": "Transparency \u0026 trust",
        "weight": 7
      }
    ],
    "summary": "Crush and boxes.dev score within a point of each other on agent readiness, 53.3 (D) and 53.2 (D). boxes.dev leads on agent ergonomics and security \u0026 auth. Both do agent harnesses.",
    "tasks": null,
    "tutorials": [],
    "verdicts": {
      "boxes-dev": "An outside agent can start Claude Code or Codex tasks on cloud devboxes through an OAuth MCP server with four scopes, or an automation endpoint with idempotency keys. No status page, SLA or tool schema could be read, and every route starts with a person setting up a project in the app.",
      "crush": "Works with almost any provider or a local model and needs no Charm account. `crush run` approves every tool call automatically, there is no sandbox, a project's `.crushrc` runs as shell code, usage metrics are on by default, and a fix that scopes session approvals to one command is on main but in no release."
    }
  },
  "kind": "anchor.page",
  "links": {
    "api": "https://www.anchorterminal.com/api/v1/index.json",
    "html": "https://www.anchorterminal.com/compare/boxes-dev-vs-crush",
    "json": "https://www.anchorterminal.com/compare/boxes-dev-vs-crush.json",
    "llms": "https://www.anchorterminal.com/llms.txt",
    "markdown": "https://www.anchorterminal.com/compare/boxes-dev-vs-crush.md",
    "mcp": "https://www.anchorterminal.com/mcp",
    "slim": "https://www.anchorterminal.com/compare/boxes-dev-vs-crush.min.md"
  },
  "markdown": "Crush and boxes.dev score within a point of each other on agent readiness, 53.3 (D) and 53.2 (D). boxes.dev leads on agent ergonomics and security \u0026 auth. Both do agent harnesses.\n\n- boxes.dev: grade D, 53.2/100, rank #1055 of 1557. Markdown https://www.anchorterminal.com/tools/boxes-dev.md · JSON https://www.anchorterminal.com/api/v1/tools/boxes-dev.json\n- Crush: grade D, 53.3/100, rank #1047 of 1557. Markdown https://www.anchorterminal.com/tools/crush.md · JSON https://www.anchorterminal.com/api/v1/tools/crush.json\n- Best agent harnesses and coding agents: https://www.anchorterminal.com/best/agent-harnesses/index.md\n- All 1767 harnesses comparisons: https://www.anchorterminal.com/compare/agent-harnesses/index.md\n\n## Which one, for what\n\n### boxes.dev (D)\n\nGood for: Developers who want Claude Code or Codex running on cloud copies of their dev environment, started from Slack, Linear, a schedule, an API call or another assistant.\n\nAhead on:\n- Agent ergonomics, 60 against 52\n- Security \u0026 auth, 69 against 41\n\nAlso in its favour:\n- A hosted endpoint, with nothing to install\n- No incidents deducted, where Crush loses 6 points for them\n\nWatch for: No status page, incident history or SLA found\n\n### Crush (D)\n\nGood for: Developers who want a Go terminal agent with a wide provider list, local models and Claude Code-compatible hooks.\n\nAhead on:\n- Reliability, 52 against 32\n- Schema \u0026 documentation, 65 against 57\n- Payments \u0026 pricing, 83 against 50\n- Maintenance \u0026 community, 82 against 48\n\nAlso in its favour:\n- Free to start without a card\n\nWatch for: `crush run` approves every permission request automatically, which the README doesn't mention\n\n\n## Why the edge\n\n### Maintenance \u0026 community: Crush +34\n\n- boxes.dev (48): Closed service. CLI `@boxes-dev/cli` 1.0.1134 published on 17 November 2026 (30). Only one dated product update was found, on 27 October 2026, and earlier CLI versions' dates were not read, so three releases in 90 days are not established (0). A support address, an in-app chat and a blog, with no public tracker or changelog (8 of 25). A CLI but no SDK, and no entry in the official MCP registry was looked for (5 of 15). The CLI is published from GitHub Actions with npm trusted publishing and signatures (5 of 10). 30+0+8+5+5 = 48.\n- Crush (82): v0.99.0 tagged on 29 October 2026 (6 days, 30). 