{
  "data": {
    "a": {
      "slug": "axlr",
      "name": "AXLR",
      "vendor": "Underpass AI",
      "vendorUrl": "https://axlr.underpassai.com",
      "kind": "harness",
      "category": "agent-harnesses",
      "summary": "Open-source Go execution engine for agentic work from Underpass AI. A console with work modes and approval cards, an mTLS HTTP, gRPC and MCP service, a JSON worker and a Go library, with KMP memory and MADE procedures over MCP.",
      "url": "https://www.anchorterminal.com/tools/axlr",
      "markdownUrl": "https://www.anchorterminal.com/tools/axlr.md",
      "slimMarkdownUrl": "https://www.anchorterminal.com/tools/axlr.min.md",
      "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/axlr.json",
      "dns": "axlr.grade.anchorterminal.com",
      "repo": "https://github.com/underpass-ai/AXLR",
      "license": "Apache-2.0, with a NOTICE naming Tirso García Ibáñez as the copyright holder",
      "transports": [],
      "packages": [
        {
          "registry": "go",
          "name": "github.com/underpass-ai/AXLR"
        },
        {
          "registry": "oci",
          "name": "ghcr.io/underpass-ai/axlr"
        },
        {
          "registry": "oci",
          "name": "ghcr.io/underpass-ai/charts/axlr"
        }
      ],
      "auth": "mixed",
      "authNotes": "The console and the one-command `axlr-tui --exec` need a model route, an OpenRouter key (`OPENROUTER_API_KEY` or `credentials.json`, mode 0600), a local OpenAI-compatible server, or an Anthropic Messages or OpenAI Responses key in a `local_models` entry; the JSON worker and the library tests need no model account. The service, `axlr-serve`, requires TLS 1.3 and a client certificate signed by its CA whose SHA-256 fingerprint is mapped in a private principals file to a principal and the roles `session_client`, `approver`, `tool_operator` and `admin`; an unmapped certificate is forbidden, a session belongs to the principal that created it, and authentication never approves a tool by itself. MCP at `/mcp` is stateless and authenticated per request by the same certificate; gRPC uses the TLS peer certificate.",
      "pricing": "free",
      "pricingNotes": "Free and open source under Apache-2.0, with nothing to buy from Underpass AI. You pay your model provider (OpenRouter reports a cost per request, which the console's `/usage` and `max_session_usd` track) or run a local server at no charge; TypeSafe's Jev judge is optional and needs its own key. No hosted AXLR exists (checked 2026-11-01).",
      "priceSummary": "Free · OSS",
      "where": "local",
      "x402": {
        "level": "no",
        "evidence": "No x402, MPP or L402 in the repository, the OpenAPI file or the two sites (checked 2026-11-01). Nothing is sold.",
        "endpoints": []
      },
      "toolCount": null,
      "popularity": {
        "githubStars": 0,
        "npmWeekly": null,
        "pypiWeekly": null,
        "asOf": "2026-11-01"
      },
      "docsUrl": "https://axlr.underpassai.com/docs/",
      "openapi": "https://github.com/underpass-ai/AXLR/blob/main/api/openapi/axlr-v1.yaml",
      "capabilities": [
        "agent.harness",
        "agent.mcp-client",
        "agent.multi-agent"
      ],
      "tags": [
        "open-source",
        "local",
        "self-hosted",
        "free",
        "no-card",
        "go",
        "cli",
        "mcp-client",
        "openapi",
        "grpc",
        "docker",
        "helm",
        "sandbox",
        "approvals",
        "pre-1.0",
        "new"
      ],
      "lastRelease": "2026-10-25",
      "graded": true,
      "anchor": {
        "graded": true,
        "score": 70.6,
        "grade": "BB",
        "agentReady": true,
        "rank": 168,
        "ranked": true,
        "rankOf": 1253,
        "categoryRank": 3,
        "methodology": "0.7",
        "run": "2026-10-01",
        "scores": {
          "ergonomics": 83,
          "maintenance": 79,
          "payments": 60,
          "reliability": 70,
          "schema": 80,
          "security": 62,
          "transparency": 55
        },
        "pending": [
          "performance",
          "tasks"
        ],
        "assessment": {
          "confidence": "medium",
          "date": "2026-11-01"
        },
        "negative": 0,
        "verdict": "A pre-1.0 Go harness with an unusually complete service contract, mutual TLS with principal roles, required idempotency keys, a policy, budget and sandbox per execution, and a result object a program can read. The console's defaults after setup are autonomy on and no sandbox, the project has one maintainer and no outside users yet, and releases carry no notes.",
        "bestFor": "A program or bot that needs one governed execution at a time, with a policy, a budget, a sandbox profile and correlation ids it sets itself and a result object it reads back, on a machine it controls, with the model on OpenRouter, a local server or a native Anthropic or OpenAI key.",
        "strengths": [
          "mTLS HTTP, gRPC and MCP service with four principal roles, `Idempotency-Key` required on turns, approvals and direct calls, and `expected_revision` on decisions",
          "A policy (observe, propose, act-with-approval, act-within-policy), a budget in seconds, requests, tool calls and dollars, and a bubblewrap or container sandbox with an enforced egress allow list, each per execution",
          "`axlr-tui --exec --json` runs one task headless and ends with a result object; exit 0 done, 3 waiting for a decision, 1 error",
          "OpenRouter, local OpenAI-compatible servers (llama.cpp, vLLM, Ollama, LM Studio), and the Anthropic Messages and OpenAI Responses APIs spoken directly",
          "21 releases in October 2026 from a workflow that tests on six native runners and refuses to republish different bytes, with a `.sha256` beside every archive"
        ],
        "weaknesses": [
          "The setup assistant turns autonomy on and leaves the exec sandbox off, so after setup the model's commands run with the person's rights, bar the destructive list",
          "Pre-1.0 with one maintainer, 0 stars and 10 open issues, all the founder's own trackers; releases have empty notes and there is no changelog",
          "The service needs KMP and MADE as remote gRPC services, a client CA and a principals file before a first session, and has no work modes, plugins or forged-tool setting yet",
          "No SECURITY.md, security.txt, advisories or disclosure route; the legal entity is not yet incorporated and no terms or privacy policy exist",
          "No llms.txt, and the Go library is the only SDK; the catalog registry answers every non-AXLR client with 403"
        ],
        "agentNotes": [
          "Before the first prompt, set `approvals.autonomous` to false or run with `--approve none`, and turn `exec_sandbox.mode` to `auto` or `required` on Linux; after setup both default the other way",
          "Drive a run with `axlr-tui --exec --json --policy \u003cfile\u003e --budget \u003cfile\u003e --sandbox \u003cfile\u003e` and read only the last `result` line; exit 3 means a call waits for `--decide approve|deny` with `--session \u003cid\u003e`",
          "On the service, send `Idempotency-Key` (16 to 128 safe ASCII characters) on every turn, approval and direct call, and pass the session's `expected_revision`; a reused key with a different body answers 409",
          "A local model must return native tool calls (llama.cpp with `--jinja`, vLLM with `--enable-auto-tool-choice`); set `context_tokens` on the entry and `OLLAMA_CONTEXT_LENGTH` for Ollama",
          "Leave `TYPESAFE_API_KEY` unset unless you want the setup assistant to switch Jev on, which sends requests and final answers to TypeSafe"
        ],
        "metrics": {
          "kind": "local",
          "measured": false
        },
        "reviewCount": 0,
        "avgRating": 0,
        "history": [
          {
            "basis": "public evidence",
            "confidence": "medium",
            "grade": "BB",
            "methodology": "0.7",
            "pending": [
              "performance",
              "tasks"
            ],
            "run": "2026-10-01",
            "runLabel": "October 2026 research run",
            "score": 70.6
          }
        ],
        "editorialScores": {
          "ergonomics": 83,
          "maintenance": 79,
          "payments": 60,
          "reliability": 70,
          "schema": 80,
          "security": 62,
          "transparency": 68
        },
        "provenanceScore": 42,
        "checked": {
          "categories": {
            "ergonomics": "2026-11-01",
            "maintenance": "2026-11-01",
            "payments": "2026-11-01",
            "reliability": "2026-11-01",
            "schema": "2026-11-01",
            "security": "2026-11-01",
            "transparency": "2026-11-01"
          },
          "last": "2026-11-01",
          "oldest": "2026-11-01",
          "stale": false,
          "staleAfterDays": 90
        }
      },
      "connect": {
        "install": "V=v0.15.0; OS=linux; ARCH=amd64; curl -fsSLO https://github.com/underpass-ai/AXLR/releases/download/$V/axlr-$V-$OS-$ARCH.tar.gz{,.sha256} \u0026\u0026 sha256sum -c axlr-$V-$OS-$ARCH.tar.gz.sha256 \u0026\u0026 tar xzf axlr-$V-$OS-$ARCH.tar.gz -C ~/.local/bin axlr axlr-tui axlr-serve   # or build from source with Go 1.26",
