{ "data": { "similar": [ { "grade": "BB", "json": "https://www.anchorterminal.com/tools/kilo-code-cli.json", "name": "Kilo Code CLI", "score": 75.4, "shared": [ "agent.harness", "agent.mcp-client", "agent.multi-agent" ], "slug": "kilo-code-cli" }, { "grade": "BB", "json": "https://www.anchorterminal.com/tools/goose.json", "name": "goose", "score": 73.9, "shared": [ "agent.harness", "agent.mcp-client", "agent.multi-agent" ], "slug": "goose" }, { "grade": "BB", "json": "https://www.anchorterminal.com/tools/qwen-code.json", "name": "Qwen Code", "score": 72.4, "shared": [ "agent.harness", "agent.mcp-client", "agent.multi-agent" ], "slug": "qwen-code" }, { "grade": "BB", "json": "https://www.anchorterminal.com/tools/openhands.json", "name": "OpenHands", "score": 70.8, "shared": [ "agent.harness", "agent.mcp-client", "agent.multi-agent" ], "slug": "openhands" }, { "grade": "B", "json": "https://www.anchorterminal.com/tools/opencode.json", "name": "OpenCode", "score": 67.7, "shared": [ "agent.harness", "agent.mcp-client", "agent.multi-agent" ], "slug": "opencode" }, { "grade": "B", "json": "https://www.anchorterminal.com/tools/gemini-cli.json", "name": "Gemini CLI", "score": 66.7, "shared": [ "agent.harness", "agent.mcp-client", "agent.multi-agent" ], "slug": "gemini-cli" } ], "tool": { "slug": "muse-code", "name": "Muse Code", "vendor": "Meta", "vendorUrl": "https://dev.meta.ai/products/muse-code", "kind": "harness", "category": "agent-harnesses", "summary": "Muse Code is Meta's coding agent for the terminal and CI, built for its Muse models. It plans, edits files and runs commands under approvals and an OS sandbox, interactively, headless through `muse exec` or from an SDK.", "url": "https://www.anchorterminal.com/tools/muse-code", "markdownUrl": "https://www.anchorterminal.com/tools/muse-code.md", "slimMarkdownUrl": "https://www.anchorterminal.com/tools/muse-code.min.md", "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/muse-code.json", "repo": "https://github.com/meta-models/muse-code-sdk", "license": "Proprietary binary, used under the Meta Model API Terms of Service, which cover Meta's coding harness. Subscriptions are also under the Meta Subscription Terms of Service. The TypeScript and Python SDKs in the linked repository are MIT.", "transports": [], "packages": [ { "registry": "npm", "name": "@muse-code/sdk" }, { "registry": "pypi", "name": "muse-code-sdk" } ], "auth": "mixed", "authNotes": "A browser sign-in to a Meta Model API account on first run, or a Meta Model API key in `META_API_KEY` or stored with `muse auth set`. A key takes priority over a browser session. CI runs and Meta Managed Accounts must use a key.", "pricing": "paid", "pricingNotes": "Pay-as-you-go at Meta Model API token prices, or a monthly plan at $5 (Everyday Usage), $15 (High Usage), $50 (Power Usage) or $200 (Maximum Usage), checked 2026-10-12. Muse Wonder Full needs Power Usage or Maximum Usage. No free plan or trial was found.", "priceSummary": "$5 / mo", "where": "local", "x402": { "level": "no", "evidence": "No x402, MPP or L402 in the Muse Code docs, the subscription pages or dev.meta.ai/llms.txt, checked 12 October 2026. Plans are paid through Meta Accounts Centre and pay-as-you-go through Model API billing.", "endpoints": [] }, "toolCount": null, "popularity": { "githubStars": null, "npmWeekly": 63119, "pypiWeekly": null, "asOf": "2026-10-12" }, "docsUrl": "https://dev.meta.ai/docs/muse-code", "llmsTxt": "https://dev.meta.ai/llms.txt", "capabilities": [ "agent.harness", "agent.mcp-client", "agent.multi-agent" ], "tags": [ "official", "harness", "coding-agent", "cli", "closed-source", "mcp", "llms-txt", "sandbox", "approvals", "card-required" ], "lastRelease": "2026-10-11", "graded": true, "anchor": { "graded": true, "score": 61.3, "grade": "C", "agentReady": false, "rank": 487, "ranked": true, "rankOf": 993, "categoryRank": 10, "methodology": "0.4", "run": "2026-10-01", "scores": { "ergonomics": 79, "maintenance": 75, "payments": 20, "reliability": 45, "schema": 84, "security": 67, "transparency": 57 }, "pending": [ "performance", "tasks" ], "breakdown": [ { "key": "reliability", "name": "Reliability", "weight": 16, "effectiveWeight": 20, "score": 45, "points": 9, "reason": "Local-package reading. Official installers for macOS, Linux and Windows that fetch a native binary from a release channel, with a SHA-256 check on the launcher and per-platform checksums in the release manifest (20). No public CI or test suite for the program, since the source isn't published. The SDK repository's workflows only publish to npm and PyPI (0). No public issue tracker for the CLI was found, so there's nothing to count either way. The SDK repository takes issues for the SDK and protocol only (5, a departure from the line, which assumes a tracker). Release notes per version under New, Improvements, Performance and Fixes, with security fixes labelled and deprecated aliases named inline, but no dates and no breaking-change heading (5). 1.4.6 (15). Same reading as Claude Code, which is also closed source." }, { "key": "performance", "name": "Performance", "weight": 10, "effectiveWeight": 0, "pending": true, "points": 0, "reason": "Pending. Latency is measured per call by our probes, which haven't run yet, so this run doesn't score it. Its weight is shared across the assessed categories until the first probe window closes." }, { "key": "schema", "name": "Schema \u0026 documentation", "weight": 13, "effectiveWeight": 16.25, "score": 84, "points": 13.65, "reason": "Framework reading. `muse schema` prints the JSON schema of a versioned session protocol, the protocol declarations and a stable manifest are published in the SDK repository, and `muse exec --json` emits JSONL events. No JSON Schema for `settings.json` was found (22 of 25). llms.txt at dev.meta.ai/llms.txt with a Markdown copy of each page (10). The permissions page says what each profile and flag is for and when to use it, such as Unrestricted only in an isolated environment, and the extending page says when to use subagents and when not to (16 of 20). Profiles, approval modes, sandbox network modes and reasoning-effort levels are enumerated, with MCP servers typed by transport (12 of 15). Examples on every page, exit codes for `muse exec`, and named settings errors, though no full list of run errors (12 of 15). A changelog for every version, with no dates (12 of 15)." }, { "key": "ergonomics", "name": "Agent ergonomics", "weight": 13, "effectiveWeight": 16.25, "score": 79, "points": 12.84, "reason": "Framework reading, adapted to a harness driven by a pipeline. `muse exec` runs one prompt with the MCP servers in settings, and named toolsets select MCP tools by name or prefix. We found no deferred tool loading in Muse Code's own docs (18 of 25). `--max-model-steps` stops a stuck run, and `muse export` writes a session record, but no budget cap or output schema was found (15 of 20). Exit codes 0, 1, 2, 130 and 143 are documented, and retry notices carry the provider error and HTTP status (16 of 20). `--session-id` continues a headless run, `muse export` and the event log support replay, and rewind branches without changing the original (18 of 20). TypeScript and Python SDKs. The defaults (Auto-review, proxy-only network) can stop for a review nobody answers in CI, so a pipeline has to choose a posture (12 of 15)." }, { "key": "security", "name": "Security \u0026 auth", "weight": 14, "effectiveWeight": 17.5, "score": 67, "points": 11.73, "reason": "Framework reading (telemetry defaults, approvals, guardrails, sandboxing), five lines. A browser session or a Model API key, cleared by `muse logout`. Settings include telemetry options, and the release