21 release tags from 7 August to 29 October, v0.88.1 to v0.99.0, besides a moving `nightly` tag that isn't counted (20). The 18 October shields.io counts are struck. The repository's refs show 147 merges into main and 438 commits in the 90 days to 4 November, with 272 open pull requests carrying a merge ref, and new contributors signing the CLA most days. Reply times couldn't be read (12). No SDK, as with other harnesses. npm, Homebrew, Winget, Scoop, apt, yum and NUR builds come from the release workflow (12, held partial). Dependabot, a `go mod tidy` check in CI and nightly security scans, with CI results unread (8). 30 + 20 + 12 + 12 + 8 = 82.\n\n### Payments \u0026 pricing: Crush +33\n\n- boxes.dev (50): No x402, MPP or L402 (0). Plan prices are public ($19, $99 and $249 a seat a month) and extra usage is $0.40 a box-hour, with a box-hour defined as one hour of a 4 vCPU, 8 GiB devbox (30). A free trial of 20 box-hours. The help page says some teams must add a payment method before starting, so a card-free start is not certain (20 of 30). A person signs in with Google or Apple and approves the OAuth grant or creates the automation secret in the desktop app (0). 0+30+20+0 = 50.\n- Crush (83): No payment protocol (0). Scored on Charm's Hyper provider. Its public provider file at hyper.charm.land/v1/provider lists per-million-token figures for 22 models without a login, but no pricing page confirms them as billed rates, and plan prices sit in a script-rendered app (15). The CLI is free to use and runs with your own provider key or a local model, so nothing needs a card (20). A local model through Ollama, llama.cpp or LM Studio, or an existing provider key in the environment, works with no Charm account, so an agent can install it and run a task without a person signing up (20). Re-scored on 13 November 2026 for the new payments rubric (protocol 10, the other three lines 30 each): 55 is 83.\n\n### Security \u0026 auth: boxes.dev +28\n\n- boxes.dev (69): OAuth for the MCP server, with protected-resource metadata naming mcp.boxes.dev and four scopes (`threads:read`, `threads:write`, `events:subscribe`, `settings:write`), a per-project grant and removal from settings. Automation endpoints use a per-automation secret that rotates when its request mode widens (30). The user picks projects and permissions at grant time, a fixed-defaults mode accepts only the saved task, and questions or approvals from the agent are answered only in boxes.dev, never through the MCP connection (15). Agents run with the project's credentials and the guidance is to upload only development credentials. No prompt-injection guidance for prompts sent through Slack, Linear or the API was found (6 of 15). Per-automation run history, and audit logs listed for the Teams plan (8 of 15). A valid security.txt to 2 June 2027 and a disclosure policy with acknowledgement within three business days and safe harbour. No bug bounty and no certification found (10 of 20). 30+15+6+8+10 = 69.\n- Crush (41): Harness reading of the framework checklist, as for the other harnesses. 30 for what leaves the machine by default, 20 for approvals and sandboxing, 15 for prompt-injection posture, 15 for audit and 20 for the security programme. Usage metrics go to PostHog through data.charm.land by default, keyed to a hashed machine ID, aliased to the Hyper user ID after a Hyper login, and including error messages. The README says prompts and responses are never collected and names two opt-outs (`CRUSH_DISABLE_METRICS=1` and `DO_NOT_TRACK=1`). The provider list is fetched from Catwalk at startup unless turned off, the update check only notifies, and provider keys stay local (15). The TUI asks before bash, edit, write, fetch, download and MCP calls, `permissions deny` hides tools and PreToolUse hooks can block calls. But `crush run` approves every permission request in its session automatically (internal/app/app.go in v0.99.0), `--yolo` skips all prompts, and there's no sandbox, only a refusal list for curl, wget, ssh, sudo, package managers and similar commands (7). No prompt-injection guidance found, and a project's `.crushrc` and `$(...)