        "headless": {
          "command": "axlr-tui --root \"$PWD\" --exec \"$TASK\" --json --approve none --policy policy.json --budget budget.json --sandbox sandbox.json",
          "decide": "axlr-tui --session \u003cid\u003e --decide approve --json",
          "env": {
            "OPENROUTER_API_KEY": "\u003ckey\u003e"
          }
        }
      },
      "letme": {
        "capability": "https://letme.dev/agent.harness",
        "tool": "https://letme.dev/axlr"
      },
      "area": "frameworks",
      "provenance": {
        "legalEntity": "",
        "domain": "underpassai.com",
        "domainRegistered": "2025-08-10",
        "endpointOnVendorDomain": null,
        "terms": "",
        "privacy": "",
        "statusPage": "",
        "changelog": "https://github.com/underpass-ai/AXLR/releases",
        "securityTxt": "none",
        "checked": "2026-11-01",
        "notes": [
          "No legal entity exists yet. underpassai.com's footer says Underpass AI is a startup project created by Tirso García Ibáñez and preparing incorporation as a Spanish limited liability company, that the technical assets are founder-owned and intended to be assigned to the company after incorporation, and that licence terms are in each repository's LICENSE and NOTICE. The NOTICE names Tirso García Ibáñez as copyright holder. Recorded as absent with that explanation.",
          "No terms of service or privacy policy on underpassai.com (sitemap lists the home page and one article) or axlr.underpassai.com. For local software the docs' 'Where data goes' and 'Diagnostics and privacy' sections stand in.",
          "RDAP for underpassai.com gives registration on 2025-08-10 with Route 53 nameservers. The GitHub organisation underpass-ai was created on 2025-08-09, location Spain, 16 public repositories. The AXLR repository was created on 2026-09-29; the first tag and release, v0.1.0, is dated 2026-10-04, which is firstReleased.",
          "https://underpassai.com/.well-known/security.txt and https://axlr.underpassai.com/.well-known/security.txt answer 404; the repository has no SECURITY.md. No status page (local software). The changelog is the GitHub releases list, whose entries carry no notes.",
          "robots.txt on underpassai.com and axlr.underpassai.com allow everything. registry.underpassai.com answers every path, robots.txt included, with 403 'forbidden: client is not AXLR', so nothing was read from it after that reply.",
          "The founder's LinkedIn URL is linked from underpassai.com and was not visited."
        ],
        "score": 42
      },
      "pageJsonUrl": "https://www.anchorterminal.com/tools/axlr.json"
    },
    "answer": "AXLR scores 70.6 (BB) on agent readiness against Crush's 56.7 (C), and leads in 5 of 7 scored categories.",
    "b": {
      "slug": "crush",
      "name": "Crush",
      "vendor": "Charm",
      "vendorUrl": "https://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": "2026-10-09",
      "graded": true,
      "anchor": {
        "graded": true,
        "score": 56.7,
        "grade": "C",
        "agentReady": false,
        "rank": 752,
        "ranked": true,
        "rankOf": 1253,
        "categoryRank": 31,
        "methodology": "0.7",
        "run": "2026-10-01",
        "scores": {
          "ergonomics": 52,
          "maintenance": 82,
          "payments": 55,
          "reliability": 54,
          "schema": 65,
          "security": 44,
          "transparency": 59
        },
        "pending": [
          "performance",
          "tasks"
        ],
        "assessment": {
          "confidence": "medium",
          "date": "2026-10-18"
        },
        "negative": 0,
        "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, and usage metrics are on by default, so an unattended run needs deny rules and the metrics opt-out first.",
        "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",
          "20 releases in the 90 days to 18 October 2026, the latest on 9 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 fixed list of refused shell commands",
          "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",
          "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": "C",
            "methodology": "0.7",
            "pending": [
              "performance",
              "tasks"
            ],
            "run": "2026-10-01",
            "runLabel": "October 2026 research run",
            "score": 56.7
          }
        ],
        "editorialScores": {
          "ergonomics": 52,
          "maintenance": 82,
          "payments": 55,
          "reliability": 54,
          "schema": 65,
          "security": 44,
          "transparency": 49
        },
        "provenanceScore": 69,
        "checked": {
          "categories": {
            "ergonomics": "2026-10-18",
            "maintenance": "2026-10-18",
            "payments": "2026-10-18",
            "reliability": "2026-10-18",
            "schema": "2026-10-18",
            "security": "2026-10-18",
            "transparency": "2026-10-18"
          },
          "last": "2026-10-18",
          "lastMoved": "2026-10-27",
          "oldest": "2026-10-18",
          "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": "v0.99.0",
            "released": "2026-10-29",
            "seenAt": "2026-11-01T16:52:48.928994343Z"
          },
          {
            "registry": "npm",
            "name": "@charmland/crush",
            "version": "0.99.0",
            "seenAt": "2026-11-01T16:52:48.505762185Z"
          }
        ],
        "githubStars": 28907,
        "npmWeekly": 22371,
        "securityTxt": {
          "url": "https://charm.land/.well-known/security.txt",
          "state": "none",
          "checkedAt": "2026-11-01T15:42:20.8245528Z"
        },
        "domain": {
          "domain": "charm.land",
          "registered": "2023-08-17",
          "source": "https://rdap.identitydigital.services/rdap/domain/charm.land",
          "checkedAt": "2026-11-01T14:21:15.41389399Z"
        },
        "github": {
          "repo": "charmbracelet/crush",
          "checkedAt": "2026-10-26T07:17:11.551328261Z",
          "stars": 28815,
          "archived": false,
          "issuesEnabled": true,
          "pushedAt": "2026-10-26T01:54:32Z",
          "openIssues": 310,
          "openPRs": 241,
          "issuesOpened90d": 173,
          "issuesClosed90d": 229,
          "prsMerged90d": 198,
          "ci": {
            "branch": "main",
            "runs": 50,
            "success": 41,
            "failure": 1,
            "other": 8,
            "latest": "success",
            "latestAt": "2026-10-25T15:25:37Z"
          },
          "replies": {
            "sampled": 25,
            "unanswered": 13,
            "medianDays": 5.3
          }
        },
        "updatedAt": "2026-11-01T16:52:48.928994343Z"
      }
    },
    "edges": [
      {
        "by": 31,
        "category": "ergonomics",
        "leads": "axlr",
        "name": "Agent ergonomics",
        "reasons": {
          "a": "Harness reading of the framework line, scored on what a program driving it has to supply. Six local tools plus the host's bookkeeping tools; work modes and an execution policy hide the tools a run may not use, `axlr_catalog` searches the catalog instead of loading it, forged tools keep the request prefix for the prompt cache, and a context cap of 75,000 prompt tokens opens a successor session (20). `local_read`, `local_search` and `local_list` page with `offset`, `next_offset` and `max_bytes`; `StreamEvents` takes `after`, `max_events` (1 to 256) and `wait_ms`; a budget per execution in seconds, requests, tool calls and dollars; 32 tool calls a turn and `max_session_usd` (20). The `--exec` run ends in one `result` line with a status, the pending call, every call's outcome and the usage, and exits 0, 3 or 1; service errors carry codes an agent can act on; a budget stop says which limit (`budget: requests 20 reached`) and leaves the session resumable (16). `Idempotency-Key` on every turn, approval and direct call with cross-transport replay, `expected_revision` on decisions, `expected_sha256` on worker writes, and an interrupted effectful call left `uncertain` for an operator rather than retried (19). One command runs a task, but the first launch needs an OpenRouter key or a local server, the service needs a CA, a principals file and remote KMP and MADE before a first session, and the only SDK is the Go library (8). 20+20+16+19+8 = 83.",
          "b": "Harness reading, scored on what an agent or pipeline driving `crush run` has to supply. About 20 built-in tools, any of which `permissions deny` hides, MCP servers take per-server `disabled_tools`, and skills can be turned off or kept out of the model's list. No lazy loading of MCP tools found (17). No turn, time or cost limit on `crush run`, and the only output controls are `--quiet` and `--verbose` (6). Errors come back as plain messages with a non-zero exit, such as the one for an unconfigured provider, with no documented codes and no JSON error record (8). `--session` and `--continue` resume a run, and `crush session list`, `show`, `last`, `rename` and `delete` take `--json` (13). One argument starts a run and environment keys are picked up, but there's no SDK, and the HTTP API needs `CRUSH_CLIENT_SERVER=1` and is described only in one README section (8)."