notes mention opt-outs for feedback and diagnostic upload and for remote feature settings, but no page says what is sent or what is on by default. Subscriptions default to Contributor mode, so Meta may train on code unless the user turns it off, with a notice before the first request (10 of 30). Ask me, Auto-review and Unrestricted profiles, stage-by-stage review of compound shell commands, and an OS sandbox on by default that keeps `.git`, `.muse` and `.agents` read-only and refuses to run when it can't confirm containment. The default is Auto-review, an automated judge rather than a person (17 of 20). Network is proxy-only by default with per-destination review, and the docs warn that MCP tools are not sandboxed. The 1.4.6 notes fix `find -exec rm` running without approval and say a `find -exec sh -c` script still can (11 of 15). An append-only event log with replay and a record of who authorised each action, plus `muse export` (14 of 15). Meta's bug bounty, named in the SDK's SECURITY.md, a valid security.txt on www.facebook.com, and security fixes labelled in the release notes, but no published advisories for Muse Code (15 of 20). Judgement call, written by an agent on Claude, on the checklist the other harnesses got." }, { "key": "payments", "name": "Payments \u0026 pricing", "weight": 10, "effectiveWeight": 12.5, "score": 20, "points": 2.5, "reason": "Harness reading of the published rubric. No payment protocol (0). Plan prices ($5, $15, $50 and $200 a month) and Model API token prices are public without a login, with plan usage given as multiples of the Everyday plan's 10 to 50 prompts every 5 hours (20). No free plan or trial found, and pay-as-you-go needs a card on the Model API account (0). A person signs in through a browser or creates a key in the dashboard, and no local-model mode is documented (0)." }, { "key": "tasks", "name": "Task success", "weight": 10, "effectiveWeight": 0, "pending": true, "points": 0, "reason": "Pending. Task success needs the category task suites run through each tool, which haven't run yet, so this run doesn't score it. Its weight is shared across the assessed categories until then. A data provider's data-quality score is published on its listing now and becomes half of this category when it's scored." }, { "key": "maintenance", "name": "Maintenance \u0026 community", "weight": 7, "effectiveWeight": 8.75, "score": 75, "points": 6.56, "reason": "1.4.6, served by the muse-stable channel on 12 October 2026 and published as SDK 1.4.6 on 11 October (30). The SDK, released in step, published 1.3.0 on 18 September, 1.4.2 on 30 September, 1.4.4 on 8 October and 1.4.6 on 11 October (20). No public tracker for the CLI. The SDK repository takes issues with a written triage guide, and the help centre takes support tickets, neither tested (8 of 25). MIT TypeScript and Python SDKs at 1.4.6, labelled a developer preview (12 of 15). A checksummed launcher and release manifest, but no public CI for the program (5 of 10)." }, { "key": "transparency", "name": "Transparency \u0026 trust", "weight": 7, "effectiveWeight": 8.75, "score": 57, "points": 4.99, "note": "editorial 46, provenance 68", "reason": "Closed-source binary under the Meta Model API Terms of Service, with MIT SDKs (15). The subscription docs, the Contributor mode help page, the geographic use policy and the terms agree that a coding-harness subscription is in Contributor mode by default and that Standard mode content isn't used for training. Local sessions are kept forever unless `session_retention_days` is set, and no server-side retention period is stated (18 of 30). No deprecation policy. Deprecated aliases are named in undated release notes (5 of 20). Telemetry options exist in settings, with opt-outs mentioned in the release notes, but the data sent isn't documented (8 of 20)." } ], "assessment": { "date": "2026-10-12", "basis": "public evidence", "confidence": "medium", "notes": { "ergonomics": "Framework reading, adapted to a harness driven by a pipeline. `muse exec` runs one prompt with the MCP servers in settings, and named toolsets select MCP tools by name or prefix. We found no deferred tool loading in Muse Code's own docs (18 of 25). `--max-model-steps` stops a stuck run, and `muse export` writes a session record, but no budget cap or output schema was found (15 of 20). Exit codes 0, 1, 2, 130 and 143 are documented, and retry notices carry the provider error and HTTP status (16 of 20). `--session-id` continues a headless run, `muse export` and the event log support replay, and rewind branches without changing the original (18 of 20). TypeScript and Python SDKs. The defaults (Auto-review, proxy-only network) can stop for a review nobody answers in CI, so a pipeline has to choose a posture (12 of 15).", "maintenance": "1.4.6, served by the muse-stable channel on 12 October 2026 and published as SDK 1.4.6 on 11 October (30). The SDK, released in step, published 1.3.0 on 18 September, 1.4.2 on 30 September, 1.4.4 on 8 October and 1.4.6 on 11 October (20). No public tracker for the CLI. The SDK repository takes issues with a written triage guide, and the help centre takes support tickets, neither tested (8 of 25). MIT TypeScript and Python SDKs at 1.4.6, labelled a developer preview (12 of 15). A checksummed launcher and release manifest, but no public CI for the program (5 of 10).", "payments": "Harness reading of the published rubric. No payment protocol (0). Plan prices ($5, $15, $50 and $200 a month) and Model API token prices are public without a login, with plan usage given as multiples of the Everyday plan's 10 to 50 prompts every 5 hours (20). No free plan or trial found, and pay-as-you-go needs a card on the Model API account (0). A person signs in through a browser or creates a key in the dashboard, and no local-model mode is documented (0).", "reliability": "Local-package reading. Official installers for macOS, Linux and Windows that fetch a native binary from a release channel, with a SHA-256 check on the launcher and per-platform checksums in the release manifest (20). No public CI or test suite for the program, since the source isn't published. The SDK repository's workflows only publish to npm and PyPI (0). No public issue tracker for the CLI was found, so there's nothing to count either way. The SDK repository takes issues for the SDK and protocol only (5, a departure from the line, which assumes a tracker). Release notes per version under New, Improvements, Performance and Fixes, with security fixes labelled and deprecated aliases named inline, but no dates and no breaking-change heading (5). 