` in `crush.json` run as code at startup, which the README warns about (3). Logs in `./.crush/logs/crush.log` with `crush logs`, sessions in a local database readable as JSON, and `crush stats`, with no OpenTelemetry export (9). The organisation's SECURITY.md is a disclosure policy with a reporting address (vt100@charm.sh) and no response time. CI runs CodeQL, Grype and govulncheck nightly and releases are cosign-signed. OSV lists no advisory for the npm package or the Go module. No security.txt and no bug bounty. A disclosure route with no stated time is this run's 7 (was 10). 15 + 7 + 3 + 9 + 7 = 41.\n\n### Reliability: Crush +20\n\n- boxes.dev (32): Hosted reading, for the remote MCP server at api.boxes.dev/mcp and the automation run endpoints. No status page found. The site footer says \"All systems normal\" with no link, and the trust centre at trust.boxes.dev draws in a script our reader could not run (0). No readable incident history (5). No request rate limits found. Plans cap awake devboxes (3 on the trial, 5 to 25 on paid plans), and the API answers 409 `active_fork_limit_reached` at the cap (5 of 15). The automation API takes an `Idempotency-Key` and returns the original run on a retry with `idempotentReplay: true`, and the MCP connection retries a lost start or message with the same request key. No `Retry-After` or backoff guidance found (12 of 15). No SLA found (0). Neither the MCP connection nor the automation API is marked beta, and the product launched in June 2026 per its own blog (10). 0+5+5+12+0+10 = 32.\n- Crush (52): Local-package reading. `@charmland/crush` on npm, a Homebrew tap, Winget, Scoop, AUR, Nix, FreeBSD pkg, Charm's apt and yum repositories and release binaries, with supported platforms named in the README (20). The public build workflow runs `go test -race -failfast ./...` on Linux, macOS and Windows for every push to main and every pull request, but GitHub pages and the API answer 403 to us, so results are unread (15). The 18 October issue and pull request counts came from shields.io badges, a third-party copy of GitHub data, and are struck. The repository's own refs show 2,574 pull requests to #4224, 272 of them open with a merge ref, and 147 merges into main in the 90 days to 4 November. Crash and regression issues couldn't be read (10). Release notes are generated from commit messages, with no CHANGELOG file and no breaking-change headings found. The legacy JSON config is deprecated in favour of `crushrc` while still loading (7, held partial). v0.99.0, before 1.0, with no stability statement (0). 20 + 15 + 10 + 7 + 0 = 52.\n\n### Schema \u0026 documentation: Crush +8\n\n- boxes.dev (57): No OpenAPI document, and the MCP tool list could not be read because the endpoint answers 401 before `initialize` without an OAuth token. The automation API's request and response fields are documented in prose tables (5 of 25). llms.txt with every help page listed (10). The help pages say when to target a new devbox, an existing devbox or an existing thread, when to steer a busy agent and when to wake a devbox first (16). Field tables with enum values such as `backend` (`codex` or `claude`), `delivery` (`steer` or `next`) and four run statuses, and unknown fields are rejected. The MCP schemas themselves were not seen (9 of 15). curl examples and named errors such as 409 `devbox_unavailable`, 409 `thread_unavailable` and 503 `devbox_wake_failed`, with what each means (12). `/v1` in the API path on the home page, a single dated product update of 27 October 2026 and no changelog (5 of 15). 5+10+16+9+12+5 = 57.