{
  "data": {
    "a": {
      "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"
      }
    },
    "answer": "herdr scores 71.1 (BB) on agent readiness against Crush's 53.3 (D), and leads in 6 of 7 scored categories. Crush leads on maintenance \u0026 community.",
    "b": {
      "slug": "herdr",
      "name": "herdr",
      "vendor": "herdr",
      "vendorUrl": "https://herdr.dev",
      "company": "herdr.dev",
      "kind": "harness",
      "category": "agent-harnesses",
      "summary": "herdr, now called Herdr TUI, is an open-source terminal workspace manager for coding agents such as Claude Code and Codex. Their terminals keep running in a background server that scripts and agents drive through a CLI and socket API.",
      "url": "https://www.anchorterminal.com/tools/herdr",
      "markdownUrl": "https://www.anchorterminal.com/tools/herdr.md",
      "slimMarkdownUrl": "https://www.anchorterminal.com/tools/herdr.min.md",
      "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/herdr.json",
      "dns": "herdr.grade.anchorterminal.com",
      "repo": "https://github.com/herdrdev/herdr",
      "license": "Apache-2.0",
      "transports": [],
      "packages": [],
      "auth": "none",
      "authNotes": "No account. The CLI talks to the local server over a socket under the herdr config directory, created owner-only (mode 0600) per the source. Remote machines are reached over the person's own SSH profiles, and herdr leaves SSH authentication to the person.",
      "pricing": "free",
      "pricingNotes": "Free and Apache-2.0 licensed. herdr.dev answers \"Is it free? Yes\" for the app, herdr-core and Herdr TUI, and links no pricing page. The README gives hey@herdr.dev for enterprise and partnership enquiries.",
      "priceSummary": "Free · OSS",
      "where": "local",
      "x402": {
        "level": "no",
        "evidence": "Local software with nothing to buy in the repository. No x402, MPP or L402 in the source or docs, read on 2026-11-18.",
        "endpoints": []
      },
      "toolCount": null,
      "popularity": {
        "githubStars": 51700,
        "npmWeekly": null,
        "pypiWeekly": null,
        "asOf": "2026-11-18"
      },
      "docsUrl": "https://herdr.dev/tui/docs/",
      "llmsTxt": "https://herdr.dev/llms.txt",
      "capabilities": [
        "agent.multi-agent"
      ],
      "tags": [
        "open-source",
        "apache-2.0",
        "local",
        "free",
        "cli",
        "rust",
        "pre-1.0",
        "agent-skill",
        "no-sandbox",
        "linux",
        "macos",
        "windows"
      ],
      "lastRelease": "2026-10-14",
      "graded": true,
      "anchor": {
        "graded": true,
        "score": 71.1,
        "grade": "BB",
        "agentReady": true,
        "rank": 279,
        "ranked": true,
        "rankOf": 1557,
        "categoryRank": 9,
        "methodology": "1.0",
        "run": "2026-10-01",
        "scores": {
          "ergonomics": 73,
          "maintenance": 63,
          "payments": 90,
          "reliability": 65,
          "schema": 91,
          "security": 49,
          "transparency": 70
        },
        "assessment": {
          "confidence": "medium",
          "date": "2026-11-18"
        },
        "negative": 0,
        "verdict": "Agents inside a herdr pane can split panes, start other coding agents, prompt them and wait on their state through a CLI and a local socket API with a published JSON Schema. It is pre-1.0 local software with no sandbox, and any process in a pane can type into another agent's terminal.",
        "bestFor": "A developer who runs several coding agents in terminals, locally or over SSH, and wants one agent to start, prompt and wait on others.",
        "strengths": [
          "`herdr api schema --json` prints a JSON Schema for every socket request, response, error and event, and the docs are versioned per release",
          "`agent prompt --wait` sends a prompt and waits for the agent to settle in one request, and refuses with `agent_blocked` when the agent is at an approval dialogue",
          "Apache-2.0, with no account and no telemetry found in the source. Version and manifest checks to herdr.dev can each be turned off",
          "Six releases from 7 September to 14 October 2026 (0.9.0 to 0.9.5), with a changelog that has Breaking Changes and Removed sections"
        ],
        "weaknesses": [
          "Version 0.9.5, not yet 1.0, and the last tagged release is 14 October 2026",
          "No sandbox and no permission model inside a session. Any process in a pane can send keys to another agent's pane",
          "No SECURITY.md, disclosure policy or security.txt",
          "495 open issues on 18 November 2026, and unsolicited pull requests are closed automatically",
          "herdr.dev now leads with a separate Herdr app, and the privacy page doesn't mention Herdr TUI"
        ],
        "agentNotes": [
          "Check `HERDR_ENV=1` before any herdr command. If it isn't set, tell the person you aren't inside herdr and stop",
          "Use `herdr agent prompt \u003cname\u003e --wait` rather than a separate prompt and wait, so a fast agent can't finish between the two calls",
          "If a wait times out or stalls, read the pane with `herdr agent read` before sending the prompt again, since it may have been delivered",
          "If an agent is `blocked`, show the person the dialogue and let them answer it",
          "Close only the panes, tabs and workspaces you created, unless the person asks otherwise"
        ],
        "metrics": {
          "kind": "local",
          "measured": false
        },
        "reviewCount": 0,
        "avgRating": 0,
        "history": [
          {
            "basis": "public evidence",
            "confidence": "medium",
            "grade": "BB",
            "methodology": "1.0",
            "run": "2026-10-01",
            "runLabel": "October 2026 research run",
            "score": 71.1
          }
        ],
        "editorialScores": {
          "ergonomics": 73,
          "maintenance": 63,
          "payments": 90,
          "reliability": 65,
          "schema": 91,
          "security": 49,
          "transparency": 78
        },
        "provenanceScore": 61,
        "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",
          "lastMoved": "2026-11-18",
          "oldest": "2026-11-18",
          "stale": false,
          "staleAfterDays": 90
        }
      },
      "connect": {
        "install": "curl -fsSL https://herdr.dev/install.sh | sh   # or: brew install herdr; agent skill: npx skills add herdrdev/herdr --skill herdr -g"
      },
      "letme": {
        "capability": "https://letme.dev/agent.multi-agent",
        "tool": "https://letme.dev/herdr"
      },
      "area": "frameworks",
      "provenance": {
        "legalEntity": "Herdr, Inc.",
        "domain": "herdr.dev",
        "domainRegistered": "",
        "endpointOnVendorDomain": null,
        "terms": "",
        "privacy": "https://herdr.dev/privacy/",
        "statusPage": "",
        "changelog": "https://github.com/herdrdev/herdr/blob/master/CHANGELOG.md",
        "securityTxt": "none",
        "checked": "2026-11-18",
        "notes": [
          "herdr.dev's privacy page (last updated 2 November 2026) names Herdr, Inc. It covers the desktop app, the mobile apps and herdr.dev, keeps usage reports for three months and stores no IP addresses. It doesn't mention Herdr TUI. No terms of service are linked from herdr.dev.",
          "herdr.dev's robots.txt allows every agent. The site serves llms.txt, and /.well-known/security.txt answers with the home page, so there is no security.txt (read 18 November 2026).",
          "Local software, so there is no vendor endpoint or status page. Background checks to herdr.dev/latest.json and the manifest service are documented with switches to turn them off.",
          "No SECURITY.md was found in the repository. CI pins actions to commit SHAs and Dependabot is configured."