1.4.6 (15). Same reading as Claude Code, which is also closed source.", "schema": "Framework reading. `muse schema` prints the JSON schema of a versioned session protocol, the protocol declarations and a stable manifest are published in the SDK repository, and `muse exec --json` emits JSONL events. No JSON Schema for `settings.json` was found (22 of 25). llms.txt at dev.meta.ai/llms.txt with a Markdown copy of each page (10). The permissions page says what each profile and flag is for and when to use it, such as Unrestricted only in an isolated environment, and the extending page says when to use subagents and when not to (16 of 20). Profiles, approval modes, sandbox network modes and reasoning-effort levels are enumerated, with MCP servers typed by transport (12 of 15). Examples on every page, exit codes for `muse exec`, and named settings errors, though no full list of run errors (12 of 15). A changelog for every version, with no dates (12 of 15).", "security": "Framework reading (telemetry defaults, approvals, guardrails, sandboxing), five lines. A browser session or a Model API key, cleared by `muse logout`. Settings include telemetry options, and the release notes mention opt-outs for feedback and diagnostic upload and for remote feature settings, but no page says what is sent or what is on by default. Subscriptions default to Contributor mode, so Meta may train on code unless the user turns it off, with a notice before the first request (10 of 30). Ask me, Auto-review and Unrestricted profiles, stage-by-stage review of compound shell commands, and an OS sandbox on by default that keeps `.git`, `.muse` and `.agents` read-only and refuses to run when it can't confirm containment. The default is Auto-review, an automated judge rather than a person (17 of 20). Network is proxy-only by default with per-destination review, and the docs warn that MCP tools are not sandboxed. The 1.4.6 notes fix `find -exec rm` running without approval and say a `find -exec sh -c` script still can (11 of 15). An append-only event log with replay and a record of who authorised each action, plus `muse export` (14 of 15). Meta's bug bounty, named in the SDK's SECURITY.md, a valid security.txt on www.facebook.com, and security fixes labelled in the release notes, but no published advisories for Muse Code (15 of 20). Judgement call, written by an agent on Claude, on the checklist the other harnesses got.", "transparency": "Closed-source binary under the Meta Model API Terms of Service, with MIT SDKs (15). The subscription docs, the Contributor mode help page, the geographic use policy and the terms agree that a coding-harness subscription is in Contributor mode by default and that Standard mode content isn't used for training. Local sessions are kept forever unless `session_retention_days` is set, and no server-side retention period is stated (18 of 30). No deprecation policy. Deprecated aliases are named in undated release notes (5 of 20). Telemetry options exist in settings, with opt-outs mentioned in the release notes, but the data sent isn't documented (8 of 20)." }, "sources": [ { "what": "Muse Code overview", "url": "https://dev.meta.ai/docs/muse-code.md", "seen": "2026-10-12" }, { "what": "authentication and billing", "url": "https://dev.meta.ai/docs/muse-code/auth.md", "seen": "2026-10-12" }, { "what": "subscriptions", "url": "https://dev.meta.ai/docs/muse-code/subscriptions.md", "seen": "2026-10-12" }, { "what": "permissions and safety", "url": "https://dev.meta.ai/docs/muse-code/permissions.md", "seen": "2026-10-12" }, { "what": "extending, MCP and headless runs", "url": "https://dev.meta.ai/docs/muse-code/extending.md", "seen": "2026-10-12" }, { "what": "configuration and context", "url": "https://dev.meta.ai/docs/muse-code/configuration.md", "seen": "2026-10-12" }, { "what": "changelog, 0.1.0 to 1.4.6", "url": "https://dev.meta.ai/docs/muse-code/changelog.md", "seen": "2026-10-12" }, { "what": "product page with plan prices", "url": "https://dev.meta.ai/products/muse-code", "seen": "2026-10-12" }, { "what": "subscription plans with prices", "url": "https://dev.meta.ai/help/subscriptions/what-is-a-muse-code-subscription", "seen": "2026-10-12" }, { "what": "Contributor mode in Muse Code", "url": "https://dev.meta.ai/help/subscriptions/muse-code-contributor-mode", "seen": "2026-10-12" }, { "what": "models and Muse Wonder availability", "url": "https://dev.meta.ai/docs/models.md", "seen": "2026-10-12" }, { "what": "Muse Wonder launch post", "url": "https://dev.meta.ai/resources/blog/build-with-muse-wonder", "seen": "2026-10-12" }, { "what": "Muse Code out of beta, 31 August 2026", "url": "https://dev.meta.ai/resources/blog/muse-code-new-plans-and-features", "seen": "2026-10-12" }, { "what": "Muse Code early beta, 5 August 2026", "url": "https://dev.meta.ai/resources/blog/build-with-muse-code", "seen": "2026-10-12" }, { "what": "installer and release channel manifest", "url": "https://api.meta.ai/muse-code/channels/muse-stable", "seen": "2026-10-12" }, { "what": "SDK repository, README, TRIAGE.md and SECURITY.md", "url": "https://github.com/meta-models/muse-code-sdk", "seen": "2026-10-12" }, { "what": "npm registry for @muse-code/sdk", "url": "https://registry.npmjs.org/@muse-code/sdk", "seen": "2026-10-12" }, { "what": "Meta Model API Terms of Service", "url": "https://dev.meta.ai/legal/terms-of-service", "seen": "2026-10-12" }, { "what": "Model Designation and Geographic Use Policy", "url": "https://dev.meta.ai/legal/geographic-use-policy", "seen": "2026-10-12" } ], "openQuestions": [ "unchecked: the CLI's own release dates. The changelog has no dates, so recency rests on the release channel serving 1.4.6 on 12 October and the SDK's npm publish of 1.4.6 on 11 October", "unchecked: what Muse Code's telemetry sends and what is on by default. The settings page lists telemetry options without detail", "unchecked: the open issues and maintainer replies on the SDK repository. GitHub's API was not available to our reader, and the CLI has no public tracker that we found", "The 1.4.6 release notes describe an approval gap that was fixed (`find -exec rm` ran without asking) and one that remains (`find -exec sh -c`). The sandbox still limits writes to the workspace. Recorded as a weakness with no deduction, a judgement call", "The product page says Muse Code is available for macOS and Windows, while the docs and the 31 August post give macOS, Linux and Windows. Graded on the docs", "No authenticated session was run" ] }, "negative": 0, "verdict": "Muse Code runs with approvals and an OS sandbox on by default, per-host network approval, an append-only event log and a headless mode with documented exit codes. It is the only route to Muse Wonder Full. It is closed source with undated release notes and no free route, and subscriptions allow training on code unless Contributor mode is turned off.", "bestFor": "Developers who want Meta's Muse models, Muse Wonder Full included, in a terminal or CI agent with the sandbox and approvals on from the first run.", "strengths": [ "Sandbox on by default (Seatbelt on macOS, bubblewrap on Linux), with `.git`, `.muse` and `.agents` read-only and shell commands refused if containment can't be confirmed", "Network access is proxy-only by default, and the first connection to each new host, port or protocol stops for review", "`muse exec --json` streams JSONL events, with exit codes 0, 1, 2, 130 and 143 documented and `--max-model-steps` to cap a run", "A versioned session protocol (`muse serve`, `muse schema`) with MIT-licensed TypeScript and Python SDKs released in step with the CLI", "MCP over stdio and streamable HTTP with OAuth 2.1 sign-in, and named toolsets that select MCP tools by name or prefix" ], "weaknesses": [ "Closed source, with no public CI or issue tracker for the CLI found and release notes that carry no dates", "Subscriptions default to Contributor mode, which lets Meta train on prompts, code and responses until it's turned off", "No free route. Plans run from $5 to $200 a month, and pay-as-you-go billing needs a card", "New sessions start in Auto-review, where an automated judge clears eligible approvals rather than a person", "MCP tools run outside the sandbox, and settings list telemetry options without documenting what is sent or the defaults" ], "agentNotes": [ "Set `META_API_KEY` for headless runs. Browser sign-in isn't available in CI or for Meta Managed Accounts", "Gate on your own test command, not the exit code. `muse exec` returns 0 when the turn completes even if tests still fail", "Pass `--max-model-steps` on unattended runs so a stuck task can't loop", "Prefer `--disable-approval` to `--yolo` in CI so the sandbox stays on. On Linux the runner needs a working bubblewrap and a non-musl build", "Turn Contributor mode off in `/settings` before a subscription session touches private code" ], "metrics": { "kind": "local", "measured": false }, "reviewCount": 0, "avgRating": 0, "history": [ { "basis": "public evidence", "confidence": "medium", "grade": "C", "methodology": "0.4", "pending": [ "performance", "tasks" ], "run": "2026-10-01", "runLabel": "October 2026 research run", "score": 61.3 } ], "editorialScores": { "ergonomics": 79, "maintenance": 75, "payments": 20, "reliability": 45, "schema": 84, "security": 67, "transparency": 46 }, "provenanceScore": 68 }, "connect": { "install": "curl -fsSL https://dev.meta.ai/install.sh | sh # Windows: irm https://dev.meta.ai/install.ps1 | iex", "headless": { "env": { "META_API_KEY": "\u003cyour-key\u003e" }, "run": "muse exec --json \"Refactor the auth module and run the tests.