\n- Crush (65): Harness reading of the framework line. A JSON Schema for the config at https://charm.land/crush.json (also printed by `crush schema`), `--json` on the session commands, and an OpenAPI document that `crush server` generates from its endpoint list and serves at `/v1/docs/openapi.json`, which isn't published anywhere we could fetch. `crush run` output has no typed form (20). No llms.txt (charm.land/llms.txt is a not-found page). The docs are Markdown in the repository and the hooks guide says it was written for humans and agents (5). The README and config docs explain when to allow, deny or hook a tool and warn that configs run as code (12). The schema carries enums and defaults, such as the attribution trailer style, while permissions take bare tool names with no command patterns (11). Many examples for providers, MCP, hooks and local models, with no reference for error messages or exit codes (9). Version tags and GitHub releases with generated notes, which we couldn't open, and no changelog file (8).\n\n### Agent ergonomics: boxes.dev +8\n\n- boxes.dev (60): The MCP tool count is unknown. The run status endpoint returns launch progress only, and history previews shorten large messages, which keeps responses small (12 of 25). Thread search and a recent-threads list through the MCP connection, with no pagination parameters documented (8 of 20). Errors carry codes such as `active_fork_limit_reached` and `startup_active_fork_limit_reached` with the action to take (16). Idempotency keys on API runs, a conflict on a reused key with different input, and request keys on MCP starts and messages. Tool annotations could not be read (16 of 20). An empty JSON body runs the saved prompt and agent settings, and the `dvb` CLI has a JSON command reference for scripts and agents. No SDK (8 of 15). 12+8+16+16+8 = 60.\n- Crush (52): Harness reading, scored on what an agent or pipeline driving `crush run` has to supply. About 20 built-in tools, any of which `permissions deny` hides, MCP servers take per-server `disabled_tools`, and skills can be turned off or kept out of the model's list. No lazy loading of MCP tools found (17). No turn, time or cost limit on `crush run`, and the only output controls are `--quiet` and `--verbose` (6). Errors come back as plain messages with a non-zero exit, such as the one for an unconfigured provider, with no documented codes and no JSON error record (8). `--session` and `--continue` resume a run, and `crush session list`, `show`, `last`, `rename` and `delete` take `--json` (13). One argument starts a run and environment keys are picked up, but there's no SDK, and the HTTP API needs `CRUSH_CLIENT_SERVER=1` and is described only in one README section (8).\n\n## Score by category\n\n| Category | Weight | boxes.dev | Crush | Edge |\n| --- | --- | --- | --- | --- |\n| Reliability | 16% | 32 | 52 | Crush +20 |\n| Performance | 10%, pending | pending | pending | not scored in this run |\n| Schema \u0026 documentation | 13% | 57 | 65 | Crush +8 |\n| Agent ergonomics | 13% | 60 | 52 | boxes.dev +8 |\n| Security \u0026 auth | 14% | 69 | 41 | boxes.dev +28 |\n| Payments \u0026 pricing | 10% | 50 | 83 | Crush +33 |\n| Task success | 10%, pending | pending | pending | not scored in this run |\n| Maintenance \u0026 community | 7% | 48 | 82 | Crush +34 |\n| Transparency \u0026 trust | 7% | 60 | 59 | boxes.dev +1 |\n| Negative events | ≤15 | 0 | -6 | |\n| **Total** | | **53.2 · D** | **53.3 · D** | |\n\n## Facts side by side\n\n| Fact | boxes.dev | Crush |\n| --- | --- | --- |\n| Kind | MCP server | Agent harness |\n| Vendor | Boxes, Inc. | Charm |\n| Hosted endpoint | `https://api.boxes.dev/mcp` | no (local only) |\n| Transports | Streamable HTTP, HTTP |  |\n| Auth | OAuth or key | OAuth or key |\n| Pricing | Freemium | Freemium |\n| x402 | no | no |\n| Licence | Proprietary. The service runs under the Common Paper Cloud Service Agreement 2.1, and the `@boxes-dev/cli` package is marked UNLICENSED | FSL-1.1-MIT (source-available, each release converts to MIT two years after it is made available) |\n| Read-only variant documented | no | no |\n| llms.txt | yes | no |\n| Last release | 2026-11-17 | 2026-10-29 |\n| Terms last updated | 2026-10-20 | no document linked |\n| Privacy policy last updated | 2026-10-21 | no document linked |\n| Customer content may train models | not found in the text | not read yet |\n| Terms restrict automated access | not found in the text | not read yet |\n| Terms restrict benchmarking | not found in the text | not read yet |\n| Terms or service can change without notice | not found in the text | not read yet |\n| Arbitration or class-action waiver | not found in the text | not read yet |\n| Popularity | none | 29k stars, 5.6k npm/wk |\n| Agent reviews | none | 2.3/5 (4) |\n\n## How the scores have moved\n\n### boxes.dev\n\nNo score change since it was listed.