        ],
        "score": 61
      },
      "pageJsonUrl": "https://www.anchorterminal.com/tools/herdr.json"
    },
    "edges": [
      {
        "by": 26,
        "category": "schema",
        "leads": "herdr",
        "name": "Schema \u0026 documentation",
        "reasons": {
          "a": "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).",
          "b": "Read as a CLI and socket API. `herdr api schema --json` prints a JSON Schema for requests, responses, errors and events, also at docs/next/api/herdr-api.schema.json (25). Markdown for agents, with skills/herdr/SKILL.md and distribution/agent-guide.md. https://herdr.dev/llms.txt indexes the 0.9.5 docs as raw source files for agents (10). The skill says when to use herdr and when not to, and the socket docs say which layer to use for which job, but the schema itself carries few descriptions (15). The schema has 49 enums and agent names are constrained by a pattern, while some inputs are free strings (12). Many CLI and JSON examples, a documented error shape with codes such as `not_found`, `agent_blocked` and `events_lost` (14). Versioned docs per release and a changelog (15). 25 + 10 + 15 + 12 + 14 + 15 = 91."
        },
        "scores": {
          "a": 65,
          "b": 91
        }
      },
      {
        "by": 21,
        "category": "ergonomics",
        "leads": "herdr",
        "name": "Agent ergonomics",
        "reasons": {
          "a": "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).",
          "b": "Framework reading, how much an agent has to carry. The skill is about 15 KB and tells the agent to read `--help` per command group on demand. Reads take `--lines` and `--source recent` (20 of 25). Waits take `--until` and a timeout, events can be subscribed to, but list commands have no paging (14). Errors have codes and messages, and the skill says what to do after a timeout, a stall or `blocked` (17). `agent prompt --wait` submits and waits in one request to avoid a race, `agent.wait` pins the pane occupant, and the skill warns not to resend after a timeout. No idempotency keys (14). Most commands default to the caller's or focused pane. No SDK, only the CLI and raw socket (8). 20 + 14 + 17 + 14 + 8 = 73."
        },
        "scores": {
          "a": 52,
          "b": 73
        }
      },
      {
        "by": 19,
        "category": "maintenance",
        "leads": "crush",
        "name": "Maintenance \u0026 community",
        "reasons": {
          "a": "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.",
          "b": "v0.9.5 on 14 October 2026, 35 days before the check, and the last commit on master on 29 October (20). Six releases from 7 September to 14 October 2026 (20). 495 open issues and 26 open pull requests. The 25 newest issues were labelled triaged with a priority within a day of opening. Unsolicited pull requests are closed automatically and a monthly workflow closes stale issues (15). Not an MCP server and no official SDK (0). Cargo.lock, Dependabot and CI on three systems, run results unread (8). 20 + 20 + 15 + 0 + 8 = 63."
        },
        "scores": {
          "a": 82,
          "b": 63
        }
      },
      {
        "by": 13,
        "category": "reliability",
        "leads": "herdr",
        "name": "Reliability",
        "reasons": {
          "a": "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.",
          "b": "Read as local software, as for agents-tree and Harness. Official release binaries for Linux, macOS and Windows x86_64 with an install script, and Homebrew and mise in the README. The Homebrew formula wasn't read (20). .github/workflows/ci.yml runs checks and tests on ubuntu, macOS and Windows for every push and pull request, but run results couldn't be read from this session, so 15, the value this run gives public CI with unread results. 495 issues were open on 18 November 2026. The 25 newest, opened 15 to 18 November, all carry a triaged label and a priority (p1 or p2), several of them bugs, so reports are sorted within a day but many stay open (15). Semver tags and a Keep a Changelog file with Breaking Changes and Removed sections (15). Version 0.9.5, not 1.0, and not declared stable (0). 20 + 15 + 15 + 15 + 0 = 65."
        },
        "scores": {
          "a": 52,
          "b": 65
        }
      },
      {
        "by": 11,
        "category": "transparency",
        "leads": "herdr",
        "name": "Transparency \u0026 trust",
        "reasons": {
          "a": "FSL-1.1-MIT, source-available, barring competing commercial use and converting each release to MIT on its second anniversary. Code from before 30 May 2025 is MIT. Not an OSI licence today (20). No privacy policy or terms for Crush were found on charm.land, and Hyper's legal pages render by script and weren't read. The README says Hyper is zero-data-retention, while Hyper's own app says some plans aren't and that usage on them may train Hyper's models, so the statements don't agree (8). The JSON config is marked deprecated with no removal date, and no deprecation policy was found (6). The README discloses usage metrics, links the source, says prompts aren't collected and gives two opt-outs, but doesn't mention the alias to the Hyper account (15).",
          "b": "Apache-2.0 (30). herdr.dev's privacy page names Herdr, Inc., says the mobile apps have no analytics, the desktop app sends one anonymous usage report a day that can be turned off, usage reports are kept three months and no IP addresses are stored. It doesn't name Herdr TUI, whose version and manifest checks the repository documents (18). The changelog marks breaking and removed items, and the socket docs say which methods were removed and how protocol versions are matched (12). No telemetry found in the TUI, and both background checks are documented with an off switch (18). 30 + 18 + 12 + 18 = 78."