\"" } }, "letme": { "capability": "https://letme.dev/agent.harness", "tool": "https://letme.dev/muse-code" }, "sameCompany": [ "meta-model-api" ], "notable": [ "Muse Code launched as an early beta with Muse Spark 1.2 on 5 August 2026 (https://dev.meta.ai/resources/blog/build-with-muse-code) and left beta on 31 August 2026 with subscription plans and a developer preview of the SDK (https://dev.meta.ai/resources/blog/muse-code-new-plans-and-features)", "Muse Wonder (`muse-wonder-1.0`) arrived in Muse Code on 12 October 2026, on pay-as-you-go and every plan. Muse Wonder Full is available only in Muse Code, on the Power Usage and Maximum Usage plans (https://dev.meta.ai/docs/models.md)", "Subscriptions default to Contributor mode, which gives more usage in exchange for letting Meta train on prompts, code, files, context and responses, and can be turned off in `/settings` (https://dev.meta.ai/docs/muse-code/subscriptions.md)", "The 1.4.6 release notes say Ask me and Auto-review now ask before `find -delete` and `find -exec rm`, which ran without asking before, and that a `find -exec sh -c` script can still run without asking (https://dev.meta.ai/docs/muse-code/changelog.md)", "MCP tools are not sandboxed. A stdio server runs as an ordinary child process and a remote server as a direct network connection, with approval still applied (https://dev.meta.ai/docs/muse-code/extending.md)", "The npm weekly figure is for the SDK package @muse-code/sdk, 5 to 11 October 2026. The CLI is downloaded as a native binary and has no public download count (https://api.npmjs.org/downloads/point/last-week/@muse-code/sdk)" ], "area": "frameworks", "details": [ { "label": "Models", "value": "Meta's Muse models through Meta Model API. The default is `muse-spark-1.2`. Muse Wonder (`muse-wonder-1.0`) on pay-as-you-go and every plan, Muse Wonder Full on the Power Usage and Maximum Usage plans only. No other provider is documented." }, { "label": "Install", "value": "One-line installers for macOS and Linux (`install.sh`) and Windows (`install.ps1`) that fetch a native binary from a release channel and check SHA-256 sums. The product page says macOS and Windows, and the docs add Linux." }, { "label": "Permission profiles", "value": "Ask me, Auto-review (the default, an automated judge that falls back to asking) and Unrestricted (`--yolo`). Compound shell commands are reviewed stage by stage. Managed configuration can set policy." }, { "label": "Sandbox", "value": "On by default. Seatbelt on macOS, a bundled bubblewrap on Linux and a Windows sandbox that may ask for administrator approval. Network modes proxy-only (default), restricted and unrestricted." }, { "label": "MCP client", "value": "stdio and streamable HTTP servers in `mcp_servers`, OAuth 2.1 sign-in with `muse mcp login`, and named toolsets. Read-only tools skip the approval prompt. MCP tools are not sandboxed." }, { "label": "Headless", "value": "`muse exec` with `--json` JSONL events, `--prompt-file`, `--max-model-steps`, `--session-id` to continue a run and `muse export` for a session record. Subagents in isolated git worktrees and workflows for parallel work." }, { "label": "Plans", "value": "Everyday Usage $5, High Usage $15, Power Usage $50 and Maximum Usage $200 a month, with usage set as multiples of Everyday (10 to 50 prompts every 5 hours). Contributor mode is on by default for subscribers." }, { "label": "Release", "value": "1.4.6, the version the muse-stable channel served on 12 October 2026. The SDKs are released in step, with @muse-code/sdk 1.4.6 published on 11 October 2026. The CLI release notes have no dates." } ], "unitPrices": [ { "item": "Everyday Usage plan", "unit": "month", "usd": 5, "note": "10 to 50 prompts every 5 hours." }, { "item": "High Usage plan", "unit": "month", "usd": 15, "note": "5x the Everyday Usage plan." }, { "item": "Power Usage plan", "unit": "month", "usd": 50, "note": "20x the Everyday Usage plan, with Muse Wonder Full." }, { "item": "Maximum Usage plan", "unit": "month", "usd": 200, "note": "80x the Everyday Usage plan, with Muse Wonder Full." } ], "provenance": { "legalEntity": "Meta Platforms, Inc.", "domain": "meta.ai", "domainRegistered": "2017-12-16", "endpointOnVendorDomain": null, "terms": "https://dev.meta.ai/legal/terms-of-service", "privacy": "https://www.facebook.com/privacy/policy/", "statusPage": "", "changelog": "https://dev.meta.ai/docs/muse-code/changelog", "securityTxt": "none", "checked": "2026-10-12", "notes": [ "The Meta Model API Terms of Service (last updated 9 October 2026) cover an artificial intelligence coding harness and name Meta Platforms, Inc., or Meta Platforms Ireland Limited in the European Region. The subscription page adds the Meta Subscription Terms of Service.", "The privacy field is the Meta Privacy Policy, which the terms link. www.facebook.com's robots.txt asks readers like ours not to fetch it, as the 8 October policy reading records, so it wasn't read.", "RDAP for meta.ai gives a registration date of 16 December 2017. The model calls go to api.meta.ai, and the binaries download from lookaside.facebook.com.", "No status page for Meta Model API was found. dev.meta.ai/status redirects to the home page.", "dev.meta.ai/.well-known/security.txt returns 404. The SDK repository's SECURITY.md sends vulnerability reports to bugbounty.meta.com.", "dev.meta.ai/code and developer.meta.com/ai/products/muse-code redirect to dev.meta.ai/products/muse-code." ], "score": 68, "checks": [ { "check": "Legal entity named", "value": "Meta Platforms, Inc.", "points": 20, "max": 20, "state": "ok" }, { "check": "Domain age", "value": "meta.ai, registered 2017-12-16 (8 years)", "points": 11, "max": 15, "state": "part" }, { "check": "Endpoint on the vendor's domain", "value": "no hosted endpoint", "points": 0, "max": 0, "state": "na" }, { "check": "Terms of service", "value": "published", "points": 10, "max": 10, "state": "ok" }, { "check": "Privacy policy", "value": "published, but our reader couldn't read it", "points": 7, "max": 10, "state": "part" }, { "check": "Status page", "value": "not found", "points": 0, "max": 10, "state": "no" }, { "check": "Changelog", "value": "published", "points": 10, "max": 10, "state": "ok" }, { "check": "security.txt", "value": "not found", "points": 0, "max": 10, "state": "no" } ], "policies": [ { "kind": "terms", "url": "https://dev.meta.ai/legal/terms-of-service", "state": "not-read", "points": 10, "max": 10 }, { "kind": "privacy", "url": "https://www.facebook.com/privacy/policy/", "state": "unreadable", "reason": "robots.txt asks readers like ours not to fetch it", "readAt": "2026-10-08", "points": 7, "max": 10 } ] }, "pageJsonUrl": "https://www.anchorterminal.com/tools/muse-code.json", "live": { "slug": "muse-code", "versions": [ { "registry": "npm", "name": "@muse-code/sdk", "version": "1.4.6", "seenAt": "2026-10-12T22:16:21.710476766Z" }, { "registry": "pypi", "name": "muse-code-sdk", "version": "1.4.6", "released": "2026-10-11", "seenAt": "2026-10-12T22:16:21.971934495Z" } ], "githubStars": 57, "npmWeekly": 63119, "pypiWeekly": 198, "updatedAt": "2026-10-12T22:16:22.08500268Z" } }, "verify": { "accepts": "a page on meta.ai or one of its subdomains, or the README of github.com/meta-models/muse-code-sdk", "badgeUrl": "https://www.anchorterminal.com/badges/muse-code.svg", "body": { "slug": "muse-code", "url": "the page with the badge or the link" }, "docs": "https://www.anchorterminal.com/builders/#verify", "effect": "none, it never changes a grade, rank or review", "endpoint": "https://www.anchorterminal.com/api/v1/verify", "listingUrl": "https://www.anchorterminal.com/tools/muse-code", "mcpTool": "verify_listing", "recheck": "weekly; two failed checks in a row and it lapses, a later pass restores it", "snippets": { "html": "\u003ca href=\"https://www.anchorterminal.com/tools/muse-code\"\u003e\u003cimg src=\"https://www.anchorterminal.com/badges/muse-code.svg\" alt=\"Muse Code on Anchor Terminal\" height=\"20\"\u003e\u003c/a\u003e", "markdown": "[![Muse Code on Anchor Terminal](https://www.anchorterminal.com/badges/muse-code.svg)](https://www.anchorterminal.com/tools/muse-code)", "link": "\u003ca href=\"https://www.anchorterminal.com/tools/muse-code\"\u003eMuse Code on Anchor Terminal\u003c/a\u003e" } } }, "kind": "anchor.page", "links": { "api": "https://www.anchorterminal.com/api/v1/index.json", "html": "https://www.anchorterminal.com/tools/muse-code", "json": "https://www.anchorterminal.com/tools/muse-code.json", "llms": "https://www.anchorterminal.com/llms.txt", "markdown": "https://www.anchorterminal.com/tools/muse-code.md", "slim": "https://www.anchorterminal.com/tools/muse-code.min.md" }, "markdown": "## Overview\n\n**Grade C · 61.3/100 · rank #487 of 993 · #10 in Agent harnesses · not agent-ready · confidence medium**\n\n\nMore from Meta, listed separately because each is its own product: [Meta Model API](https://www.anchorterminal.com/tools/meta-model-api.md) (Model APIs \u0026 inference).\n\n## Assessment\n\nMuse Code runs with approvals and an OS sandbox on by default, per-host network approval, an append-only event log and a headless mode with documented exit codes. It is the only route to Muse Wonder Full. It is closed source with undated release notes and no free route, and subscriptions allow training on code unless Contributor mode is turned off.\n\n## Facts\n\n| Field | Value |\n| --- | --- |\n| Vendor | Meta (https://dev.meta.ai/products/muse-code) |\n| Kind | Agent harness |\n| Category | Agent harnesses (https://www.anchorterminal.com/categories/agent-harnesses) |\n| Auth | OAuth or key · A browser sign-in to a Meta Model API account on first run, or a Meta Model API key in `META_API_KEY` or stored with `muse auth set`. A key takes priority over a browser session. CI runs and Meta Managed Accounts must use a key. |\n| Pricing | Paid ($5 / mo) · Pay-as-you-go at Meta Model API token prices, or a monthly plan at $5 (Everyday Usage), $15 (High Usage), $50 (Power Usage) or $200 (Maximum Usage), checked 2026-10-12. Muse Wonder Full needs Power Usage or Maximum Usage. No free plan or trial was found. |\n| x402 | No · No x402, MPP or L402 in the Muse Code docs, the subscription pages or dev.meta.ai/llms.txt, checked 12 October 2026. Plans are paid through Meta Accounts Centre and pay-as-you-go through Model API billing. |\n| Licence | Proprietary binary, used under the Meta Model API Terms of Service, which cover Meta's coding harness. Subscriptions are also under the Meta Subscription Terms of Service. The TypeScript and Python SDKs in the linked repository are MIT. |\n| Packages | npm: `@muse-code/sdk`; pypi: `muse-code-sdk` |\n| Source | https://github.com/meta-models/muse-code-sdk |\n| Docs | https://dev.meta.ai/docs/muse-code |\n| llms.txt | https://dev.meta.ai/llms.txt |\n| Last release | 2026-10-11 |\n| npm downloads / week | 63,119 |\n| Models | Meta's Muse models through Meta Model API. The default is `muse-spark-1.2`. Muse Wonder (`muse-wonder-1.0`) on pay-as-you-go and every plan, Muse Wonder Full on the Power Usage and Maximum Usage plans only. No other provider is documented. |\n| Install | One-line installers for macOS and Linux (`install.sh`) and Windows (`install.ps1`) that fetch a native binary from a release channel and check SHA-256 sums. The product page says macOS and Windows, and the docs add Linux. |\n| Permission profiles | Ask me, Auto-review (the default, an automated judge that falls back to asking) and Unrestricted (`--yolo`). Compound shell commands are reviewed stage by stage. Managed configuration can set policy. |\n| Sandbox | On by default. Seatbelt on macOS, a bundled bubblewrap on Linux and a Windows sandbox that may ask for administrator approval. Network modes proxy-only (default), restricted and unrestricted. |\n| MCP client | stdio and streamable HTTP servers in `mcp_servers`, OAuth 2.1 sign-in with `muse mcp login`, and named toolsets. Read-only tools skip the approval prompt. MCP tools are not sandboxed. |\n| Headless | `muse exec` with `--json` JSONL events, `--prompt-file`, `--max-model-steps`, `--session-id` to continue a run and `muse export` for a session record. Subagents in isolated git worktrees and workflows for parallel work. |\n| Plans | Everyday Usage $5, High Usage $15, Power Usage $50 and Maximum Usage $200 a month, with usage set as multiples of Everyday (10 to 50 prompts every 5 hours). Contributor mode is on by default for subscribers. |\n| Release | 1.4.6, the version the muse-stable channel served on 12 October 2026. The SDKs are released in step, with @muse-code/sdk 1.4.6 published on 11 October 2026. The CLI release notes have no dates. |\n| Capabilities | agent.harness, agent.mcp-client, agent.multi-agent |\n| Tags | official, harness, coding-agent, cli, closed-source, mcp, llms-txt, sandbox, approvals, card-required |\n| JSON | https://www.anchorterminal.com/api/v1/tools/muse-code.json |\n\n## Score breakdown (methodology v0.4, October 2026 research run)\n\nAssessed 2026-10-12 from public evidence against the published checklist (https://www.anchorterminal.com/benchmark/#checklist). Confidence: medium. Performance and Task success pending (no score, not in the total); the total is Σ(score × weight) ÷ 80 over the 7 assessed categories. \"This run\" is each category's share of the 100 points.\n\n| Category | Weight | This run | Score (0–100) | Points |\n| --- | --- | --- | --- | --- |\n| Reliability | 16% | 20 | 45 | 9.0 |\n| Performance | 10% | pending | pending | n/a |\n| Schema \u0026 documentation | 13% | 16.2 | 84 | 13.7 |\n| Agent ergonomics | 13% | 16.2 | 79 | 12.8 |\n| Security \u0026 auth | 14% | 17.5 | 67 | 11.7 |\n| Payments \u0026 pricing | 10% | 12.5 | 20 | 2.5 |\n| Task success | 10% | pending | pending | n/a |\n| Maintenance \u0026 community | 7% | 8.8 | 75 | 6.6 |\n| Transparency \u0026 trust (editorial 46, provenance 68) | 7% | 8.8 | 57 | 5.0 |\n| Negative events | up to −15 | up to −15 | none recorded | 0 |\n| **Total** | | | | **61.3 → C** |\n\n### Why each score\n\n- Reliability 45: Local-package reading. Official installers for macOS, Linux and Windows that fetch a native binary from a release channel, with a SHA-256 check on the launcher and per-platform checksums in the release manifest (20). No public CI or test suite for the program, since the source isn't published. The SDK repository's workflows only publish to npm and PyPI (0). No public issue tracker for the CLI was found, so there's nothing to count either way. The SDK repository takes issues for the SDK and protocol only (5, a departure from the line, which assumes a tracker). Release notes per version under New, Improvements, Performance and Fixes, with security fixes labelled and deprecated aliases named inline, but no dates and no breaking-change heading (5). 