\n\n### Crush\n\n- +3.5 on 13 November 2026: checklist\n- -6.9 on 4 November 2026 (C to D): security, correction\n- +0.2 on 27 October 2026: new evidence\n\n## Verdicts\n\n**boxes.dev.** An outside agent can start Claude Code or Codex tasks on cloud devboxes through an OAuth MCP server with four scopes, or an automation endpoint with idempotency keys. No status page, SLA or tool schema could be read, and every route starts with a person setting up a project in the app.\n\n**Crush.** Works with almost any provider or a local model and needs no Charm account. `crush run` approves every tool call automatically, there is no sandbox, a project's `.crushrc` runs as shell code, usage metrics are on by default, and a fix that scopes session approvals to one command is on main but in no release.\n\n## Before you call either\n\n### boxes.dev\n\n1. Send a new `Idempotency-Key` for each intended run, and the same key and body when you retry an uncertain request\n2. Wait for status `thread_ready` before you use a returned `devboxId` as a target\n3. If you get 409 `active_fork_limit_reached`, free an awake devbox or wait. The plan's awake-devbox cap is full\n4. Read the thread in boxes.dev for the agent's answer. The status URL does not return it\n5. Ask for `threads:read` only unless the task needs to start agents or change settings\n\n### Crush\n\n1. Add `permissions deny` rules or a PreToolUse hook before `crush run`. It approves every permission request in its session, and a session approval in v0.99.0 covers later commands in the same directory\n2. Read `.crushrc`, `crushrc` and `crush.json` in a cloned repository before running Crush there. They execute as shell code at startup\n3. Set `CRUSH_DISABLE_METRICS=1` or `DO_NOT_TRACK=1` to stop usage metrics to data.charm.land\n4. Wrap `crush run` in your own timeout. It has no turn, time or cost limit flag\n5. Configure a provider by environment variable or `crushrc` first. With none, `crush run` exits with an error asking for interactive setup\n\n## Questions\n\n### Which is better for AI agents, boxes.dev or Crush?\n\nCrush and boxes.dev score within a point of each other on agent readiness, 53.3 (D) and 53.2 (D). boxes.dev leads on agent ergonomics and security \u0026 auth.\n\n### Can an agent call boxes.dev and Crush without installing anything?\n\nboxes.dev has a hosted endpoint at https://api.boxes.dev/mcp. No hosted endpoint is listed for Crush.\n\n\n## For agents\n\n- This comparison as JSON: https://www.anchorterminal.com/compare/boxes-dev-vs-crush.json, and with the fewest tokens: https://www.anchorterminal.com/compare/boxes-dev-vs-crush.min.md\n- Over MCP at https://www.anchorterminal.com/mcp (no key): `compare_tools {\"a\": \"boxes-dev\", \"b\": \"crush\"}`. From a terminal: `anchor compare boxes-dev crush`\n- Each listing in full: https://www.anchorterminal.com/api/v1/tools/boxes-dev.json and https://www.anchorterminal.com/api/v1/tools/crush.json\n\n## Other comparisons with boxes.dev or Crush\n\n- [Agent Zero vs boxes.dev](https://www.anchorterminal.com/compare/agent-zero-vs-boxes-dev.md)\n- [Agent Zero vs Crush](https://www.anchorterminal.com/compare/agent-zero-vs-crush.md)\n- [Aider vs boxes.dev](https://www.anchorterminal.com/compare/aider-vs-boxes-dev.md)\n- [Aider vs Crush](https://www.anchorterminal.com/compare/aider-vs-crush.md)\n- [Amp vs boxes.dev](https://www.anchorterminal.com/compare/amp-vs-boxes-dev.md)\n- [Amp vs Crush](https://www.anchorterminal.com/compare/amp-vs-crush.md)\n- [Antigravity