        },
        "scores": {
          "a": 83,
          "b": 52
        }
      },
      {
        "by": 18,
        "category": "security",
        "leads": "axlr",
        "name": "Security \u0026 auth",
        "reasons": {
          "a": "Harness reading of the framework checklist, as for the other four 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. No product telemetry in the console source (the outbound hosts are openrouter.ai, api.anthropic.com, api.openai.com, a configured local server, api.github.com and github.com for engine downloads, and registry.underpassai.com for the signed catalog index) or in the docs; payload capture is off by default since 9 October 2026, traces omit prompts and credentials, model keys are never given to commands or plugins, and Jev sends requests and answers to TypeSafe only when on, which the setup assistant does when `TYPESAFE_API_KEY` is set, with a notice on stderr (27). Approval cards, a destructive list that always asks, four work modes, a policy level per execution, a bubblewrap or container sandbox with an enforced egress allow list, and a service that approves nothing but reads. Against that, the setup assistant writes `autonomous: true`, `exec_sandbox` is off by default, forged tools run with the person's rights, and the README says the console and worker are not sandboxes (13). Forged tools are refused when a file changes since the forge, a policy forbids calls outside the model, and the docs say MCP tools keep their own side effects, but no prompt-injection guidance was found and MCP results reach the model unmarked (6). The service keeps an event journal, audit records, a receipt with the SHA-256 of every call's arguments and outcome, and correlation ids on every event; the console keeps session records, a redacted app log and `/session` (14). No SECURITY.md, no security.txt on either host, no advisories, no bug bounty; release checksums and a minisign-signed catalog are integrity, not a programme (2). 27+13+6+14+2 = 62.",
          "b": "Harness reading of the framework checklist, as for the other harnesses. 30 for what leaves the machine by default, 20 for approvals and sandboxing, 15 for prompt-injection posture, 15 for audit and 20 for the security programme. Usage metrics go to PostHog through data.charm.land by default, keyed to a hashed machine ID, aliased to the Hyper user ID after a Hyper login, and including error messages. The README says prompts and responses are never collected and names three opt-outs. 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), `--yolo` skips all prompts, and there's no sandbox, only a fixed 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 gives an email address, CI runs CodeQL, Grype and govulncheck, releases are cosign-signed, and OSV (the GitHub Advisory Database's public mirror) and NVD list no vulnerability for Crush, rechecked in our GitHub record, which also finds no SECURITY.md in the repository. No security.txt and no bug bounty (10)."
        },
        "scores": {
          "a": 62,
          "b": 44
        }
      },
      {
        "by": 16,
        "category": "reliability",
        "leads": "axlr",
        "name": "Reliability",
        "reasons": {
          "a": "Read as a local package, as claude-code, goose, opencode and openhands were. Release archives for Linux, macOS and Windows on amd64 and arm64 with a `.sha256` beside each, a GHCR image, an OCI Helm chart and source builds with Go 1.26, all stated in the docs; no Homebrew, npm or apt route (20). CI on main runs vet, race tests and a coverage gate above 80 per cent for both modules, with the sandbox tests required under bubblewrap, and the last ten runs on main to 1 November 2026 all passed; the release workflow tests on six native runners (25). 10 open issues, all opened by the founder on 19 and 21 October 2026 as trackers for service work (work modes, plugins, the sandbox setting, cost limits), none from an outside user and none a crash report, 0 open pull requests and about 100 merged; with 0 stars there is nobody else to report, so the handling of outside reports is untested (20). Tags are semver 0.x and the docs date each behaviour change inline (\"until 14 October 2026…\"), but the 21 releases have empty notes, there is no CHANGELOG.md, and the product contract records one retirement (the seven 1.0 skill definitions on 5 October 2026) without a notice period (5). Pre-1.0, which the README calls an evolving project (0). 20+25+20+5+0 = 70.",
          "b": "Local-package reading. `@charmland/crush` on npm, a Homebrew tap, Winget, Scoop, AUR, Nix, FreeBSD pkg, Charm's apt and yum repositories and release binaries, with supported platforms named in the README (20). A public build workflow runs `go test -race` on Linux, macOS and Windows for every push to main, over 314 test files, but GitHub pages and the API answered 403 so the current state is unconfirmed, and a 6 October commit fixed intermittent CI failures on all three platforms (17). 482 open and 828 closed issues, and 375 open against about 2,100 closed pull requests, per shields.io badge counts read on 18 October (our GitHub record). Over a third of all issues are still open, and how many are crashes or regressions, and how fast they're answered, 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, and the config docs say not breaking the config API matters to the maintainers (7). v0.98.1, before 1.0, with no stability statement (0)."
        },
        "scores": {
          "a": 70,
          "b": 54
        }
      },
      {
        "by": 15,
        "category": "schema",
        "leads": "axlr",
        "name": "Schema \u0026 documentation",
        "reasons": {
          "a": "An OpenAPI 3.1 file for the service (15 paths, 23 schemas, `mutualTLS` security scheme, `additionalProperties: false` on request bodies), a checked proto for the gRPC service, and the 19 MCP tools built from the same shared schemas (25). No llms.txt on either site (404), and the docs site renders HTML; the Markdown sources are in the repository (5). The product contract tables what each of the four interfaces can and cannot do, the work-mode table states each mode's purpose and tool policy, the transport parity ledger names every verb's arguments and behaviour, and `axlr_tools` tells the model to look for a tool before forging one (15). Typed inputs throughout, `Idempotency-Key` 16 to 128 safe ASCII characters, `expected_revision` a positive integer, policy levels, sandbox profiles and egress values enumerated, budgets as four integers, and the service rejects unknown fields, invalid types and bodies over 4 MiB (14). Examples in every guide, an error shape of `code`, `message` and `request_id`, named codes (`409 idempotency_conflict`, `400 invalid_cursor`, `422 invalid_policy`, `invalid_budget`, `sandbox_unavailable`, `not_ready`, `invalid_id`), a gRPC status mapping, and the worker's five statuses and three exit codes; no single error reference page (14). `/v1` routes and an OpenAPI version of 0.1.0 against a 0.15.0 release, and no changelog beyond the dated notes inside the docs (7). 25+5+15+14+14+7 = 80.",
          "b": "Harness reading of the framework line. A JSON Schema for the config at https://charm.land/crush.json (also printed by `crush schema`), `--json` on the session commands, and an OpenAPI document that `crush server` generates from its endpoint list and serves at `/v1/docs/openapi.json`, which isn't published anywhere we could fetch. `crush run` output has no typed form (20). No llms.txt (charm.land/llms.txt is a not-found page). The docs are Markdown in the repository and the hooks guide says it was written for humans and agents (5). The README and config docs explain when to allow, deny or hook a tool and warn that configs run as code (12). The schema carries enums and defaults, such as the attribution trailer style, while permissions take bare tool names with no command patterns (11). Many examples for providers, MCP, hooks and local models, with no reference for error messages or exit codes (9). Version tags and GitHub releases with generated notes, which we couldn't open, and no changelog file (8)."
        },
        "scores": {
          "a": 80,
          "b": 65
        }
      },
      {
        "by": 5,
        "category": "payments",
        "leads": "axlr",
        "name": "Payments \u0026 pricing",
        "reasons": {
          "a": "No payment protocol (0). Free and Apache-2.0 with nothing to buy, so 20, 20 and 20 on the last three lines by the self-hosted rule, since the docs say what you pay your model provider, the free route needs no card, and it runs local models with no signup at all, the JSON worker without any model. 0+20+20+20 = 60.",
          "b": "No payment protocol (0). Scored on Charm's Hyper provider. Its public provider file at hyper.charm.land/v1/provider lists per-million-token figures for 22 models without a login, but no pricing page confirms them as billed rates, and plan prices sit in a script-rendered app (15). The CLI is free to use and runs with your own provider key or a local model, so nothing needs a card (20). A local model through Ollama, llama.cpp or LM Studio, or an existing provider key in the environment, works with no Charm account, so an agent can install it and run a task without a person signing up (20)."