1.4.6 (15). Same reading as Claude Code, which is also closed source.\n- Performance: Pending. Latency is measured per call by our probes, which haven't run yet, so this run doesn't score it. Its weight is shared across the assessed categories until the first probe window closes.\n- Schema \u0026 documentation 84: Framework reading. `muse schema` prints the JSON schema of a versioned session protocol, the protocol declarations and a stable manifest are published in the SDK repository, and `muse exec --json` emits JSONL events. No JSON Schema for `settings.json` was found (22 of 25). llms.txt at dev.meta.ai/llms.txt with a Markdown copy of each page (10). The permissions page says what each profile and flag is for and when to use it, such as Unrestricted only in an isolated environment, and the extending page says when to use subagents and when not to (16 of 20). Profiles, approval modes, sandbox network modes and reasoning-effort levels are enumerated, with MCP servers typed by transport (12 of 15). Examples on every page, exit codes for `muse exec`, and named settings errors, though no full list of run errors (12 of 15). A changelog for every version, with no dates (12 of 15).\n- Agent ergonomics 79: Framework reading, adapted to a harness driven by a pipeline. `muse exec` runs one prompt with the MCP servers in settings, and named toolsets select MCP tools by name or prefix. We found no deferred tool loading in Muse Code's own docs (18 of 25). `--max-model-steps` stops a stuck run, and `muse export` writes a session record, but no budget cap or output schema was found (15 of 20). Exit codes 0, 1, 2, 130 and 143 are documented, and retry notices carry the provider error and HTTP status (16 of 20). `--session-id` continues a headless run, `muse export` and the event log support replay, and rewind branches without changing the original (18 of 20). TypeScript and Python SDKs. The defaults (Auto-review, proxy-only network) can stop for a review nobody answers in CI, so a pipeline has to choose a posture (12 of 15).\n- Security \u0026 auth 67: Framework reading (telemetry defaults, approvals, guardrails, sandboxing), five lines. A browser session or a Model API key, cleared by `muse logout`. Settings include telemetry options, and the release notes mention opt-outs for feedback and diagnostic upload and for remote feature settings, but no page says what is sent or what is on by default. Subscriptions default to Contributor mode, so Meta may train on code unless the user turns it off, with a notice before the first request (10 of 30). Ask me, Auto-review and Unrestricted profiles, stage-by-stage review of compound shell commands, and an OS sandbox on by default that keeps `.git`, `.muse` and `.agents` read-only and refuses to run when it can't confirm containment. The default is Auto-review, an automated judge rather than a person (17 of 20). Network is proxy-only by default with per-destination review, and the docs warn that MCP tools are not sandboxed. The 1.4.6 notes fix `find -exec rm` running without approval and say a `find -exec sh -c` script still can (11 of 15). An append-only event log with replay and a record of who authorised each action, plus `muse export` (14 of 15). Meta's bug bounty, named in the SDK's SECURITY.md, a valid security.txt on www.facebook.com, and security fixes labelled in the release notes, but no published advisories for Muse Code (15 of 20). Judgement call, written by an agent on Claude, on the checklist the other harnesses got.\n- Payments \u0026 pricing 20: Harness reading of the published rubric. No payment protocol (0). Plan prices ($5, $15, $50 and $200 a month) and Model API token prices are public without a login, with plan usage given as multiples of the Everyday plan's 10 to 50 prompts every 5 hours (20). No free plan or trial found, and pay-as-you-go needs a card on the Model API account (0). A person signs in through a browser or creates a key in the dashboard, and no local-model mode is documented (0).\n- Task success: Pending. Task success needs the category task suites run through each tool, which haven't run yet, so this run doesn't score it. Its weight is shared across the assessed categories until then. A data provider's data-quality score is published on its listing now and becomes half of this category when it's scored.\n- Maintenance \u0026 community 75: 1.4.6, served by the muse-stable channel on 12 October 2026 and published as SDK 1.4.6 on 11 October (30). The SDK, released in step, published 1.3.0 on 18 September, 1.4.2 on 30 September, 1.4.4 on 8 October and 1.4.6 on 11 October (20). No public tracker for the CLI. The SDK repository takes issues with a written triage guide, and the help centre takes support tickets, neither tested (8 of 25). MIT TypeScript and Python SDKs at 1.4.6, labelled a developer preview (12 of 15). A checksummed launcher and release manifest, but no public CI for the program (5 of 10).\n- Transparency \u0026 trust 57: Closed-source binary under the Meta Model API Terms of Service, with MIT SDKs (15). The subscription docs, the Contributor mode help page, the geographic use policy and the terms agree that a coding-harness subscription is in Contributor mode by default and that Standard mode content isn't used for training. Local sessions are kept forever unless `session_retention_days` is set, and no server-side retention period is stated (18 of 30). No deprecation policy. Deprecated aliases are named in undated release notes (5 of 20). Telemetry options exist in settings, with opt-outs mentioned in the release notes, but the data sent isn't documented (8 of 20).\n\nFix list for a coding agent, everything this grade says the listing lacks, the biggest gain first (17 items): https://www.anchorterminal.com/fixes/muse-code.md (JSON https://www.anchorterminal.com/fixes/muse-code.json)\n\n### What we couldn't check\n\n- unchecked: the CLI's own release dates. The changelog has no dates, so recency rests on the release channel serving 1.4.6 on 12 October and the SDK's npm publish of 1.4.6 on 11 October\n- unchecked: what Muse Code's telemetry sends and what is on by default. The settings page lists telemetry options without detail\n- unchecked: the open issues and maintainer replies on the SDK repository. GitHub's API was not available to our reader, and the CLI has no public tracker that we found\n- The 1.4.6 release notes describe an approval gap that was fixed (`find -exec rm` ran without asking) and one that remains (`find -exec sh -c`). The sandbox still limits writes to the workspace. Recorded as a weakness with no deduction, a judgement call\n- The product page says Muse Code is available for macOS and Windows, while the docs and the 31 August post give macOS, Linux and Windows. Graded on the docs\n- No authenticated session was run\n\n### Sources\n\n- Muse Code overview: \u003chttps://dev.meta.ai/docs/muse-code.md\u003e (seen 2026-10-12)\n- authentication and billing: \u003chttps://dev.meta.ai/docs/muse-code/auth.md\u003e (seen 2026-10-12)\n- subscriptions: \u003chttps://dev.meta.ai/docs/muse-code/subscriptions.md\u003e (seen 2026-10-12)\n- permissions and safety: \u003chttps://dev.meta.ai/docs/muse-code/permissions.md\u003e (seen 2026-10-12)\n- extending, MCP and headless runs: \u003chttps://dev.meta.ai/docs/muse-code/extending.md\u003e (seen 2026-10-12)\n- configuration and context: \u003chttps://dev.meta.ai/docs/muse-code/configuration.md\u003e (seen 2026-10-12)\n- changelog, 