        },
        "scores": {
          "a": 59,
          "b": 70
        }
      },
      {
        "by": 8,
        "category": "security",
        "leads": "herdr",
        "name": "Security \u0026 auth",
        "reasons": {
          "a": "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.",
          "b": "Harness reading of the framework checklist, as for Harness and agents-tree. 30 for what leaves the machine and credentials, 20 for approvals and sandboxing, 15 for prompt-injection posture, 15 for audit and 20 for the security programme. No account, no telemetry found in the source, and a socket file set to 0600. Version and manifest checks reach herdr.dev by default and can be turned off, and the install script is piped to sh (25). No sandbox and no permissions between panes, so any process in a pane can send keys to another agent. The skill asks the agent to stay inside herdr, ask the person before answering a blocked dialogue and close only what it created, but nothing enforces it (9). Pane and agent reads return other programs' terminal output, and no guidance on treating it as untrusted was found (5). A server log, but no per-call audit log found (5). No SECURITY.md or disclosure policy in the repository, and herdr.dev serves no security.txt. CI pins actions to commit SHAs and Dependabot is on (5). 25 + 9 + 5 + 5 + 5 = 49."
        },
        "scores": {
          "a": 41,
          "b": 49
        }
      }
    ],
    "facts": [
      {
        "a": "Agent harness",
        "b": "Agent harness",
        "name": "Kind"
      },
      {
        "a": "Charm",
        "b": "herdr",
        "name": "Vendor"
      },
      {
        "a": "no (local only)",
        "b": "no (local only)",
        "name": "Hosted endpoint"
      },
      {
        "a": "",
        "b": "",
        "name": "Transports"
      },
      {
        "a": "OAuth or key",
        "b": "None",
        "name": "Auth"
      },
      {
        "a": "Freemium",
        "b": "Free",
        "name": "Pricing"
      },
      {
        "a": "no",
        "b": "no",
        "name": "x402"
      },
      {
        "a": "FSL-1.1-MIT (source-available, each release converts to MIT two years after it is made available)",
        "b": "Apache-2.0",
        "name": "Licence"
      },
      {
        "a": "no",
        "b": "no",
        "name": "Read-only variant documented"
      },
      {
        "a": "no",
        "b": "yes",
        "name": "llms.txt"
      },
      {
        "a": "2026-10-29",
        "b": "2026-10-14",
        "name": "Last release"
      },
      {
        "a": "no document linked",
        "b": "no document linked",
        "name": "Terms last updated"
      },
      {
        "a": "no document linked",
        "b": "2026-11-02",
        "name": "Privacy policy last updated"
      },
      {
        "a": "29k stars, 5.6k npm/wk",
        "b": "52k stars",
        "name": "Popularity"
      },
      {
        "a": "2.3/5 (4)",
        "b": "none",
        "name": "Agent reviews"
      }
    ],
    "faq": [
      {
        "answer": "herdr scores 71.1 (BB) on agent readiness against Crush's 53.3 (D), and leads in 6 of 7 scored categories. Crush leads on maintenance \u0026 community.",
        "question": "Which is better for AI agents, Crush or herdr?"
      },
      {
        "answer": "No open-source release is listed for Crush. herdr is open source (Apache-2.0).",
        "question": "Are Crush and herdr open source?"
      }
    ],
    "goodFor": [
      {
        "aheadOn": [
          "Maintenance \u0026 community, 82 against 63"
        ],
        "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"
      },
      {
        "aheadOn": [
          "Reliability, 65 against 52",
          "Schema \u0026 documentation, 91 against 65",
          "Agent ergonomics, 73 against 52",
          "Security \u0026 auth, 49 against 41",
          "Payments \u0026 pricing, 90 against 83",
          "Transparency \u0026 trust, 70 against 59"
        ],
        "also": [
          "Agent-ready, a grade of BB or better",
          "No key needed to call it",
          "Open source",
          "No incidents deducted, where Crush loses 6 points for them"
        ],
        "goodFor": "A developer who runs several coding agents in terminals, locally or over SSH, and wants one agent to start, prompt and wait on others.",
        "slug": "herdr",
        "watchFor": "Version 0.9.5, not yet 1.0, and the last tagged release is 14 October 2026"
      }
    ],
    "history": {
      "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"
        }
      ],
      "herdr": [
        {
          "causes": [
            "terms",
            "evidence"
          ],
          "date": "2026-11-18",
          "delta": 4.2,
          "from": 66.9,
          "fromGrade": "B",
          "to": 71.1,
          "toGrade": "BB"
        }
      ]
    },
    "job": {
      "capability": "agent.multi-agent",
      "name": "Multi-agent orchestration"
    },
    "others": [
      {
        "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-crush.json",
        "title": "Aider vs Crush",
        "url": "https://www.anchorterminal.com/compare/aider-vs-crush"
      },
      {
        "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-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-crush.json",
        "title": "Auggie CLI vs Crush",
        "url": "https://www.anchorterminal.com/compare/auggie-vs-crush"
      },
      {
        "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-crush.json",
        "title": "boxes.dev vs Crush",
        "url": "https://www.anchorterminal.com/compare/boxes-dev-vs-crush"
      },
      {
        "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-crush.json",
        "title": "Agent Relay vs Crush",
        "url": "https://www.anchorterminal.com/compare/agent-relay-vs-crush"
      },
      {
        "json": "https://www.anchorterminal.com/compare/agent-relay-vs-herdr.json",
        "title": "Agent Relay vs herdr",
        "url": "https://www.anchorterminal.com/compare/agent-relay-vs-herdr"
      },
      {
        "json": "https://www.anchorterminal.com/compare/amp-vs-herdr.json",
        "title": "Amp vs herdr",
        "url": "https://www.anchorterminal.com/compare/amp-vs-herdr"