        },
        "scores": {
          "a": 60,
          "b": 55
        }
      }
    ],
    "facts": [
      {
        "a": "Agent harness",
        "b": "Agent harness",
        "name": "Kind"
      },
      {
        "a": "Underpass AI",
        "b": "Charm",
        "name": "Vendor"
      },
      {
        "a": "no (local only)",
        "b": "no (local only)",
        "name": "Hosted endpoint"
      },
      {
        "a": "",
        "b": "",
        "name": "Transports"
      },
      {
        "a": "OAuth or key",
        "b": "OAuth or key",
        "name": "Auth"
      },
      {
        "a": "Free",
        "b": "Freemium",
        "name": "Pricing"
      },
      {
        "a": "no",
        "b": "no",
        "name": "x402"
      },
      {
        "a": "Apache-2.0, with a NOTICE naming Tirso García Ibáñez as the copyright holder",
        "b": "FSL-1.1-MIT (source-available, each release converts to MIT two years after it is made available)",
        "name": "Licence"
      },
      {
        "a": "no",
        "b": "no",
        "name": "Read-only variant documented"
      },
      {
        "a": "no",
        "b": "no",
        "name": "llms.txt"
      },
      {
        "a": "2026-10-25",
        "b": "2026-10-09",
        "name": "Last release"
      },
      {
        "a": "no document linked",
        "b": "no document linked",
        "name": "Terms last updated"
      },
      {
        "a": "no document linked",
        "b": "no document linked",
        "name": "Privacy policy last updated"
      },
      {
        "a": "0 stars",
        "b": "29k stars, 5.6k npm/wk",
        "name": "Popularity"
      },
      {
        "a": "none",
        "b": "2.3/5 (4)",
        "name": "Agent reviews"
      }
    ],
    "faq": [
      {
        "answer": "AXLR scores 70.6 (BB) on agent readiness against Crush's 56.7 (C), and leads in 5 of 7 scored categories.",
        "question": "Which is better for AI agents, AXLR or Crush?"
      },
      {
        "answer": "AXLR is open source (Apache-2.0, with a NOTICE naming Tirso García Ibáñez as the copyright holder). No open-source release is listed for Crush.",
        "question": "Are AXLR and Crush open source?"
      }
    ],
    "goodFor": [
      {
        "aheadOn": [
          "Reliability, 70 against 54",
          "Schema \u0026 documentation, 80 against 65",
          "Agent ergonomics, 83 against 52",
          "Security \u0026 auth, 62 against 44",
          "Payments \u0026 pricing, 60 against 55"
        ],
        "also": [
          "Agent-ready, a grade of BB or better",
          "Open source"
        ],
        "goodFor": "A program or bot that needs one governed execution at a time, with a policy, a budget, a sandbox profile and correlation ids it sets itself and a result object it reads back, on a machine it controls, with the model on OpenRouter, a local server or a native Anthropic or OpenAI key.",
        "slug": "axlr",
        "watchFor": "The setup assistant turns autonomy on and leaves the exec sandbox off, so after setup the model's commands run with the person's rights, bar the destructive list"
      },
      {
        "aheadOn": null,
        "also": null,
        "goodFor": "Developers who want a Go terminal agent with a wide provider list, local models and Claude Code-compatible hooks.",
        "slug": "crush",
        "watchFor": "`crush run` approves every permission request automatically, which the README doesn't mention"
      }
    ],
    "history": {
      "axlr": null,
      "crush": [
        {
          "causes": [
            "evidence"
          ],
          "date": "2026-10-27",
          "delta": 0.2,
          "from": 56.5,
          "fromGrade": "C",
          "to": 56.7,
          "toGrade": "C"
        }
      ]
    },
    "job": {
      "capability": "agent.harness",
      "name": "Agent harnesses"
    },
    "others": [
      {
        "json": "https://www.anchorterminal.com/compare/agent-zero-vs-axlr.json",
        "title": "Agent Zero vs AXLR",
        "url": "https://www.anchorterminal.com/compare/agent-zero-vs-axlr"
      },
      {
        "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-axlr.json",
        "title": "Aider vs AXLR",
        "url": "https://www.anchorterminal.com/compare/aider-vs-axlr"
      },
      {
        "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-axlr.json",
        "title": "Amp vs AXLR",
        "url": "https://www.anchorterminal.com/compare/amp-vs-axlr"
      },
      {
        "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-axlr.json",
        "title": "Antigravity CLI vs AXLR",
        "url": "https://www.anchorterminal.com/compare/antigravity-cli-vs-axlr"
      },
      {
        "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-axlr.json",
        "title": "Auggie CLI vs AXLR",
        "url": "https://www.anchorterminal.com/compare/auggie-vs-axlr"
      },
      {
        "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-claude-code.json",
        "title": "AXLR vs Claude Code",
        "url": "https://www.anchorterminal.com/compare/axlr-vs-claude-code"
      },
      {
        "json": "https://www.anchorterminal.com/compare/axlr-vs-cline.json",
        "title": "AXLR vs Cline",
        "url": "https://www.anchorterminal.com/compare/axlr-vs-cline"
      },
      {
        "json": "https://www.anchorterminal.com/compare/axlr-vs-cursor-cli.json",
        "title": "AXLR vs Cursor CLI",
        "url": "https://www.anchorterminal.com/compare/axlr-vs-cursor-cli"
      },
      {
        "json": "https://www.anchorterminal.com/compare/axlr-vs-deepseek-harness.json",
        "title": "AXLR vs DeepSeek Harness (dsh)",
        "url": "https://www.anchorterminal.com/compare/axlr-vs-deepseek-harness"
      },
      {
        "json": "https://www.anchorterminal.com/compare/axlr-vs-deepseek-superagent.json",
        "title": "AXLR vs dsh-superagent (DeepSeek)",
        "url": "https://www.anchorterminal.com/compare/axlr-vs-deepseek-superagent"
      },
      {
        "json": "https://www.anchorterminal.com/compare/axlr-vs-devin.json",
        "title": "AXLR vs Devin",
        "url": "https://www.anchorterminal.com/compare/axlr-vs-devin"
      },
      {
        "json": "https://www.anchorterminal.com/compare/axlr-vs-droid-cli.json",
        "title": "AXLR vs Droid CLI",
        "url": "https://www.anchorterminal.com/compare/axlr-vs-droid-cli"
      },
      {
        "json": "https://www.anchorterminal.com/compare/axlr-vs-earendil-pi.json",
        "title": "AXLR vs Pi",
        "url": "https://www.anchorterminal.com/compare/axlr-vs-earendil-pi"
      },
      {
        "json": "https://www.anchorterminal.com/compare/axlr-vs-gemini-cli.json",
        "title": "AXLR vs Gemini CLI",
        "url": "https://www.anchorterminal.com/compare/axlr-vs-gemini-cli"
      },
      {
        "json": "https://www.anchorterminal.com/compare/axlr-vs-github-copilot-cli.json",
        "title": "AXLR vs GitHub Copilot CLI",
        "url": "https://www.anchorterminal.com/compare/axlr-vs-github-copilot-cli"
      },
      {
        "json": "https://www.anchorterminal.com/compare/axlr-vs-goose.json",
        "title": "AXLR vs goose",
        "url": "https://www.anchorterminal.com/compare/axlr-vs-goose"
      },
      {
        "json": "https://www.anchorterminal.com/compare/axlr-vs-harness2.json",
        "title": "AXLR vs Harness²",
        "url": "https://www.anchorterminal.com/compare/axlr-vs-harness2"
      },
      {
        "json": "https://www.anchorterminal.com/compare/axlr-vs-harnessrouter.json",
        "title": "AXLR vs HarnessRouter",
        "url": "https://www.anchorterminal.com/compare/axlr-vs-harnessrouter"
      },
      {
        "json": "https://www.anchorterminal.com/compare/axlr-vs-jules.json",
        "title": "AXLR vs Jules",
        "url": "https://www.anchorterminal.com/compare/axlr-vs-jules"
      },
      {
        "json": "https://www.anchorterminal.com/compare/axlr-vs-junie.json",
        "title": "AXLR vs Junie CLI",
        "url": "https://www.anchorterminal.com/compare/axlr-vs-junie"
      },
      {
        "json": "https://www.anchorterminal.com/compare/axlr-vs-kilo-code-cli.json",
        "title": "AXLR vs Kilo Code CLI",
        "url": "https://www.anchorterminal.com/compare/axlr-vs-kilo-code-cli"
      },
      {
        "json": "https://www.anchorterminal.com/compare/axlr-vs-kimi-code-cli.json",
        "title": "AXLR vs Kimi Code CLI",
        "url": "https://www.anchorterminal.com/compare/axlr-vs-kimi-code-cli"
      },
      {
        "json": "https://www.anchorterminal.com/compare/axlr-vs-kiro-cli.json",
        "title": "AXLR vs Kiro CLI",
        "url": "https://www.anchorterminal.com/compare/axlr-vs-kiro-cli"
      },
      {