0.1.0 to 1.4.6: \u003chttps://dev.meta.ai/docs/muse-code/changelog.md\u003e (seen 2026-10-12)\n- product page with plan prices: \u003chttps://dev.meta.ai/products/muse-code\u003e (seen 2026-10-12)\n- subscription plans with prices: \u003chttps://dev.meta.ai/help/subscriptions/what-is-a-muse-code-subscription\u003e (seen 2026-10-12)\n- Contributor mode in Muse Code: \u003chttps://dev.meta.ai/help/subscriptions/muse-code-contributor-mode\u003e (seen 2026-10-12)\n- models and Muse Wonder availability: \u003chttps://dev.meta.ai/docs/models.md\u003e (seen 2026-10-12)\n- Muse Wonder launch post: \u003chttps://dev.meta.ai/resources/blog/build-with-muse-wonder\u003e (seen 2026-10-12)\n- Muse Code out of beta, 31 August 2026: \u003chttps://dev.meta.ai/resources/blog/muse-code-new-plans-and-features\u003e (seen 2026-10-12)\n- Muse Code early beta, 5 August 2026: \u003chttps://dev.meta.ai/resources/blog/build-with-muse-code\u003e (seen 2026-10-12)\n- installer and release channel manifest: \u003chttps://api.meta.ai/muse-code/channels/muse-stable\u003e (seen 2026-10-12)\n- SDK repository, README, TRIAGE.md and SECURITY.md: \u003chttps://github.com/meta-models/muse-code-sdk\u003e (seen 2026-10-12)\n- npm registry for @muse-code/sdk: \u003chttps://registry.npmjs.org/@muse-code/sdk\u003e (seen 2026-10-12)\n- Meta Model API Terms of Service: \u003chttps://dev.meta.ai/legal/terms-of-service\u003e (seen 2026-10-12)\n- Model Designation and Geographic Use Policy: \u003chttps://dev.meta.ai/legal/geographic-use-policy\u003e (seen 2026-10-12)\n\n## Who's behind it (provenance 68/100, checked 2026-10-12)\n\n| Check | Finding | Points |\n| --- | --- | --- |\n| Legal entity named | Meta Platforms, Inc. | 20/20 |\n| Domain age | meta.ai, registered 2017-12-16 (8 years) | 11/15 |\n| Endpoint on the vendor's domain | no hosted endpoint | n/a |\n| Terms of service | published | 10/10 |\n| Privacy policy | published, but our reader couldn't read it | 7/10 |\n| Status page | not found | 0/10 |\n| Changelog | published | 10/10 |\n| security.txt | not found | 0/10 |\n\nThe Meta Model API Terms of Service (last updated 9 October 2026) cover an artificial intelligence coding harness and name Meta Platforms, Inc., or Meta Platforms Ireland Limited in the European Region. The subscription page adds the Meta Subscription Terms of Service.\n\nThe privacy field is the Meta Privacy Policy, which the terms link. www.facebook.com's robots.txt asks readers like ours not to fetch it, as the 8 October policy reading records, so it wasn't read.\n\nRDAP for meta.ai gives a registration date of 16 December 2017. The model calls go to api.meta.ai, and the binaries download from lookaside.facebook.com.\n\nNo status page for Meta Model API was found. dev.meta.ai/status redirects to the home page.\n\ndev.meta.ai/.well-known/security.txt returns 404. The SDK repository's SECURITY.md sends vulnerability reports to bugbounty.meta.com.\n\ndev.meta.ai/code and developer.meta.com/ai/products/muse-code redirect to dev.meta.ai/products/muse-code.\n\n### Terms and privacy, as read\n\nA reading by a fixed set of rules, each answered with the vendor's own sentence. Not legal advice.\n\n**Terms of service** (https://dev.meta.ai/legal/terms-of-service), not read yet.\n\n\n**Privacy policy** (https://www.facebook.com/privacy/policy/), read 2026-10-08. Our reader couldn't read it (robots.txt asks readers like ours not to fetch it).\n\n\n## Live (updated 2026-10-12 22:16 UTC)\n\n- npm `@muse-code/sdk` 1.4.6\n- pypi `muse-code-sdk` 1.4.6, released 2026-10-11\n- Always current: https://www.anchorterminal.com/api/v1/live/muse-code.json\n\n## Probe metrics\n\nNot measured yet. Our benchmark probes haven't run, so there's no availability, latency or error rate from a run and Performance is pending. Live uptime, where we poll the endpoint, is under Live and doesn't change the score.\n\n## Prices\n\n| Item | Price | Unit | Note |\n| --- | --- | --- | --- |\n| Everyday Usage plan | $5 | per month (plan) | 10 to 50 prompts every 5 hours. |\n| High Usage plan | $15 | per month (plan) | 5x the Everyday Usage plan. |\n| Power Usage plan | $50 | per month (plan) | 20x the Everyday Usage plan, with Muse Wonder Full. |\n| Maximum Usage plan | $200 | per month (plan) | 80x the Everyday Usage plan, with Muse Wonder Full. |\n\nAcross all listings: https://www.anchorterminal.com/prices/index.md\n\n## Strengths\n\n- Sandbox on by default (Seatbelt on macOS, bubblewrap on Linux), with `.git`, `.muse` and `.agents` read-only and shell commands refused if containment can't be confirmed\n- Network access is proxy-only by default, and the first connection to each new host, port or protocol stops for review\n- `muse exec --json` streams JSONL events, with exit codes 0, 1, 2, 130 and 143 documented and `--max-model-steps` to cap a run\n- A versioned session protocol (`muse serve`, `muse schema`) with MIT-licensed TypeScript and Python SDKs released in step with the CLI\n- MCP over stdio and streamable HTTP with OAuth 2.1 sign-in, and named toolsets that select MCP tools by name or prefix\n\n## Weaknesses\n\n- Closed source, with no public CI or issue tracker for the CLI found and release notes that carry no dates\n- Subscriptions default to Contributor mode, which lets Meta train on prompts, code and responses until it's turned off\n- No free route. Plans run from $5 to $200 a month, and pay-as-you-go billing needs a card\n- New sessions start in Auto-review, where an automated judge clears eligible approvals rather than a person\n- MCP tools run outside the sandbox, and settings list telemetry options without documenting what is sent or the defaults\n\n## Before you call it (notes for agents)\n\n1. Set `META_API_KEY` for headless runs. Browser sign-in isn't available in CI or for Meta Managed Accounts\n2. Gate on your own test command, not the exit code. `muse exec` returns 0 when the turn completes even if tests still fail\n3. Pass `--max-model-steps` on unattended runs so a stuck task can't loop\n4. Prefer `--disable-approval` to `--yolo` in CI so the sandbox stays on. On Linux the runner needs a working bubblewrap and a non-musl build\n5. Turn Contributor mode off in `/settings` before a subscription session touches private code\n\n## Connect\n\nInstall:\n\n```bash\ncurl -fsSL https://dev.meta.ai/install.sh | sh # Windows: irm https://dev.meta.ai/install.ps1 | iex\n```\n\nHeadless / CI:\n\n```json\n{\n \"env\": {\n \"META_API_KEY\": \"\\u003cyour-key\\u003e\"\n },\n \"run\": \"muse exec --json \\\"Refactor the auth module and run the tests.\\\"\"\n}\n```\n\n## Similar tools\n\nRanked by shared capabilities, then score. Same-category tools with no shared capability key are listed last.\n\n| Tool | Grade | Score | Rank | Shared capabilities | x402 | Markdown |\n| --- | --- | --- | --- | --- | --- | --- |\n| Kilo Code CLI | BB | 75.4 | 48 | agent.harness, agent.mcp-client, agent.multi-agent | no | https://www.anchorterminal.com/tools/kilo-code-cli.md |\n| goose | BB | 73.9 | 81 | agent.harness, agent.mcp-client, agent.multi-agent | no | https://www.anchorterminal.com/tools/goose.md |\n| Qwen Code | BB | 72.4 | 107 | agent.harness, agent.mcp-client, agent.multi-agent | no | https://www.anchorterminal.com/tools/qwen-code.md |\n| OpenHands | BB | 70.8 | 143 | agent.harness, agent.mcp-client, agent.multi-agent | no | https://www.anchorterminal.com/tools/openhands.md |\n| OpenCode | B | 67.7 | 247 | agent.harness, agent.mcp-client, agent.multi-agent | no | https://www.anchorterminal.com/tools/opencode.md |\n| Gemini CLI | B | 66.7 | 286 | agent.harness, agent.mcp-client, agent.multi-agent | no | https://www.anchorterminal.com/tools/gemini-cli.md |\n\n## Panel reviews (0)\n\nReviewed by the Anchor panel (https://www.anchorterminal.com/reviewers/index.md): .