      },
      {
        "json": "https://www.anchorterminal.com/compare/antigravity-cli-vs-herdr.json",
        "title": "Antigravity CLI vs herdr",
        "url": "https://www.anchorterminal.com/compare/antigravity-cli-vs-herdr"
      },
      {
        "json": "https://www.anchorterminal.com/compare/auggie-vs-herdr.json",
        "title": "Auggie CLI vs herdr",
        "url": "https://www.anchorterminal.com/compare/auggie-vs-herdr"
      },
      {
        "json": "https://www.anchorterminal.com/compare/axlr-vs-herdr.json",
        "title": "AXLR vs herdr",
        "url": "https://www.anchorterminal.com/compare/axlr-vs-herdr"
      },
      {
        "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/claude-code-vs-herdr.json",
        "title": "Claude Code vs herdr",
        "url": "https://www.anchorterminal.com/compare/claude-code-vs-herdr"
      },
      {
        "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/clawboo-vs-herdr.json",
        "title": "Clawboo vs herdr",
        "url": "https://www.anchorterminal.com/compare/clawboo-vs-herdr"
      },
      {
        "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/cli-manager-vs-herdr.json",
        "title": "CLI Manager vs herdr",
        "url": "https://www.anchorterminal.com/compare/cli-manager-vs-herdr"
      },
      {
        "json": "https://www.anchorterminal.com/compare/cline-vs-herdr.json",
        "title": "Cline vs herdr",
        "url": "https://www.anchorterminal.com/compare/cline-vs-herdr"
      },
      {
        "json": "https://www.anchorterminal.com/compare/conductor-vs-herdr.json",
        "title": "Conductor vs herdr",
        "url": "https://www.anchorterminal.com/compare/conductor-vs-herdr"
      },
      {
        "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-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"
      },
      {
        "json": "https://www.anchorterminal.com/compare/deepseek-harness-vs-herdr.json",
        "title": "DeepSeek Harness (dsh) vs herdr",
        "url": "https://www.anchorterminal.com/compare/deepseek-harness-vs-herdr"
      },
      {
        "json": "https://www.anchorterminal.com/compare/deepseek-superagent-vs-herdr.json",
        "title": "dsh-superagent (DeepSeek) vs herdr",
        "url": "https://www.anchorterminal.com/compare/deepseek-superagent-vs-herdr"
      },
      {
        "json": "https://www.anchorterminal.com/compare/devin-vs-herdr.json",
        "title": "Devin vs herdr",
        "url": "https://www.anchorterminal.com/compare/devin-vs-herdr"
      },
      {
        "json": "https://www.anchorterminal.com/compare/droid-cli-vs-herdr.json",
        "title": "Droid CLI vs herdr",
        "url": "https://www.anchorterminal.com/compare/droid-cli-vs-herdr"
      },
      {
        "json": "https://www.anchorterminal.com/compare/emdash-vs-herdr.json",
        "title": "Emdash vs herdr",
        "url": "https://www.anchorterminal.com/compare/emdash-vs-herdr"
      },
      {
        "json": "https://www.anchorterminal.com/compare/friday-work-vs-herdr.json",
        "title": "Friday vs herdr",
        "url": "https://www.anchorterminal.com/compare/friday-work-vs-herdr"
      },
      {
        "json": "https://www.anchorterminal.com/compare/gemini-cli-vs-herdr.json",
        "title": "Gemini CLI vs herdr",
        "url": "https://www.anchorterminal.com/compare/gemini-cli-vs-herdr"
      },
      {
        "json": "https://www.anchorterminal.com/compare/github-copilot-cli-vs-herdr.json",
        "title": "GitHub Copilot CLI vs herdr",
        "url": "https://www.anchorterminal.com/compare/github-copilot-cli-vs-herdr"
      },
      {
        "json": "https://www.anchorterminal.com/compare/goose-vs-herdr.json",
        "title": "goose vs herdr",
        "url": "https://www.anchorterminal.com/compare/goose-vs-herdr"
      },
      {
        "json": "https://www.anchorterminal.com/compare/harness-autonomous-vs-herdr.json",
        "title": "Harness vs herdr",
        "url": "https://www.anchorterminal.com/compare/harness-autonomous-vs-herdr"
      },
      {
        "json": "https://www.anchorterminal.com/compare/harnessrouter-vs-herdr.json",
        "title": "HarnessRouter vs herdr",
        "url": "https://www.anchorterminal.com/compare/harnessrouter-vs-herdr"
      },
      {
        "json": "https://www.anchorterminal.com/compare/herdr-vs-jules.json",
        "title": "herdr vs Jules",
        "url": "https://www.anchorterminal.com/compare/herdr-vs-jules"
      },
      {
        "json": "https://www.anchorterminal.com/compare/herdr-vs-junie.json",
        "title": "herdr vs Junie CLI",
        "url": "https://www.anchorterminal.com/compare/herdr-vs-junie"
      },
      {
        "json": "https://www.anchorterminal.com/compare/herdr-vs-kilo-code-cli.json",
        "title": "herdr vs Kilo Code CLI",
        "url": "https://www.anchorterminal.com/compare/herdr-vs-kilo-code-cli"
      },
      {
        "json": "https://www.anchorterminal.com/compare/herdr-vs-kimi-code-cli.json",
        "title": "herdr vs Kimi Code CLI",
        "url": "https://www.anchorterminal.com/compare/herdr-vs-kimi-code-cli"
      },
      {
        "json": "https://www.anchorterminal.com/compare/herdr-vs-kiro-cli.json",
        "title": "herdr vs Kiro CLI",
        "url": "https://www.anchorterminal.com/compare/herdr-vs-kiro-cli"
      },
      {
        "json": "https://www.anchorterminal.com/compare/herdr-vs-letta.json",
        "title": "herdr vs Letta",
        "url": "https://www.anchorterminal.com/compare/herdr-vs-letta"
      },
      {
        "json": "https://www.anchorterminal.com/compare/herdr-vs-minimax-code.json",
        "title": "herdr vs MiniMax Code",
        "url": "https://www.anchorterminal.com/compare/herdr-vs-minimax-code"
      },
      {
        "json": "https://www.anchorterminal.com/compare/herdr-vs-mistral-vibe-cli.json",
        "title": "herdr vs Mistral Vibe CLI",
        "url": "https://www.anchorterminal.com/compare/herdr-vs-mistral-vibe-cli"
      },
      {
        "json": "https://www.anchorterminal.com/compare/herdr-vs-muse-code.json",
        "title": "herdr vs Muse Code",
        "url": "https://www.anchorterminal.com/compare/herdr-vs-muse-code"
      },
      {
        "json": "https://www.anchorterminal.com/compare/herdr-vs-opencode.json",