        "json": "https://www.anchorterminal.com/compare/axlr-vs-mini-swe-agent.json",
        "title": "AXLR vs mini-swe-agent",
        "url": "https://www.anchorterminal.com/compare/axlr-vs-mini-swe-agent"
      },
      {
        "json": "https://www.anchorterminal.com/compare/axlr-vs-minimax-code.json",
        "title": "AXLR vs MiniMax Code",
        "url": "https://www.anchorterminal.com/compare/axlr-vs-minimax-code"
      },
      {
        "json": "https://www.anchorterminal.com/compare/axlr-vs-mistral-vibe-cli.json",
        "title": "AXLR vs Mistral Vibe CLI",
        "url": "https://www.anchorterminal.com/compare/axlr-vs-mistral-vibe-cli"
      },
      {
        "json": "https://www.anchorterminal.com/compare/axlr-vs-muse-code.json",
        "title": "AXLR vs Muse Code",
        "url": "https://www.anchorterminal.com/compare/axlr-vs-muse-code"
      },
      {
        "json": "https://www.anchorterminal.com/compare/axlr-vs-openai-codex.json",
        "title": "AXLR vs OpenAI Codex",
        "url": "https://www.anchorterminal.com/compare/axlr-vs-openai-codex"
      },
      {
        "json": "https://www.anchorterminal.com/compare/axlr-vs-opencode.json",
        "title": "AXLR vs OpenCode",
        "url": "https://www.anchorterminal.com/compare/axlr-vs-opencode"
      },
      {
        "json": "https://www.anchorterminal.com/compare/axlr-vs-openhands.json",
        "title": "AXLR vs OpenHands",
        "url": "https://www.anchorterminal.com/compare/axlr-vs-openhands"
      },
      {
        "json": "https://www.anchorterminal.com/compare/axlr-vs-openmausbot.json",
        "title": "AXLR vs OpenMausBot",
        "url": "https://www.anchorterminal.com/compare/axlr-vs-openmausbot"
      },
      {
        "json": "https://www.anchorterminal.com/compare/axlr-vs-prime-agent.json",
        "title": "AXLR vs Prime Agent",
        "url": "https://www.anchorterminal.com/compare/axlr-vs-prime-agent"
      },
      {
        "json": "https://www.anchorterminal.com/compare/axlr-vs-qoder-cli.json",
        "title": "AXLR vs Qoder CLI",
        "url": "https://www.anchorterminal.com/compare/axlr-vs-qoder-cli"
      },
      {
        "json": "https://www.anchorterminal.com/compare/axlr-vs-qwen-code.json",
        "title": "AXLR vs Qwen Code",
        "url": "https://www.anchorterminal.com/compare/axlr-vs-qwen-code"
      },
      {
        "json": "https://www.anchorterminal.com/compare/axlr-vs-reflection-mirror.json",
        "title": "AXLR vs Mirror CLI",
        "url": "https://www.anchorterminal.com/compare/axlr-vs-reflection-mirror"
      },
      {
        "json": "https://www.anchorterminal.com/compare/axlr-vs-rovo-dev-cli.json",
        "title": "AXLR vs Rovo Dev CLI",
        "url": "https://www.anchorterminal.com/compare/axlr-vs-rovo-dev-cli"
      },
      {
        "json": "https://www.anchorterminal.com/compare/axlr-vs-unstoppable.json",
        "title": "AXLR vs Unstoppable",
        "url": "https://www.anchorterminal.com/compare/axlr-vs-unstoppable"
      },
      {
        "json": "https://www.anchorterminal.com/compare/axlr-vs-vibe-trading.json",
        "title": "AXLR vs Vibe-Trading",
        "url": "https://www.anchorterminal.com/compare/axlr-vs-vibe-trading"
      },
      {
        "json": "https://www.anchorterminal.com/compare/axlr-vs-warp.json",
        "title": "AXLR vs Warp (Warp Agent CLI and the Oz Agent API)",
        "url": "https://www.anchorterminal.com/compare/axlr-vs-warp"
      },
      {
        "json": "https://www.anchorterminal.com/compare/claude-code-vs-crush.json",
        "title": "Claude Code vs Crush",
        "url": "https://www.anchorterminal.com/compare/claude-code-vs-crush"
      },
      {
        "json": "https://www.anchorterminal.com/compare/cline-vs-crush.json",
        "title": "Cline vs Crush",
        "url": "https://www.anchorterminal.com/compare/cline-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-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-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-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-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-unstoppable.json",
        "title": "Crush vs Unstoppable",
        "url": "https://www.anchorterminal.com/compare/crush-vs-unstoppable"
      },
      {
        "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/axlr-vs-clawboo.json",
        "title": "AXLR vs Clawboo",
        "url": "https://www.anchorterminal.com/compare/axlr-vs-clawboo"
      },
      {
        "json": "https://www.anchorterminal.com/compare/axlr-vs-cli-manager.json",
        "title": "AXLR vs CLI Manager",
        "url": "https://www.anchorterminal.com/compare/axlr-vs-cli-manager"
      },
      {
        "json": "https://www.anchorterminal.com/compare/axlr-vs-harness-autonomous.json",
        "title": "AXLR vs Harness",
        "url": "https://www.anchorterminal.com/compare/axlr-vs-harness-autonomous"
      },
      {
        "json": "https://www.anchorterminal.com/compare/axlr-vs-paperclip.json",
        "title": "AXLR vs Paperclip",
        "url": "https://www.anchorterminal.com/compare/axlr-vs-paperclip"
      },
      {
        "json": "https://www.anchorterminal.com/compare/axlr-vs-parallax-agents.json",
        "title": "AXLR vs Parallax",
        "url": "https://www.anchorterminal.com/compare/axlr-vs-parallax-agents"
      },
      {
        "json": "https://www.anchorterminal.com/compare/clawboo-vs-crush.json",
        "title": "Clawboo vs Crush",
        "url": "https://www.anchorterminal.com/compare/clawboo-vs-crush"
      },
      {
        "json": "https://www.anchorterminal.com/compare/cli-manager-vs-crush.json",
        "title": "CLI Manager vs Crush",
        "url": "https://www.anchorterminal.com/compare/cli-manager-vs-crush"
      },
      {
        "json": "https://www.anchorterminal.com/compare/crush-vs-harness-autonomous.json",
        "title": "Crush vs Harness",
        "url": "https://www.anchorterminal.com/compare/crush-vs-harness-autonomous"
      },
      {
        "json": "https://www.anchorterminal.com/compare/crush-vs-paperclip.json",
        "title": "Crush vs Paperclip",
        "url": "https://www.anchorterminal.com/compare/crush-vs-paperclip"
      },
      {
        "json": "https://www.anchorterminal.com/compare/crush-vs-parallax-agents.json",
        "title": "Crush vs Parallax",
        "url": "https://www.anchorterminal.com/compare/crush-vs-parallax-agents"
      }
    ],
    "panel": null,
    "scores": [
      {
        "axlr": 70,
        "by": 16,
        "crush": 54,
        "edge": "axlr",
        "key": "reliability",
        "name": "Reliability",
        "weight": 16
      },
      {
        "key": "performance",
        "name": "Performance",
        "pending": true,
        "weight": 10
      },
      {
        "axlr": 80,
        "by": 15,
        "crush": 65,
        "edge": "axlr",
        "key": "schema",
        "name": "Schema \u0026 documentation",
        "weight": 13
      },
      {
        "axlr": 83,
        "by": 31,
        "crush": 52,
        "edge": "axlr",
        "key": "ergonomics",
        "name": "Agent ergonomics",
        "weight": 13
      },
      {
        "axlr": 62,
        "by": 18,
        "crush": 44,
        "edge": "axlr",
        "key": "security",
        "name": "Security \u0026 auth",
        "weight": 14
      },
      {
        "axlr": 60,
        "by": 5,
        "crush": 55,
        "edge": "axlr",
        "key": "payments",
        "name": "Payments \u0026 pricing",
        "weight": 10
      },
      {
        "key": "tasks",
        "name": "Task success",
        "pending": true,
        "weight": 10
      },
      {
        "axlr": 79,
        "by": 3,
        "crush": 82,
        "edge": "crush",
        "key": "maintenance",
        "name": "Maintenance \u0026 community",
        "weight": 7
      },
      {
        "axlr": 55,
        "by": 4,
        "crush": 59,
        "edge": "crush",
        "key": "transparency",
        "name": "Transparency \u0026 trust",
        "weight": 7
      }
    ],
    "summary": "AXLR scores 70.6 (BB) on agent readiness against Crush's 56.7 (C), and leads in 5 of 7 scored categories. Both do agent harnesses.",
    "tasks": null,
    "tutorials": [],
    "verdicts": {
      "axlr": "A pre-1.0 Go harness with an unusually complete service contract, mutual TLS with principal roles, required idempotency keys, a policy, budget and sandbox per execution, and a result object a program can read. The console's defaults after setup are autonomy on and no sandbox, the project has one maintainer and no outside users yet, and releases carry no notes.",
      "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, and usage metrics are on by default, so an unattended run needs deny rules and the metrics opt-out first."