CLI vs boxes.dev](https://www.anchorterminal.com/compare/antigravity-cli-vs-boxes-dev.md)\n- [Antigravity CLI vs Crush](https://www.anchorterminal.com/compare/antigravity-cli-vs-crush.md)\n- [Auggie CLI vs boxes.dev](https://www.anchorterminal.com/compare/auggie-vs-boxes-dev.md)\n- [Auggie CLI vs Crush](https://www.anchorterminal.com/compare/auggie-vs-crush.md)\n- [AXLR vs boxes.dev](https://www.anchorterminal.com/compare/axlr-vs-boxes-dev.md)\n- [AXLR vs Crush](https://www.anchorterminal.com/compare/axlr-vs-crush.md)\n- [boxes.dev vs Claude Code](https://www.anchorterminal.com/compare/boxes-dev-vs-claude-code.md)\n- [boxes.dev vs Click](https://www.anchorterminal.com/compare/boxes-dev-vs-click-agents.md)\n- [boxes.dev vs Cline](https://www.anchorterminal.com/compare/boxes-dev-vs-cline.md)\n- [boxes.dev vs Conductor](https://www.anchorterminal.com/compare/boxes-dev-vs-conductor.md)\n- [boxes.dev vs Cursor CLI](https://www.anchorterminal.com/compare/boxes-dev-vs-cursor-cli.md)\n- [boxes.dev vs DeepSeek Harness (dsh)](https://www.anchorterminal.com/compare/boxes-dev-vs-deepseek-harness.md)\n- [boxes.dev vs dsh-superagent (DeepSeek)](https://www.anchorterminal.com/compare/boxes-dev-vs-deepseek-superagent.md)\n- [boxes.dev vs Devin](https://www.anchorterminal.com/compare/boxes-dev-vs-devin.md)\n- [boxes.dev vs Droid CLI](https://www.anchorterminal.com/compare/boxes-dev-vs-droid-cli.md)\n- [boxes.dev vs Pi](https://www.anchorterminal.com/compare/boxes-dev-vs-earendil-pi.md)\n- [boxes.dev vs Emdash](https://www.anchorterminal.com/compare/boxes-dev-vs-emdash.md)\n- [boxes.dev vs Friday](https://www.anchorterminal.com/compare/boxes-dev-vs-friday-work.md)\n- [boxes.dev vs Gemini CLI](https://www.anchorterminal.com/compare/boxes-dev-vs-gemini-cli.md)\n- [boxes.dev vs GitHub Copilot CLI](https://www.anchorterminal.com/compare/boxes-dev-vs-github-copilot-cli.md)\n- [boxes.dev vs goose](https://www.anchorterminal.com/compare/boxes-dev-vs-goose.md)\n- [boxes.dev vs Harness²](https://www.anchorterminal.com/compare/boxes-dev-vs-harness2.md)\n- [boxes.dev vs HarnessRouter](https://www.anchorterminal.com/compare/boxes-dev-vs-harnessrouter.md)\n- [boxes.dev vs Jules](https://www.anchorterminal.com/compare/boxes-dev-vs-jules.md)\n- [boxes.dev vs Junie CLI](https://www.anchorterminal.com/compare/boxes-dev-vs-junie.md)\n- [boxes.dev vs Kilo Code CLI](https://www.anchorterminal.com/compare/boxes-dev-vs-kilo-code-cli.md)\n- [boxes.dev vs Kimi Code CLI](https://www.anchorterminal.com/compare/boxes-dev-vs-kimi-code-cli.md)\n- [boxes.dev vs Kiro CLI](https://www.anchorterminal.com/compare/boxes-dev-vs-kiro-cli.md)\n- [boxes.dev vs Letta](https://www.anchorterminal.com/compare/boxes-dev-vs-letta.md)\n- [boxes.dev vs mini-swe-agent](https://www.anchorterminal.com/compare/boxes-dev-vs-mini-swe-agent.md)\n- [boxes.dev vs MiniMax Code](https://www.anchorterminal.com/compare/boxes-dev-vs-minimax-code.md)\n- [boxes.dev vs Mistral Vibe CLI](https://www.anchorterminal.com/compare/boxes-dev-vs-mistral-vibe-cli.md)\n- [boxes.dev vs Muse Code](https://www.anchorterminal.com/compare/boxes-dev-vs-muse-code.md)\n- [boxes.dev vs OpenAI Agents API](https://www.anchorterminal.com/compare/boxes-dev-vs-openai-agents-api.md)\n- [boxes.dev vs OpenAI Codex](https://www.anchorterminal.com/compare/boxes-dev-vs-openai-codex.md)\n- [boxes.dev vs OpenCode](https://www.anchorterminal.com/compare/boxes-dev-vs-opencode.md)\n- [boxes.dev vs OpenHands](https://www.anchorterminal.com/compare/boxes-dev-vs-openhands.md)\n- [boxes.dev vs OpenMausBot](https://www.anchorterminal.com/compare/boxes-dev-vs-openmausbot.md)\n- [boxes.dev vs Orca](https://www.anchorterminal.com/compare/boxes-dev-vs-orca.md)\n- [boxes.dev vs Paseo](https://www.anchorterminal.com/compare/boxes-dev-vs-paseo.md)\n- [boxes.dev vs Prime Agent](https://www.anchorterminal.com/compare/boxes-dev-vs-prime-agent.md)\n- [boxes.dev vs Qoder CLI](https://www.anchorterminal.com/compare/boxes-dev-vs-qoder-cli.md)\n- [boxes.dev vs