\n\nDesk reviews, written from public documentation, pricing, terms, source and status history on 1 October 2026. No calls made. For a desk review, the outcome says whether the reviewer's questions could be answered from public material: success, partial or failure. How reviews work: https://www.anchorterminal.com/reviews/how-it-works.md\n\n## Notable\n\n- Muse Code launched as an early beta with Muse Spark 1.2 on 5 August 2026 (https://dev.meta.ai/resources/blog/build-with-muse-code) and left beta on 31 August 2026 with subscription plans and a developer preview of the SDK (source: \u003chttps://dev.meta.ai/resources/blog/muse-code-new-plans-and-features\u003e)\n- Muse Wonder (`muse-wonder-1.0`) arrived in Muse Code on 12 October 2026, on pay-as-you-go and every plan. Muse Wonder Full is available only in Muse Code, on the Power Usage and Maximum Usage plans (source: \u003chttps://dev.meta.ai/docs/models.md\u003e)\n- Subscriptions default to Contributor mode, which gives more usage in exchange for letting Meta train on prompts, code, files, context and responses, and can be turned off in `/settings` (source: \u003chttps://dev.meta.ai/docs/muse-code/subscriptions.md\u003e)\n- The 1.4.6 release notes say Ask me and Auto-review now ask before `find -delete` and `find -exec rm`, which ran without asking before, and that a `find -exec sh -c` script can still run without asking (source: \u003chttps://dev.meta.ai/docs/muse-code/changelog.md\u003e)\n- MCP tools are not sandboxed. A stdio server runs as an ordinary child process and a remote server as a direct network connection, with approval still applied (source: \u003chttps://dev.meta.ai/docs/muse-code/extending.md\u003e)\n- The npm weekly figure is for the SDK package @muse-code/sdk, 5 to 11 October 2026. The CLI is downloaded as a native binary and has no public download count (source: \u003chttps://api.npmjs.org/downloads/point/last-week/@muse-code/sdk\u003e)\n\n- #10 of 22 in Best agent harnesses and coding agents: https://www.anchorterminal.com/best/agent-harnesses/index.md\n- All 226 harnesses comparisons: https://www.anchorterminal.com/compare/agent-harnesses/index.md\n\n## Compare\n\n- [Agent Zero vs Muse Code](https://www.anchorterminal.com/compare/agent-zero-vs-muse-code.md): C 54.2 vs C 61.3\n- [Aider vs Muse Code](https://www.anchorterminal.com/compare/aider-vs-muse-code.md): D 46.9 vs C 61.3\n- [Amp vs Muse Code](https://www.anchorterminal.com/compare/amp-vs-muse-code.md): C 57.1 vs C 61.3\n- [Antigravity CLI vs Muse Code](https://www.anchorterminal.com/compare/antigravity-cli-vs-muse-code.md): C 57.4 vs C 61.3\n- [Claude Code vs Muse Code](https://www.anchorterminal.com/compare/claude-code-vs-muse-code.md): C 61.9 vs C 61.3\n- [Cline vs Muse Code](https://www.anchorterminal.com/compare/cline-vs-muse-code.md): C 60.4 vs C 61.3\n- [Cursor CLI vs Muse Code](https://www.anchorterminal.com/compare/cursor-cli-vs-muse-code.md): F 35.3 vs C 61.3\n- [Devin vs Muse Code](https://www.anchorterminal.com/compare/devin-vs-muse-code.md): C 55.7 vs C 61.3\n- [Droid CLI vs Muse Code](https://www.anchorterminal.com/compare/droid-cli-vs-muse-code.md): C 59.1 vs C 61.3\n- [Pi vs Muse Code](https://www.anchorterminal.com/compare/earendil-pi-vs-muse-code.md): B 68.4 vs C 61.3\n- [Gemini CLI vs Muse Code](https://www.anchorterminal.com/compare/gemini-cli-vs-muse-code.md): B 66.7 vs C 61.3\n- [GitHub Copilot CLI vs Muse Code](https://www.anchorterminal.com/compare/github-copilot-cli-vs-muse-code.md): C 57.6 vs C 61.3\n- [goose vs Muse Code](https://www.anchorterminal.com/compare/goose-vs-muse-code.md): BB 73.9 vs C 61.3\n- [Kilo Code CLI vs Muse Code](https://www.anchorterminal.com/compare/kilo-code-cli-vs-muse-code.md): BB 75.4 vs C 61.3\n- [Kiro CLI vs Muse Code](https://www.anchorterminal.com/compare/kiro-cli-vs-muse-code.md): C 59.9 vs C 61.3\n- [Muse Code vs OpenAI Codex](https://www.anchorterminal.com/compare/muse-code-vs-openai-codex.md): C 61.3 vs BB 73\n- [Muse Code vs OpenCode](https://www.anchorterminal.com/compare/muse-code-vs-opencode.md): C 61.3 vs B 67.7\n- [Muse Code vs OpenHands](https://www.anchorterminal.com/compare/muse-code-vs-openhands.md): C 61.3 vs BB 70.8\n- [Muse Code vs Prime Agent](https://www.anchorterminal.com/compare/muse-code-vs-prime-agent.md): C 61.3 vs C 60.5\n- [Muse Code vs Qwen Code](https://www.anchorterminal.com/compare/muse-code-vs-qwen-code.md): C 61.3 vs BB 72.4\n- [Muse Code vs Paperclip](https://www.anchorterminal.com/compare/muse-code-vs-paperclip.md): C 61.3 vs C 59\n\n## Verify this listing\n\nFor the vendor. The badge or a plain link to this page verifies the listing, from a page on meta.ai or one of its subdomains, or the README of github.com/meta-models/muse-code-sdk. It shows the listing is the vendor's and that the vendor knows it's here, and it never changes a grade, rank or review. The vendor sends the page's address to `POST https://www.anchorterminal.com/api/v1/verify` as `{\"slug\": \"muse-code\", \"url\": \"…\"}`, or calls the `verify_listing` tool at https://www.anchorterminal.com/mcp. We fetch the page once, then again every week; two failed checks in a row and the verification lapses, and a later pass restores it. What we check: https://www.anchorterminal.com/builders/index.md#verify\n\nHTML badge:\n\n```html\n\u003ca href=\"https://www.anchorterminal.com/tools/muse-code\"\u003e\u003cimg src=\"https://www.anchorterminal.com/badges/muse-code.svg\" alt=\"Muse Code on Anchor Terminal\" height=\"20\"\u003e\u003c/a\u003e\n```\n\nMarkdown badge, for a README:\n\n```markdown\n[![Muse Code on Anchor Terminal](https://www.anchorterminal.com/badges/muse-code.svg)](https://www.anchorterminal.com/tools/muse-code)\n```\n\nPlain link:\n\n```html\n\u003ca href=\"https://www.anchorterminal.com/tools/muse-code\"\u003eMuse Code on Anchor Terminal\u003c/a\u003e\n```\n\n## Share this listing\n\nFor the vendor. Sharing assets for social media, two PNGs of 1200 × 630 that say Muse Code is listed on Anchor Terminal, with the vendor's logo and this page's address and no grade or score.\n\n- Dark: https://www.anchorterminal.com/assets/share/muse-code-dark.png\n- Light: https://www.anchorterminal.com/assets/share/muse-code-light.png\n", "meta": { "attribution": "Anchor Terminal (https://www.anchorterminal.com)", "docs": "https://www.anchorterminal.com/docs/", "generatedAt": "2026-10-12", "license": "CC-BY-4.0", "method": "https://www.anchorterminal.com/benchmark/", "methodology": "0.4", "openapi": "https://www.anchorterminal.com/openapi.json", "preview": false, "run": "2026-10-01", "runLabel": "October 2026 research run" }, "page": { "breadcrumbs": [ { "name": "Home", "url": "https://www.anchorterminal.com/" }, { "name": "Terminal", "url": "https://www.anchorterminal.com/tools/" }, { "name": "Agent harnesses", "url": "https://www.anchorterminal.com/categories/agent-harnesses" }, { "name": "Muse Code", "url": "" } ], "description": "Muse Code is Meta's coding agent for the terminal and CI, built for its Muse models. It plans, edits files and runs commands under approvals and an OS sandbox, interactively, headless through muse exec or from an SDK.", "facts": [ "rank #487 of 993", "OAuth or key auth", "0 desk reviews" ], "h1": "Muse Code", "image": "https://www.anchorterminal.com/assets/og/tools-muse-code.png", "path": "/tools/muse-code", "published": "2026-10-01", "section": "tools", "title": "Muse Code review (2026): pricing, alternatives and grade C", "toc": null, "updated": "2026-10-12", "url": "https://www.anchorterminal.com/tools/muse-code" }, "tokens": { "markdown": 6950, "slim": 1580 }, "version": 1 }