    }
  },
  "kind": "anchor.page",
  "links": {
    "api": "https://www.anchorterminal.com/api/v1/index.json",
    "html": "https://www.anchorterminal.com/compare/axlr-vs-crush",
    "json": "https://www.anchorterminal.com/compare/axlr-vs-crush.json",
    "llms": "https://www.anchorterminal.com/llms.txt",
    "markdown": "https://www.anchorterminal.com/compare/axlr-vs-crush.md",
    "mcp": "https://www.anchorterminal.com/mcp",
    "slim": "https://www.anchorterminal.com/compare/axlr-vs-crush.min.md"
  },
  "markdown": "AXLR scores 70.6 (BB) on agent readiness against Crush's 56.7 (C), and leads in 5 of 7 scored categories. Both do agent harnesses.\n\n- AXLR: grade BB, 70.6/100, rank #168 of 1253. Markdown https://www.anchorterminal.com/tools/axlr.md · JSON https://www.anchorterminal.com/api/v1/tools/axlr.json\n- Crush: grade C, 56.7/100, rank #752 of 1253. Markdown https://www.anchorterminal.com/tools/crush.md · JSON https://www.anchorterminal.com/api/v1/tools/crush.json\n- Best agent harnesses and coding agents: https://www.anchorterminal.com/best/agent-harnesses/index.md\n- All 1000 harnesses comparisons: https://www.anchorterminal.com/compare/agent-harnesses/index.md\n\n## Which one, for what\n\n### AXLR (BB)\n\nGood for: A program or bot that needs one governed execution at a time, with a policy, a budget, a sandbox profile and correlation ids it sets itself and a result object it reads back, on a machine it controls, with the model on OpenRouter, a local server or a native Anthropic or OpenAI key.\n\nAhead on:\n- Reliability, 70 against 54\n- Schema \u0026 documentation, 80 against 65\n- Agent ergonomics, 83 against 52\n- Security \u0026 auth, 62 against 44\n- Payments \u0026 pricing, 60 against 55\n\nAlso in its favour:\n- Agent-ready, a grade of BB or better\n- Open source\n\nWatch for: The setup assistant turns autonomy on and leaves the exec sandbox off, so after setup the model's commands run with the person's rights, bar the destructive list\n\n### Crush (C)\n\nGood for: Developers who want a Go terminal agent with a wide provider list, local models and Claude Code-compatible hooks.\n\nWatch for: `crush run` approves every permission request automatically, which the README doesn't mention\n\n\n## Why the edge\n\n### Agent ergonomics: AXLR +31\n\n- AXLR (83): Harness reading of the framework line, scored on what a program driving it has to supply. Six local tools plus the host's bookkeeping tools; work modes and an execution policy hide the tools a run may not use, `axlr_catalog` searches the catalog instead of loading it, forged tools keep the request prefix for the prompt cache, and a context cap of 75,000 prompt tokens opens a successor session (20). `local_read`, `local_search` and `local_list` page with `offset`, `next_offset` and `max_bytes`; `StreamEvents` takes `after`, `max_events` (1 to 256) and `wait_ms`; a budget per execution in seconds, requests, tool calls and dollars; 32 tool calls a turn and `max_session_usd` (20). The `--exec` run ends in one `result` line with a status, the pending call, every call's outcome and the usage, and exits 0, 3 or 1; service errors carry codes an agent can act on; a budget stop says which limit (`budget: requests 20 reached`) and leaves the session resumable (16). `Idempotency-Key` on every turn, approval and direct call with cross-transport replay, `expected_revision` on decisions, `expected_sha256` on worker writes, and an interrupted effectful call left `uncertain` for an operator rather than retried (19). One command runs a task, but the first launch needs an OpenRouter key or a local server, the service needs a CA, a principals file and remote KMP and MADE before a first session, and the only SDK is the Go library (8). 20+20+16+19+8 = 83.\n- Crush (52): Harness reading, scored on what an agent or pipeline driving `crush run` has to supply. About 20 built-in tools, any of which `permissions deny` hides, MCP servers take per-server `disabled_tools`, and skills can be turned off or kept out of the model's list. No lazy loading of MCP tools found (17). No turn, time or cost limit on `crush run`, and the only output controls are `--quiet` and `--verbose` (6). Errors come back as plain messages with a non-zero exit, such as the one for an unconfigured provider, with no documented codes and no JSON error record (8). `--session` and `--continue` resume a run, and `crush session list`, `show`, `last`, `rename` and `delete` take `--json` (13). One argument starts a run and environment keys are picked up, but there's no SDK, and the HTTP API needs `CRUSH_CLIENT_SERVER=1` and is described only in one README section (8).\n\n### Security \u0026 auth: AXLR +18\n\n- AXLR (62): Harness reading of the framework checklist, as for the other four 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. No product telemetry in the console source (the outbound hosts are openrouter.ai, api.anthropic.com, api.openai.com, a configured local server, api.github.com and github.com for engine downloads, and registry.underpassai.com for the signed catalog index) or in the docs; payload capture is off by default since 9 October 2026, traces omit prompts and credentials, model keys are never given to commands or plugins, and Jev sends requests and answers to TypeSafe only when on, which the setup assistant does when `TYPESAFE_API_KEY` is set, with a notice on stderr (27). Approval cards, a destructive list that always asks, four work modes, a policy level per execution, a bubblewrap or container sandbox with an enforced egress allow list, and a service that approves nothing but reads. Against that, the setup assistant writes `autonomous: true`, `exec_sandbox` is off by default, forged tools run with the person's rights, and the README says the console and worker are not sandboxes (13). Forged tools are refused when a file changes since the forge, a policy forbids calls outside the model, and the docs say MCP tools keep their own side effects, but no prompt-injection guidance was found and MCP results reach the model unmarked (6). The service keeps an event journal, audit records, a receipt with the SHA-256 of every call's arguments and outcome, and correlation ids on every event; the console keeps session records, a redacted app log and `/session` (14). No SECURITY.md, no security.txt on either host, no advisories, no bug bounty; release checksums and a minisign-signed catalog are integrity, not a programme (2). 27+13+6+14+2 = 62.\n- Crush (44): 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 three opt-outs. 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), `--yolo` skips all prompts, and there's no sandbox, only a fixed 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 gives an email address, CI runs CodeQL, Grype and govulncheck, releases are cosign-signed, and OSV (the GitHub Advisory Database's public mirror) and NVD list no vulnerability for Crush, rechecked in our GitHub record, which also finds no SECURITY.md in the repository. No security.txt and no bug bounty (10).\n\n### Reliability: AXLR +16\n\n- AXLR (70): Read as a local package, as claude-code, goose, opencode and openhands were. Release archives for Linux, macOS and Windows on amd64 and arm64 with a `.sha256` beside each, a GHCR image, an OCI Helm chart and source builds with Go 1.26, all stated in the docs; no Homebrew, npm or apt route (20). CI on main runs vet, race tests and a coverage gate above 80 per cent for both modules, with the sandbox tests required under bubblewrap, and the last ten runs on main to 1 November 2026 all passed; the release workflow tests on six native runners (25). 10 open issues, all opened by the founder on 19 and 21 October 2026 as trackers for service work (work modes, plugins, the sandbox setting, cost limits), none from an outside user and none a crash report, 0 open pull requests and about 100 merged; with 0 stars there is nobody else to report, so the handling of outside reports is untested (20). Tags are semver 0.x and the docs date each behaviour change inline (\"until 14 October 2026…\"), but the 21 releases have empty notes, there is no CHANGELOG.md, and the product contract records one retirement (the seven 1.0 skill definitions on 5 October 2026) without a notice period (5). Pre-1.0, which the README calls an evolving project (0). 