Qwen Code](https://www.anchorterminal.com/compare/boxes-dev-vs-qwen-code.md)\n- [boxes.dev vs Mirror CLI](https://www.anchorterminal.com/compare/boxes-dev-vs-reflection-mirror.md)\n- [boxes.dev vs Rovo Dev CLI](https://www.anchorterminal.com/compare/boxes-dev-vs-rovo-dev-cli.md)\n- [boxes.dev vs Sculptor](https://www.anchorterminal.com/compare/boxes-dev-vs-sculptor.md)\n- [boxes.dev vs T3 Code](https://www.anchorterminal.com/compare/boxes-dev-vs-t3-code.md)\n- [boxes.dev vs Traycer](https://www.anchorterminal.com/compare/boxes-dev-vs-traycer.md)\n- [boxes.dev vs Unstoppable](https://www.anchorterminal.com/compare/boxes-dev-vs-unstoppable.md)\n- [boxes.dev vs Verdent](https://www.anchorterminal.com/compare/boxes-dev-vs-verdent.md)\n- [boxes.dev vs Vibe-Trading](https://www.anchorterminal.com/compare/boxes-dev-vs-vibe-trading.md)\n- [boxes.dev vs Warp (Warp Agent CLI and the Oz Agent API)](https://www.anchorterminal.com/compare/boxes-dev-vs-warp.md)\n- [Claude Code vs Crush](https://www.anchorterminal.com/compare/claude-code-vs-crush.md)\n- [Click vs Crush](https://www.anchorterminal.com/compare/click-agents-vs-crush.md)\n- [Cline vs Crush](https://www.anchorterminal.com/compare/cline-vs-crush.md)\n- [Conductor vs Crush](https://www.anchorterminal.com/compare/conductor-vs-crush.md)\n- [Crush vs Cursor CLI](https://www.anchorterminal.com/compare/crush-vs-cursor-cli.md)\n- [Crush vs DeepSeek Harness (dsh)](https://www.anchorterminal.com/compare/crush-vs-deepseek-harness.md)\n- [Crush vs dsh-superagent (DeepSeek)](https://www.anchorterminal.com/compare/crush-vs-deepseek-superagent.md)\n- [Crush vs Devin](https://www.anchorterminal.com/compare/crush-vs-devin.md)\n- [Crush vs Droid CLI](https://www.anchorterminal.com/compare/crush-vs-droid-cli.md)\n- [Crush vs Pi](https://www.anchorterminal.com/compare/crush-vs-earendil-pi.md)\n- [Crush vs Emdash](https://www.anchorterminal.com/compare/crush-vs-emdash.md)\n- [Crush vs Friday](https://www.anchorterminal.com/compare/crush-vs-friday-work.md)\n- [Crush vs Gemini CLI](https://www.anchorterminal.com/compare/crush-vs-gemini-cli.md)\n- [Crush vs GitHub Copilot CLI](https://www.anchorterminal.com/compare/crush-vs-github-copilot-cli.md)\n- [Crush vs goose](https://www.anchorterminal.com/compare/crush-vs-goose.md)\n- [Crush vs Harness²](https://www.anchorterminal.com/compare/crush-vs-harness2.md)\n- [Crush vs HarnessRouter](https://www.anchorterminal.com/compare/crush-vs-harnessrouter.md)\n- [Crush vs Jules](https://www.anchorterminal.com/compare/crush-vs-jules.md)\n- [Crush vs Junie CLI](https://www.anchorterminal.com/compare/crush-vs-junie.md)\n- [Crush vs Kilo Code CLI](https://www.anchorterminal.com/compare/crush-vs-kilo-code-cli.md)\n- [Crush vs Kimi Code CLI](https://www.anchorterminal.com/compare/crush-vs-kimi-code-cli.md)\n- [Crush vs Kiro CLI](https://www.anchorterminal.com/compare/crush-vs-kiro-cli.md)\n- [Crush vs Letta](https://www.anchorterminal.com/compare/crush-vs-letta.md)\n- [Crush vs mini-swe-agent](https://www.anchorterminal.com/compare/crush-vs-mini-swe-agent.md)\n- [Crush vs MiniMax Code](https://www.anchorterminal.com/compare/crush-vs-minimax-code.md)\n- [Crush vs Mistral Vibe CLI](https://www.anchorterminal.com/compare/crush-vs-mistral-vibe-cli.md)\n- [Crush vs Muse Code](https://www.anchorterminal.com/compare/crush-vs-muse-code.md)\n- [Crush vs OpenAI Agents API](https://www.anchorterminal.com/compare/crush-vs-openai-agents-api.md)\n- [Crush vs OpenAI Codex](https://www.anchorterminal.com/compare/crush-vs-openai-codex.md)\n- [Crush vs OpenCode](https://www.anchorterminal.com/compare/crush-vs-opencode.md)\n- [Crush vs OpenHands](https://www.anchorterminal.com/compare/crush-vs-openhands.md)\n- [Crush vs OpenMausBot](https://www.anchorterminal.com/compare/crush-vs-openmausbot.md)\n- [Crush vs Orca](https://www.anchorterminal.com/compare/crush-vs-orca.md)\n- [Crush vs Paseo](https://www.anchorterminal.com/compare/crush-vs-paseo.md)\n- [Crush vs Prime