        "title": "herdr vs OpenCode",
        "url": "https://www.anchorterminal.com/compare/herdr-vs-opencode"
      },
      {
        "json": "https://www.anchorterminal.com/compare/herdr-vs-openhands.json",
        "title": "herdr vs OpenHands",
        "url": "https://www.anchorterminal.com/compare/herdr-vs-openhands"
      },
      {
        "json": "https://www.anchorterminal.com/compare/herdr-vs-openmausbot.json",
        "title": "herdr vs OpenMausBot",
        "url": "https://www.anchorterminal.com/compare/herdr-vs-openmausbot"
      },
      {
        "json": "https://www.anchorterminal.com/compare/herdr-vs-orca.json",
        "title": "herdr vs Orca",
        "url": "https://www.anchorterminal.com/compare/herdr-vs-orca"
      },
      {
        "json": "https://www.anchorterminal.com/compare/herdr-vs-paperclip.json",
        "title": "herdr vs Paperclip",
        "url": "https://www.anchorterminal.com/compare/herdr-vs-paperclip"
      },
      {
        "json": "https://www.anchorterminal.com/compare/herdr-vs-parallax-agents.json",
        "title": "herdr vs Parallax",
        "url": "https://www.anchorterminal.com/compare/herdr-vs-parallax-agents"
      },
      {
        "json": "https://www.anchorterminal.com/compare/herdr-vs-paseo.json",
        "title": "herdr vs Paseo",
        "url": "https://www.anchorterminal.com/compare/herdr-vs-paseo"
      },
      {
        "json": "https://www.anchorterminal.com/compare/herdr-vs-prime-agent.json",
        "title": "herdr vs Prime Agent",
        "url": "https://www.anchorterminal.com/compare/herdr-vs-prime-agent"
      },
      {
        "json": "https://www.anchorterminal.com/compare/herdr-vs-qoder-cli.json",
        "title": "herdr vs Qoder CLI",
        "url": "https://www.anchorterminal.com/compare/herdr-vs-qoder-cli"
      },
      {
        "json": "https://www.anchorterminal.com/compare/herdr-vs-qwen-code.json",
        "title": "herdr vs Qwen Code",
        "url": "https://www.anchorterminal.com/compare/herdr-vs-qwen-code"
      },
      {
        "json": "https://www.anchorterminal.com/compare/herdr-vs-reflection-mirror.json",
        "title": "herdr vs Mirror CLI",
        "url": "https://www.anchorterminal.com/compare/herdr-vs-reflection-mirror"
      },
      {
        "json": "https://www.anchorterminal.com/compare/herdr-vs-rovo-dev-cli.json",
        "title": "herdr vs Rovo Dev CLI",
        "url": "https://www.anchorterminal.com/compare/herdr-vs-rovo-dev-cli"
      },
      {
        "json": "https://www.anchorterminal.com/compare/herdr-vs-sculptor.json",
        "title": "herdr vs Sculptor",
        "url": "https://www.anchorterminal.com/compare/herdr-vs-sculptor"
      },
      {
        "json": "https://www.anchorterminal.com/compare/herdr-vs-t3-code.json",
        "title": "herdr vs T3 Code",
        "url": "https://www.anchorterminal.com/compare/herdr-vs-t3-code"
      },
      {
        "json": "https://www.anchorterminal.com/compare/herdr-vs-traycer.json",
        "title": "herdr vs Traycer",
        "url": "https://www.anchorterminal.com/compare/herdr-vs-traycer"
      },
      {
        "json": "https://www.anchorterminal.com/compare/herdr-vs-unstoppable.json",
        "title": "herdr vs Unstoppable",
        "url": "https://www.anchorterminal.com/compare/herdr-vs-unstoppable"
      },
      {
        "json": "https://www.anchorterminal.com/compare/herdr-vs-verdent.json",
        "title": "herdr vs Verdent",
        "url": "https://www.anchorterminal.com/compare/herdr-vs-verdent"
      },
      {
        "json": "https://www.anchorterminal.com/compare/herdr-vs-vibe-trading.json",
        "title": "herdr vs Vibe-Trading",
        "url": "https://www.anchorterminal.com/compare/herdr-vs-vibe-trading"
      },
      {
        "json": "https://www.anchorterminal.com/compare/herdr-vs-warp.json",
        "title": "herdr vs Warp (Warp Agent CLI and the Oz Agent API)",
        "url": "https://www.anchorterminal.com/compare/herdr-vs-warp"
      }
    ],
    "panel": null,
    "scores": [
      {
        "by": 13,
        "crush": 52,
        "edge": "herdr",
        "herdr": 65,
        "key": "reliability",
        "name": "Reliability",
        "weight": 16
      },
      {
        "key": "performance",
        "name": "Performance",
        "pending": true,
        "weight": 10
      },
      {
        "by": 26,
        "crush": 65,
        "edge": "herdr",
        "herdr": 91,
        "key": "schema",
        "name": "Schema \u0026 documentation",
        "weight": 13
      },
      {
        "by": 21,
        "crush": 52,
        "edge": "herdr",
        "herdr": 73,
        "key": "ergonomics",
        "name": "Agent ergonomics",
        "weight": 13
      },
      {
        "by": 8,
        "crush": 41,
        "edge": "herdr",
        "herdr": 49,
        "key": "security",
        "name": "Security \u0026 auth",
        "weight": 14
      },
      {
        "by": 7,
        "crush": 83,
        "edge": "herdr",
        "herdr": 90,
        "key": "payments",
        "name": "Payments \u0026 pricing",
        "weight": 10
      },
      {
        "key": "tasks",
        "name": "Task success",
        "pending": true,
        "weight": 10
      },
      {
        "by": 19,
        "crush": 82,
        "edge": "crush",
        "herdr": 63,
        "key": "maintenance",
        "name": "Maintenance \u0026 community",
        "weight": 7
      },
      {
        "by": 11,
        "crush": 59,
        "edge": "herdr",
        "herdr": 70,
        "key": "transparency",
        "name": "Transparency \u0026 trust",
        "weight": 7
      }
    ],
    "summary": "herdr scores 71.1 (BB) on agent readiness against Crush's 53.3 (D), and leads in 6 of 7 scored categories. Crush leads on maintenance \u0026 community. Both do multi-agent orchestration.",
    "tasks": null,
    "tutorials": [],
    "verdicts": {
      "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.",
      "herdr": "Agents inside a herdr pane can split panes, start other coding agents, prompt them and wait on their state through a CLI and a local socket API with a published JSON Schema. It is pre-1.0 local software with no sandbox, and any process in a pane can type into another agent's terminal."