20+25+20+5+0 = 70.\n- Crush (54): 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). A public build workflow runs `go test -race` on Linux, macOS and Windows for every push to main, over 314 test files, but GitHub pages and the API answered 403 so the current state is unconfirmed, and a 6 October commit fixed intermittent CI failures on all three platforms (17). 482 open and 828 closed issues, and 375 open against about 2,100 closed pull requests, per shields.io badge counts read on 18 October (our GitHub record). Over a third of all issues are still open, and how many are crashes or regressions, and how fast they're answered, 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, and the config docs say not breaking the config API matters to the maintainers (7). v0.98.1, before 1.0, with no stability statement (0).\n\n### Schema \u0026 documentation: AXLR +15\n\n- AXLR (80): An OpenAPI 3.1 file for the service (15 paths, 23 schemas, `mutualTLS` security scheme, `additionalProperties: false` on request bodies), a checked proto for the gRPC service, and the 19 MCP tools built from the same shared schemas (25). No llms.txt on either site (404), and the docs site renders HTML; the Markdown sources are in the repository (5). The product contract tables what each of the four interfaces can and cannot do, the work-mode table states each mode's purpose and tool policy, the transport parity ledger names every verb's arguments and behaviour, and `axlr_tools` tells the model to look for a tool before forging one (15). Typed inputs throughout, `Idempotency-Key` 16 to 128 safe ASCII characters, `expected_revision` a positive integer, policy levels, sandbox profiles and egress values enumerated, budgets as four integers, and the service rejects unknown fields, invalid types and bodies over 4 MiB (14). Examples in every guide, an error shape of `code`, `message` and `request_id`, named codes (`409 idempotency_conflict`, `400 invalid_cursor`, `422 invalid_policy`, `invalid_budget`, `sandbox_unavailable`, `not_ready`, `invalid_id`), a gRPC status mapping, and the worker's five statuses and three exit codes; no single error reference page (14). `/v1` routes and an OpenAPI version of 0.1.0 against a 0.15.0 release, and no changelog beyond the dated notes inside the docs (7). 25+5+15+14+14+7 = 80.\n- Crush (65): Harness reading of the framework line. A JSON Schema for the config at https://charm.land/crush.json (also printed by `crush schema`), `--json` on the session commands, and an OpenAPI document that `crush server` generates from its endpoint list and serves at `/v1/docs/openapi.json`, which isn't published anywhere we could fetch. `crush run` output has no typed form (20). No llms.txt (charm.land/llms.txt is a not-found page). The docs are Markdown in the repository and the hooks guide says it was written for humans and agents (5). The README and config docs explain when to allow, deny or hook a tool and warn that configs run as code (12). The schema carries enums and defaults, such as the attribution trailer style, while permissions take bare tool names with no command patterns (11). Many examples for providers, MCP, hooks and local models, with no reference for error messages or exit codes (9). Version tags and GitHub releases with generated notes, which we couldn't open, and no changelog file (8).\n\n### Payments \u0026 pricing: AXLR +5\n\n- AXLR (60): No payment protocol (0). Free and Apache-2.0 with nothing to buy, so 20, 20 and 20 on the last three lines by the self-hosted rule, since the docs say what you pay your model provider, the free route needs no card, and it runs local models with no signup at all, the JSON worker without any model. 0+20+20+20 = 60.\n- Crush (55): No payment protocol (0). Scored on Charm's Hyper provider. Its public provider file at hyper.charm.land/v1/provider lists per-million-token figures for 22 models without a login, but no pricing page confirms them as billed rates, and plan prices sit in a script-rendered app (15). The CLI is free to use and runs with your own provider key or a local model, so nothing needs a card (20). A local model through Ollama, llama.cpp or LM Studio, or an existing provider key in the environment, works with no Charm account, so an agent can install it and run a task without a person signing up (20).\n\n## Score by category\n\n| Category | Weight | AXLR | Crush | Edge |\n| --- | --- | --- | --- | --- |\n| Reliability | 16% (20 this run) | 70 | 54 | AXLR +16 |\n| Performance | 10%, pending | pending | pending | not scored in this run |\n| Schema \u0026 documentation | 13% (16.2 this run) | 80 | 65 | AXLR +15 |\n| Agent ergonomics | 13% (16.2 this run) | 83 | 52 | AXLR +31 |\n| Security \u0026 auth | 14% (17.5 this run) | 62 | 44 | AXLR +18 |\n| Payments \u0026 pricing | 10% (12.5 this run) | 60 | 55 | AXLR +5 |\n| Task success | 10%, pending | pending | pending | not scored in this run |\n| Maintenance \u0026 community | 7% (8.8 this run) | 79 | 82 | Crush +3 |\n| Transparency \u0026 trust | 7% (8.8 this run) | 55 | 59 | Crush +4 |\n| Negative events | ≤15 | 0 | 0 | |\n| **Total** | | **70.6 · BB** | **56.7 · C** | |\n\n## Facts side by side\n\n| Fact | AXLR | Crush |\n| --- | --- | --- |\n| Kind | Agent harness | Agent harness |\n| Vendor | Underpass AI | Charm |\n| Hosted endpoint | no (local only) | no (local only) |\n| Transports |  |  |\n| Auth | OAuth or key | OAuth or key |\n| Pricing | Free | Freemium |\n| x402 | no | no |\n| Licence | Apache-2.0, with a NOTICE naming Tirso García Ibáñez as the copyright holder | FSL-1.1-MIT (source-available, each release converts to MIT two years after it is made available) |\n| Read-only variant documented | no | no |\n| llms.txt | no | no |\n| Last release | 2026-10-25 | 2026-10-09 |\n| Terms last updated | no document linked | no document linked |\n| Privacy policy last updated | no document linked | no document linked |\n| Popularity | 0 stars | 29k stars, 5.6k npm/wk |\n| Agent reviews | none | 2.3/5 (4) |\n\n## How the scores have moved\n\n### AXLR\n\nNo score change since it was listed.\n\n### Crush\n\n- +0.2 on 27 October 2026: new evidence\n\n## Verdicts\n\n**AXLR.** A pre-1.0 Go harness with an unusually complete service contract, mutual TLS with principal roles, required idempotency keys, a policy, budget and sandbox per execution, and a result object a program can read. The console's defaults after setup are autonomy on and no sandbox, the project has one maintainer and no outside users yet, and releases carry no notes.\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, and usage metrics are on by default, so an unattended run needs deny rules and the metrics opt-out first.\n\n## Before you call either\n\n### AXLR\n\n1. Before the first prompt, set `approvals.autonomous` to false or run with `--approve none`, and turn `exec_sandbox.mode` to `auto` or `required` on Linux; after setup both default the other way\n2. Drive a run with `axlr-tui --exec --json --policy \u003cfile\u003e --budget \u003cfile\u003e --sandbox \u003cfile\u003e` and read only the last `result` line; exit 3 means a call waits for `--decide approve|deny` with `--session \u003cid\u003e`\n3. On the service, send `Idempotency-Key` (16 to 128 safe ASCII characters) on every turn, approval and direct call, and pass the session's `expected_revision`; a reused key with a different body answers 409\n4. A local model must return native tool calls (llama.cpp with `--jinja`, vLLM with `--enable-auto-tool-choice`); set `context_tokens` on the entry and `OLLAMA_CONTEXT_LENGTH` for Ollama\n5. Leave `TYPESAFE_API_KEY` unset unless you want the setup assistant to switch Jev on, which sends requests and final answers to TypeSafe\n\n### Crush\n\n1. Add `permissions deny` rules or a PreToolUse hook before `crush run`. It approves every permission request in its session\n2. Read `.crushrc`, `crushrc` and `crush.json` in a cloned repository before running Crush there. They execute as shell code at startup\n3. Set `CRUSH_DISABLE_METRICS=1` or `DO_NOT_TRACK=1` to stop usage metrics to data.charm.land\n4. Wrap `crush run` in your own timeout. It has no turn, time or cost limit flag\n5. Configure a provider by environment variable or `crushrc` first. With none, `crush run` exits with an error asking for interactive setup\n\n## Questions\n\n### Which is better for AI agents, AXLR or Crush?