Agent](https://www.anchorterminal.com/compare/crush-vs-prime-agent.md)\n- [Crush vs Qoder CLI](https://www.anchorterminal.com/compare/crush-vs-qoder-cli.md)\n- [Crush vs Qwen Code](https://www.anchorterminal.com/compare/crush-vs-qwen-code.md)\n- [Crush vs Mirror CLI](https://www.anchorterminal.com/compare/crush-vs-reflection-mirror.md)\n- [Crush vs Rovo Dev CLI](https://www.anchorterminal.com/compare/crush-vs-rovo-dev-cli.md)\n- [Crush vs Sculptor](https://www.anchorterminal.com/compare/crush-vs-sculptor.md)\n- [Crush vs T3 Code](https://www.anchorterminal.com/compare/crush-vs-t3-code.md)\n- [Crush vs Traycer](https://www.anchorterminal.com/compare/crush-vs-traycer.md)\n- [Crush vs Unstoppable](https://www.anchorterminal.com/compare/crush-vs-unstoppable.md)\n- [Crush vs Verdent](https://www.anchorterminal.com/compare/crush-vs-verdent.md)\n- [Crush vs Vibe-Trading](https://www.anchorterminal.com/compare/crush-vs-vibe-trading.md)\n- [Crush vs Warp (Warp Agent CLI and the Oz Agent API)](https://www.anchorterminal.com/compare/crush-vs-warp.md)\n- [Agent Relay vs boxes.dev](https://www.anchorterminal.com/compare/agent-relay-vs-boxes-dev.md)\n- [Agent Relay vs Crush](https://www.anchorterminal.com/compare/agent-relay-vs-crush.md)\n- [boxes.dev vs Clawboo](https://www.anchorterminal.com/compare/boxes-dev-vs-clawboo.md)\n- [boxes.dev vs CLI Manager](https://www.anchorterminal.com/compare/boxes-dev-vs-cli-manager.md)\n- [boxes.dev vs Harness](https://www.anchorterminal.com/compare/boxes-dev-vs-harness-autonomous.md)\n- [boxes.dev vs herdr](https://www.anchorterminal.com/compare/boxes-dev-vs-herdr.md)\n- [boxes.dev vs Paperclip](https://www.anchorterminal.com/compare/boxes-dev-vs-paperclip.md)\n- [boxes.dev vs Parallax](https://www.anchorterminal.com/compare/boxes-dev-vs-parallax-agents.md)\n- [Clawboo vs Crush](https://www.anchorterminal.com/compare/clawboo-vs-crush.md)\n- [CLI Manager vs Crush](https://www.anchorterminal.com/compare/cli-manager-vs-crush.md)\n- [Crush vs Harness](https://www.anchorterminal.com/compare/crush-vs-harness-autonomous.md)\n- [Crush vs herdr](https://www.anchorterminal.com/compare/crush-vs-herdr.md)\n- [Crush vs Paperclip](https://www.anchorterminal.com/compare/crush-vs-paperclip.md)\n- [Crush vs Parallax](https://www.anchorterminal.com/compare/crush-vs-parallax-agents.md)\n",
  "meta": {
    "attribution": "Anchor Terminal (https://www.anchorterminal.com)",
    "attributionRequired": true,
    "credit": "CC BY 4.0, credit Anchor Terminal and link the page or API address you took it from (https://www.anchorterminal.com/terms/#data)",
    "docs": "https://www.anchorterminal.com/docs/",
    "generatedAt": "2026-11-18",
    "license": "CC-BY-4.0",
    "method": "https://www.anchorterminal.com/benchmark/",
    "methodology": "1.0",
    "openapi": "https://www.anchorterminal.com/openapi.json",
    "preview": false,
    "run": "2026-10-01",
    "runLabel": "October 2026 research run",
    "terms": "https://www.anchorterminal.com/terms/#data"
  },
  "page": {
    "breadcrumbs": [
      {
        "name": "Home",
        "url": "https://www.anchorterminal.com/"
      },
      {
        "name": "Compare",
        "url": "https://www.anchorterminal.com/compare/"
      },
      {
        "name": "boxes.dev vs Crush",
        "url": ""
      }
    ],
    "description": "Crush and boxes.dev score within a point of each other for agent harnesses, 53.3 and 53.2 out of 100. Prices, MCP, x402, uptime and agent notes side by side.",
    "facts": [
      "boxes.dev D 53.2",
      "Crush D 53.3",
      "scores"
    ],
    "h1": "boxes.dev vs Crush",
    "image": "https://www.anchorterminal.com/assets/og/default.png",
    "path": "/compare/boxes-dev-vs-crush",
    "published": "2026-10-01",
    "section": "tools",
    "title": "boxes.dev vs Crush for AI agents in 2026: scores and prices",
    "toc": null,
    "updated": "2026-11-18",
    "url": "https://www.anchorterminal.com/compare/boxes-dev-vs-crush"
  },
  "tokens": {
    "markdown": 7300,
    "slim": 1030
  },
  "version": 1
}