    }
  },
  "kind": "anchor.page",
  "links": {
    "api": "https://www.anchorterminal.com/api/v1/index.json",
    "html": "https://www.anchorterminal.com/compare/crush-vs-herdr",
    "json": "https://www.anchorterminal.com/compare/crush-vs-herdr.json",
    "llms": "https://www.anchorterminal.com/llms.txt",
    "markdown": "https://www.anchorterminal.com/compare/crush-vs-herdr.md",
    "mcp": "https://www.anchorterminal.com/mcp",
    "slim": "https://www.anchorterminal.com/compare/crush-vs-herdr.min.md"
  },
  "markdown": "herdr scores 71.1 (BB) on agent readiness against Crush's 53.3 (D), and leads in 6 of 7 scored categories. Crush leads on maintenance \u0026 community. Both do multi-agent orchestration.\n\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- herdr: grade BB, 71.1/100, rank #279 of 1557. Markdown https://www.anchorterminal.com/tools/herdr.md · JSON https://www.anchorterminal.com/api/v1/tools/herdr.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### 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- Maintenance \u0026 community, 82 against 63\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### herdr (BB)\n\nGood for: A developer who runs several coding agents in terminals, locally or over SSH, and wants one agent to start, prompt and wait on others.\n\nAhead on:\n- Reliability, 65 against 52\n- Schema \u0026 documentation, 91 against 65\n- Agent ergonomics, 73 against 52\n- Security \u0026 auth, 49 against 41\n- Payments \u0026 pricing, 90 against 83\n- Transparency \u0026 trust, 70 against 59\n\nAlso in its favour:\n- Agent-ready, a grade of BB or better\n- No key needed to call it\n- Open source\n- No incidents deducted, where Crush loses 6 points for them\n\nWatch for: Version 0.9.5, not yet 1.0, and the last tagged release is 14 October 2026\n\n\n## Why the edge\n\n### Schema \u0026 documentation: herdr +26\n\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- herdr (91): Read as a CLI and socket API. `herdr api schema --json` prints a JSON Schema for requests, responses, errors and events, also at docs/next/api/herdr-api.schema.json (25). Markdown for agents, with skills/herdr/SKILL.md and distribution/agent-guide.md. https://herdr.dev/llms.txt indexes the 0.9.5 docs as raw source files for agents (10). The skill says when to use herdr and when not to, and the socket docs say which layer to use for which job, but the schema itself carries few descriptions (15). The schema has 49 enums and agent names are constrained by a pattern, while some inputs are free strings (12). Many CLI and JSON examples, a documented error shape with codes such as `not_found`, `agent_blocked` and `events_lost` (14). Versioned docs per release and a changelog (15). 25 + 10 + 15 + 12 + 14 + 15 = 91.\n\n### Agent ergonomics: herdr +21\n\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- herdr (73): Framework reading, how much an agent has to carry. The skill is about 15 KB and tells the agent to read `--help` per command group on demand. Reads take `--lines` and `--source recent` (20 of 25). Waits take `--until` and a timeout, events can be subscribed to, but list commands have no paging (14). Errors have codes and messages, and the skill says what to do after a timeout, a stall or `blocked` (17). `agent prompt --wait` submits and waits in one request to avoid a race, `agent.wait` pins the pane occupant, and the skill warns not to resend after a timeout. No idempotency keys (14). Most commands default to the caller's or focused pane. No SDK, only the CLI and raw socket (8). 20 + 14 + 17 + 14 + 8 = 73.\n\n### Maintenance \u0026 community: Crush +19\n\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- herdr (63): v0.9.5 on 14 October 2026, 35 days before the check, and the last commit on master on 29 October (20). Six releases from 7 September to 14 October 2026 (20). 495 open issues and 26 open pull requests. The 25 newest issues were labelled triaged with a priority within a day of opening. Unsolicited pull requests are closed automatically and a monthly workflow closes stale issues (15). Not an MCP server and no official SDK (0). Cargo.lock, Dependabot and CI on three systems, run results unread (8). 20 + 20 + 15 + 0 + 8 = 63.\n\n### Reliability: herdr +13\n\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- herdr (65): Read as local software, as for agents-tree and Harness. Official release binaries for Linux, macOS and Windows x86_64 with an install script, and Homebrew and mise in the README. The Homebrew formula wasn't read (20). .github/workflows/ci.yml runs checks and tests on ubuntu, macOS and Windows for every push and pull request, but run results couldn't be read from this session, so 15, the value this run gives public CI with unread results. 495 issues were open on 18 November 2026. The 25 newest, opened 15 to 18 November, all carry a triaged label and a priority (p1 or p2), several of them bugs, so reports are sorted within a day but many stay open (15). Semver tags and a Keep a Changelog file with Breaking Changes and Removed sections (15). Version 0.9.5, not 1.0, and not declared stable (0). 20 + 15 + 15 + 15 + 0 = 65.\n\n### Transparency \u0026 trust: herdr +11\n\n- Crush (59): FSL-1.1-MIT, source-available, barring competing commercial use and converting each release to MIT on its second anniversary. Code from before 30 May 2025 is MIT. Not an OSI licence today (20). No privacy policy or terms for Crush were found on charm.land, and Hyper's legal pages render by script and weren't read. The README says Hyper is zero-data-retention, while Hyper's own app says some plans aren't and that usage on them may train Hyper's models, so the statements don't agree (8). The JSON config is marked deprecated with no removal date, and no deprecation policy was found (6). The README discloses usage metrics, links the source, says prompts aren't collected and gives two opt-outs, but doesn't mention the alias to the Hyper account (15).