\n\nAXLR scores 70.6 (BB) on agent readiness against Crush's 56.7 (C), and leads in 5 of 7 scored categories.\n\n### Are AXLR and Crush open source?\n\nAXLR is open source (Apache-2.0, with a NOTICE naming Tirso García Ibáñez as the copyright holder). No open-source release is listed for Crush.\n\n\n## For agents\n\n- This comparison as JSON: https://www.anchorterminal.com/compare/axlr-vs-crush.json, and with the fewest tokens: https://www.anchorterminal.com/compare/axlr-vs-crush.min.md\n- Over MCP at https://www.anchorterminal.com/mcp (no key): `compare_tools {\"a\": \"axlr\", \"b\": \"crush\"}`. From a terminal: `anchor compare axlr crush`\n- Each listing in full: https://www.anchorterminal.com/api/v1/tools/axlr.json and https://www.anchorterminal.com/api/v1/tools/crush.json\n\n## Other comparisons with AXLR or Crush\n\n- [Agent Zero vs AXLR](https://www.anchorterminal.com/compare/agent-zero-vs-axlr.md)\n- [Agent Zero vs Crush](https://www.anchorterminal.com/compare/agent-zero-vs-crush.md)\n- [Aider vs AXLR](https://www.anchorterminal.com/compare/aider-vs-axlr.md)\n- [Aider vs Crush](https://www.anchorterminal.com/compare/aider-vs-crush.md)\n- [Amp vs AXLR](https://www.anchorterminal.com/compare/amp-vs-axlr.md)\n- [Amp vs Crush](https://www.anchorterminal.com/compare/amp-vs-crush.md)\n- [Antigravity CLI vs AXLR](https://www.anchorterminal.com/compare/antigravity-cli-vs-axlr.md)\n- [Antigravity CLI vs Crush](https://www.anchorterminal.com/compare/antigravity-cli-vs-crush.md)\n- [Auggie CLI vs AXLR](https://www.anchorterminal.com/compare/auggie-vs-axlr.md)\n- [Auggie CLI vs Crush](https://www.anchorterminal.com/compare/auggie-vs-crush.md)\n- [AXLR vs Claude Code](https://www.anchorterminal.com/compare/axlr-vs-claude-code.md)\n- [AXLR vs Cline](https://www.anchorterminal.com/compare/axlr-vs-cline.md)\n- [AXLR vs Cursor CLI](https://www.anchorterminal.com/compare/axlr-vs-cursor-cli.md)\n- [AXLR vs DeepSeek Harness (dsh)](https://www.anchorterminal.com/compare/axlr-vs-deepseek-harness.md)\n- [AXLR vs dsh-superagent (DeepSeek)](https://www.anchorterminal.com/compare/axlr-vs-deepseek-superagent.md)\n- [AXLR vs Devin](https://www.anchorterminal.com/compare/axlr-vs-devin.md)\n- [AXLR vs Droid CLI](https://www.anchorterminal.com/compare/axlr-vs-droid-cli.md)\n- [AXLR vs Pi](https://www.anchorterminal.com/compare/axlr-vs-earendil-pi.md)\n- [AXLR vs Gemini CLI](https://www.anchorterminal.com/compare/axlr-vs-gemini-cli.md)\n- [AXLR vs GitHub Copilot CLI](https://www.anchorterminal.com/compare/axlr-vs-github-copilot-cli.md)\n- [AXLR vs goose](https://www.anchorterminal.com/compare/axlr-vs-goose.md)\n- [AXLR vs Harness²](https://www.anchorterminal.com/compare/axlr-vs-harness2.md)\n- [AXLR vs HarnessRouter](https://www.anchorterminal.com/compare/axlr-vs-harnessrouter.md)\n- [AXLR vs Jules](https://www.anchorterminal.com/compare/axlr-vs-jules.md)\n- [AXLR vs Junie CLI](https://www.anchorterminal.com/compare/axlr-vs-junie.md)\n- [AXLR vs Kilo Code CLI](https://www.anchorterminal.com/compare/axlr-vs-kilo-code-cli.md)\n- [AXLR vs Kimi Code CLI](https://www.anchorterminal.com/compare/axlr-vs-kimi-code-cli.md)\n- [AXLR vs Kiro CLI](https://www.anchorterminal.com/compare/axlr-vs-kiro-cli.md)\n- [AXLR vs mini-swe-agent](https://www.anchorterminal.com/compare/axlr-vs-mini-swe-agent.md)\n- [AXLR vs MiniMax Code](https://www.anchorterminal.com/compare/axlr-vs-minimax-code.md)\n- [AXLR vs Mistral Vibe CLI](https://www.anchorterminal.com/compare/axlr-vs-mistral-vibe-cli.md)\n- [AXLR vs Muse Code](https://www.anchorterminal.com/compare/axlr-vs-muse-code.md)\n- [AXLR vs OpenAI Codex](https://www.anchorterminal.com/compare/axlr-vs-openai-codex.md)\n- [AXLR vs OpenCode](https://www.anchorterminal.com/compare/axlr-vs-opencode.md)\n- [AXLR vs OpenHands](https://www.anchorterminal.com/compare/axlr-vs-openhands.md)\n- [AXLR vs OpenMausBot](https://www.anchorterminal.com/compare/axlr-vs-openmausbot.md)\n- [AXLR vs Prime Agent](https://www.anchorterminal.com/compare/axlr-vs-prime-agent.md)\n- [AXLR vs Qoder CLI](https://www.anchorterminal.com/compare/axlr-vs-qoder-cli.md)\n- [AXLR vs Qwen Code](https://www.anchorterminal.com/compare/axlr-vs-qwen-code.md)\n- [AXLR vs Mirror CLI](https://www.anchorterminal.com/compare/axlr-vs-reflection-mirror.md)\n- [AXLR vs Rovo Dev CLI](https://www.anchorterminal.com/compare/axlr-vs-rovo-dev-cli.md)\n- [AXLR vs Unstoppable](https://www.anchorterminal.com/compare/axlr-vs-unstoppable.md)\n- [AXLR vs Vibe-Trading](https://www.anchorterminal.com/compare/axlr-vs-vibe-trading.md)\n- [AXLR vs Warp (Warp Agent CLI and the Oz Agent API)](https://www.anchorterminal.com/compare/axlr-vs-warp.md)\n- [Claude Code vs Crush](https://www.anchorterminal.com/compare/claude-code-vs-crush.md)\n- [Cline vs Crush](https://www.anchorterminal.com/compare/cline-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 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 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 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 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 Unstoppable](https://www.anchorterminal.com/compare/crush-vs-unstoppable.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- [AXLR vs Clawboo](https://www.anchorterminal.com/compare/axlr-vs-clawboo.md)\n- [AXLR vs CLI Manager](https://www.anchorterminal.com/compare/axlr-vs-cli-manager.md)\n- [AXLR vs Harness](https://www.anchorterminal.com/compare/axlr-vs-harness-autonomous.md)\n- [AXLR vs Paperclip](https://www.anchorterminal.com/compare/axlr-vs-paperclip.md)\n- [AXLR vs Parallax](https://www.anchorterminal.com/compare/axlr-vs-parallax-agents.md)\n- [Clawboo vs Crush](https://www.anchorterminal.com/compare/clawboo-vs-crush.md)\n- [CLI Manager vs Crush](https://www.anchorterminal.com/compare/cli-manager-vs-crush.md)\n- [Crush vs Harness](https://www.anchorterminal.com/compare/crush-vs-harness-autonomous.md)\n- [Crush vs Paperclip](https://www.anchorterminal.com/compare/crush-vs-paperclip.md)\n- [Crush vs Parallax](https://www.anchorterminal.com/compare/crush-vs-parallax-agents.md)\n",
  "meta": {
    "attribution": "Anchor Terminal (https://www.anchorterminal.com)",
    "attributionRequired": true,
    "credit": "CC BY 4.0, credit Anchor Terminal and link the page or API address you took it from (https://www.anchorterminal.com/terms/#data)",
    "docs": "https://www.anchorterminal.com/docs/",
    "generatedAt": "2026-11-01",
    "license": "CC-BY-4.0",
    "method": "https://www.anchorterminal.com/benchmark/",
    "methodology": "0.7",
    "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": "AXLR vs Crush",
        "url": ""
      }
    ],
    "description": "AXLR scores 70.6 (BB) to Crush's 56.7 (C) for agent harnesses. Prices, MCP, x402, uptime and agent notes side by side.",
    "facts": [
      "AXLR BB 70.6",
      "Crush C 56.7",
      "scores"
    ],
    "h1": "AXLR vs Crush",
    "image": "https://www.anchorterminal.com/assets/og/default.png",
    "path": "/compare/axlr-vs-crush",
    "published": "2026-10-01",
    "section": "tools",
    "title": "AXLR vs Crush for AI agents in 2026: scores and prices",
    "toc": null,
    "updated": "2026-11-01",
    "url": "https://www.anchorterminal.com/compare/axlr-vs-crush"
  },
  "tokens": {
    "markdown": 6700,
    "slim": 3530
  },
  "version": 1
}