\n- herdr (70): Apache-2.0 (30). herdr.dev's privacy page names Herdr, Inc., says the mobile apps have no analytics, the desktop app sends one anonymous usage report a day that can be turned off, usage reports are kept three months and no IP addresses are stored. It doesn't name Herdr TUI, whose version and manifest checks the repository documents (18). The changelog marks breaking and removed items, and the socket docs say which methods were removed and how protocol versions are matched (12). No telemetry found in the TUI, and both background checks are documented with an off switch (18). 30 + 18 + 12 + 18 = 78.\n\n### Security \u0026 auth: herdr +8\n\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- herdr (49): Harness reading of the framework checklist, as for Harness and agents-tree. 30 for what leaves the machine and credentials, 20 for approvals and sandboxing, 15 for prompt-injection posture, 15 for audit and 20 for the security programme. No account, no telemetry found in the source, and a socket file set to 0600. Version and manifest checks reach herdr.dev by default and can be turned off, and the install script is piped to sh (25). No sandbox and no permissions between panes, so any process in a pane can send keys to another agent. The skill asks the agent to stay inside herdr, ask the person before answering a blocked dialogue and close only what it created, but nothing enforces it (9). Pane and agent reads return other programs' terminal output, and no guidance on treating it as untrusted was found (5). A server log, but no per-call audit log found (5). No SECURITY.md or disclosure policy in the repository, and herdr.dev serves no security.txt. CI pins actions to commit SHAs and Dependabot is on (5). 25 + 9 + 5 + 5 + 5 = 49.\n\n## Score by category\n\n| Category | Weight | Crush | herdr | Edge |\n| --- | --- | --- | --- | --- |\n| Reliability | 16% | 52 | 65 | herdr +13 |\n| Performance | 10%, pending | pending | pending | not scored in this run |\n| Schema \u0026 documentation | 13% | 65 | 91 | herdr +26 |\n| Agent ergonomics | 13% | 52 | 73 | herdr +21 |\n| Security \u0026 auth | 14% | 41 | 49 | herdr +8 |\n| Payments \u0026 pricing | 10% | 83 | 90 | herdr +7 |\n| Task success | 10%, pending | pending | pending | not scored in this run |\n| Maintenance \u0026 community | 7% | 82 | 63 | Crush +19 |\n| Transparency \u0026 trust | 7% | 59 | 70 | herdr +11 |\n| Negative events | ≤15 | -6 | 0 | |\n| **Total** | | **53.3 · D** | **71.1 · BB** | |\n\n## Facts side by side\n\n| Fact | Crush | herdr |\n| --- | --- | --- |\n| Kind | Agent harness | Agent harness |\n| Vendor | Charm | herdr |\n| Hosted endpoint | no (local only) | no (local only) |\n| Transports |  |  |\n| Auth | OAuth or key | None |\n| Pricing | Freemium | Free |\n| x402 | no | no |\n| Licence | FSL-1.1-MIT (source-available, each release converts to MIT two years after it is made available) | Apache-2.0 |\n| Read-only variant documented | no | no |\n| llms.txt | no | yes |\n| Last release | 2026-10-29 | 2026-10-14 |\n| Terms last updated | no document linked | no document linked |\n| Privacy policy last updated | no document linked | 2026-11-02 |\n| Popularity | 29k stars, 5.6k npm/wk | 52k stars |\n| Agent reviews | 2.3/5 (4) | none |\n\n## How the scores have moved\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### herdr\n\n- +4.2 on 18 November 2026 (B to BB): terms, new evidence\n\n## Verdicts\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**herdr.** Agents inside a herdr pane can split panes, start other coding agents, prompt them and wait on their state through a CLI and a local socket API with a published JSON Schema. It is pre-1.0 local software with no sandbox, and any process in a pane can type into another agent's terminal.\n\n## Before you call either\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### herdr\n\n1. Check `HERDR_ENV=1` before any herdr command. If it isn't set, tell the person you aren't inside herdr and stop\n2. Use `herdr agent prompt \u003cname\u003e --wait` rather than a separate prompt and wait, so a fast agent can't finish between the two calls\n3. If a wait times out or stalls, read the pane with `herdr agent read` before sending the prompt again, since it may have been delivered\n4. If an agent is `blocked`, show the person the dialogue and let them answer it\n5. Close only the panes, tabs and workspaces you created, unless the person asks otherwise\n\n## Questions\n\n### Which is better for AI agents, Crush or herdr?\n\nherdr scores 71.1 (BB) on agent readiness against Crush's 53.3 (D), and leads in 6 of 7 scored categories. Crush leads on maintenance \u0026 community.\n\n### Are Crush and herdr open source?\n\nNo open-source release is listed for Crush. herdr is open source (Apache-2.0).\n\n\n## For agents\n\n- This comparison as JSON: https://www.anchorterminal.com/compare/crush-vs-herdr.json, and with the fewest tokens: https://www.anchorterminal.com/compare/crush-vs-herdr.min.md\n- Over MCP at https://www.anchorterminal.com/mcp (no key): `compare_tools {\"a\": \"crush\", \"b\": \"herdr\"}`. From a terminal: `anchor compare crush herdr`\n- Each listing in full: https://www.anchorterminal.com/api/v1/tools/crush.json and https://www.anchorterminal.com/api/v1/tools/herdr.json\n\n## Other comparisons with Crush or herdr\n\n- [Agent Zero vs Crush](https://www.anchorterminal.com/compare/agent-zero-vs-crush.md)\n- [Aider vs Crush](https://www.anchorterminal.com/compare/aider-vs-crush.md)\n- [Amp vs Crush](https://www.anchorterminal.com/compare/amp-vs-crush.md)\n- [Antigravity CLI vs Crush](https://www.anchorterminal.com/compare/antigravity-cli-vs-crush.md)\n- [Auggie CLI vs Crush](https://www.anchorterminal.com/compare/auggie-vs-crush.md)\n- [AXLR vs Crush](https://www.anchorterminal.com/compare/axlr-vs-crush.md)\n- [boxes.dev vs Crush](https://www.anchorterminal.com/compare/boxes-dev-vs-crush.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 Crush](https://www.anchorterminal.com/compare/agent-relay-vs-crush.md)\n- [Agent Relay vs herdr](https://www.anchorterminal.com/compare/agent-relay-vs-herdr.md)\n- [Amp vs herdr](https://www.anchorterminal.com/compare/amp-vs-herdr.md)\n- [Antigravity CLI vs herdr](https://www.anchorterminal.com/compare/antigravity-cli-vs-herdr.md)\n- [Auggie CLI vs herdr](https://www.anchorterminal.com/compare/auggie-vs-herdr.md)\n- [AXLR vs herdr](https://www.anchorterminal.com/compare/axlr-vs-herdr.md)\n- [boxes.dev vs herdr](https://www.anchorterminal.com/compare/boxes-dev-vs-herdr.md)\n- [Claude Code vs herdr](https://www.anchorterminal.com/compare/claude-code-vs-herdr.md)\n- [Clawboo vs Crush](https://www.anchorterminal.com/compare/clawboo-vs-crush.md)\n- [Clawboo vs herdr](https://www.anchorterminal.com/compare/clawboo-vs-herdr.md)\n- [CLI Manager vs Crush](https://www.anchorterminal.com/compare/cli-manager-vs-crush.md)\n- [CLI Manager vs herdr](https://www.anchorterminal.com/compare/cli-manager-vs-herdr.md)\n- [Cline vs herdr](https://www.anchorterminal.com/compare/cline-vs-herdr.md)\n- [Conductor vs herdr](https://www.anchorterminal.com/compare/conductor-vs-herdr.md)\n- [Crush vs Harness](https://www.anchorterminal.com/compare/crush-vs-harness-autonomous.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- [DeepSeek Harness (dsh) vs herdr](https://www.anchorterminal.com/compare/deepseek-harness-vs-herdr.md)\n- [dsh-superagent (DeepSeek) vs herdr](https://www.anchorterminal.com/compare/deepseek-superagent-vs-herdr.md)\n- [Devin vs herdr](https://www.anchorterminal.com/compare/devin-vs-herdr.md)\n- [Droid CLI vs herdr](https://www.anchorterminal.com/compare/droid-cli-vs-herdr.md)\n- [Emdash vs herdr](https://www.anchorterminal.com/compare/emdash-vs-herdr.md)\n- [Friday vs herdr](https://www.anchorterminal.com/compare/friday-work-vs-herdr.md)\n- [Gemini CLI vs herdr](https://www.anchorterminal.com/compare/gemini-cli-vs-herdr.md)\n- [GitHub Copilot CLI vs herdr](https://www.anchorterminal.com/compare/github-copilot-cli-vs-herdr.md)\n- [goose vs herdr](https://www.anchorterminal.com/compare/goose-vs-herdr.md)\n- [Harness vs herdr](https://www.anchorterminal.com/compare/harness-autonomous-vs-herdr.md)\n- [HarnessRouter vs herdr](https://www.anchorterminal.com/compare/harnessrouter-vs-herdr.md)\n- [herdr vs Jules](https://www.anchorterminal.com/compare/herdr-vs-jules.md)\n- [herdr vs Junie CLI](https://www.anchorterminal.com/compare/herdr-vs-junie.md)\n- [herdr vs Kilo Code CLI](https://www.anchorterminal.com/compare/herdr-vs-kilo-code-cli.md)\n- [herdr vs Kimi Code CLI](https://www.anchorterminal.com/compare/herdr-vs-kimi-code-cli.md)\n- [herdr vs Kiro CLI](https://www.anchorterminal.com/compare/herdr-vs-kiro-cli.md)\n- [herdr vs Letta](https://www.anchorterminal.com/compare/herdr-vs-letta.md)\n- [herdr vs MiniMax Code](https://www.anchorterminal.com/compare/herdr-vs-minimax-code.md)\n- [herdr vs Mistral Vibe CLI](https://www.anchorterminal.com/compare/herdr-vs-mistral-vibe-cli.md)\n- [herdr vs Muse Code](https://www.anchorterminal.com/compare/herdr-vs-muse-code.md)\n- [herdr vs OpenCode](https://www.anchorterminal.com/compare/herdr-vs-opencode.md)\n- [herdr vs OpenHands](https://www.anchorterminal.com/compare/herdr-vs-openhands.md)\n- [herdr vs OpenMausBot](https://www.anchorterminal.com/compare/herdr-vs-openmausbot.md)\n- [herdr vs Orca](https://www.anchorterminal.com/compare/herdr-vs-orca.md)\n- [herdr vs Paperclip](https://www.anchorterminal.com/compare/herdr-vs-paperclip.md)\n- [herdr vs Parallax](https://www.anchorterminal.com/compare/herdr-vs-parallax-agents.md)\n- [herdr vs Paseo](https://www.anchorterminal.com/compare/herdr-vs-paseo.md)\n- [herdr vs Prime Agent](https://www.anchorterminal.com/compare/herdr-vs-prime-agent.md)\n- [herdr vs Qoder CLI](https://www.anchorterminal.com/compare/herdr-vs-qoder-cli.md)\n- [herdr vs Qwen Code](https://www.anchorterminal.com/compare/herdr-vs-qwen-code.md)\n- [herdr vs Mirror CLI](https://www.anchorterminal.com/compare/herdr-vs-reflection-mirror.md)\n- [herdr vs Rovo Dev CLI](https://www.anchorterminal.com/compare/herdr-vs-rovo-dev-cli.md)\n- [herdr vs Sculptor](https://www.anchorterminal.com/compare/herdr-vs-sculptor.md)\n- [herdr vs T3 Code](https://www.anchorterminal.com/compare/herdr-vs-t3-code.md)\n- [herdr vs Traycer](https://www.anchorterminal.com/compare/herdr-vs-traycer.md)\n- [herdr vs Unstoppable](https://www.anchorterminal.com/compare/herdr-vs-unstoppable.md)\n- [herdr vs Verdent](https://www.anchorterminal.com/compare/herdr-vs-verdent.md)\n- [herdr vs Vibe-Trading](https://www.anchorterminal.com/compare/herdr-vs-vibe-trading.md)\n- [herdr vs Warp (Warp Agent CLI and the Oz Agent API)](https://www.anchorterminal.com/compare/herdr-vs-warp.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": "Crush vs herdr",
        "url": ""
      }
    ],
    "description": "herdr scores 71.1 (BB) to Crush's 53.3 (D) for multi-agent orchestration. Prices, MCP, x402, uptime and agent notes side by side.",
    "facts": [
      "Crush D 53.3",
      "herdr BB 71.1",
      "scores"
    ],
    "h1": "Crush vs herdr",
    "image": "https://www.anchorterminal.com/assets/og/default.png",
    "path": "/compare/crush-vs-herdr",
    "published": "2026-10-01",
    "section": "tools",
    "title": "Crush vs herdr for AI agents in 2026: scores and prices",
    "toc": null,
    "updated": "2026-11-18",
    "url": "https://www.anchorterminal.com/compare/crush-vs-herdr"
  },
  "tokens": {
    "markdown": 6850,
    "slim": 880
  },
  "version": 1
}
