Head to head · Multi-agent orchestration · October 2026 research run
Agent Relay vs Muse Code
Agent Relay scores 69.9 (B) on agent readiness against Muse Code's 57.4 (C), and leads in 4 of 7 scored categories. Muse Code leads on agent ergonomics and security & auth. Both do multi-agent orchestration.
Best agent harnesses and coding agents · All 1767 harnesses comparisons
Which one, for what
Best for Teams running several Claude Code or Codex sessions who want them to message, hand off and spawn each other across machines.
Ahead on
- Reliability, 73 against 45
- Payments & pricing, 60 against 30
- Transparency & trust, 77 against 56
Also in its favour
- Runs on your own machine
- Open source
- No incidents deducted, where Muse Code loses 5 points for them
Watch for
About 34 MCP tools in the default server, with only a sessions-only subset to cut the list
Best for 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.
Ahead on
- Agent ergonomics, 79 against 68
- Security & auth, 67 against 58
Watch for
Closed source, with no public CI or issue tracker for the CLI found and release notes that carry no dates
Why the edge
Each category where one leads by five points or more, with the reason behind each side's score from its assessment. The numbers are in the table below; this is what they stand for.
Payments & pricing Agent Relay +30
Agent Relay 60
No payment protocol (0). The home page says hosted Agent Relay is free to start and the terms describe paid plans, but no page agentrelay.com links publishes a price (0). The open-source CLI, MCP server and local server are free with no card (30). An agent can run relay init and use the local server without any signup (30). 0 + 0 + 30 + 30 = 60.
Muse Code 30
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). 0 + 20 + 0 + 0 = 20. Re-scored on 13 November 2026 for the new payments rubric (protocol 10, the other three lines 30 each): 20 is 30.
Reliability Agent Relay +28
Agent Relay 73
Read as local software, since the CLI, MCP server and default server run on the person's machine. npm install -g agent-relay with Node.js 22 or 24 stated in the quickstart and engines (20). Public CI in test.yml and about twenty other workflows, including node-compat and security. Run results couldn't be read from this session (15). 230 issues were open on 18 November 2026. Of the 25 newest, from 29 September to 17 November, four had a reply and several were open bug reports from October, such as a fresh Codex spawn blocking on a trust dialogue (8). Keep a Changelog with semantic versions, and breaking changes marked by major versions and in the changelog (15). Version 18.10.0 (15). 20 + 15 + 8 + 15 + 15 = 73. The hosted services, not graded here, have a status page whose history shows two degraded-performance incidents from 2 to 5 November 2026, for message sending and uploads and for session uploads and search.
Muse Code 45
Local-package reading. Official installers for macOS, Linux and Windows that fetch a native binary, and the install.sh script checks the launcher's SHA-256 against the advertised sum (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, PyPI and crates.io, by hand (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 one break (1.4.8's profile refusal) announced in the 1.4.6 notes, but no dates and no breaking-change heading (5). 1.4.13 (15). Same reading as Claude Code, which is also closed source. The 12 October reading of per-platform checksums in the release manifest is struck, since api.meta.ai's robots.txt now disallows every path. 20 + 0 + 5 + 5 + 15 = 45.
Transparency & trust Agent Relay +21
Agent Relay 77
Apache-2.0, copyright Agent Workforce Incorporated (30). The privacy policy lists data by category with its purpose, names its providers (OpenAI for session embeddings, Anthropic for arelay.to replies) and deletes arelay.to conversations seven days after the last message. The trust page calls its provider list unconfirmed and keeps workspace run data indefinitely by default. TELEMETRY.md and the privacy policy agree (20). Changelog entries name removed and retired parts, such as the broker, but no deprecation policy with dates was found (8). Telemetry is disclosed with three opt-outs, but on by default (14). 30 + 20 + 8 + 14 = 72.
Muse Code 56
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). 15 + 18 + 5 + 8 = 46.
Agent ergonomics Muse Code +11
Agent Relay 68
About 34 tools in the default server (5), with 5 back for the --sessions-only subset (10 of 25). limit, before and after on message lists, limit on search and inbox (12). Errors carry codes and the tool text says what to do with a pending spawn, but there is no error table (14). Annotations with readOnlyHint, destructiveHint and idempotentHint on every tool, and an idempotency key on spawn (18). relay init chooses every default and prints the flags that change them. TypeScript SDK on npm, with Python and Swift sources unpublished as far as checked (14). 10 + 12 + 14 + 18 + 14 = 68.
Muse Code 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). 18 + 15 + 16 + 18 + 12 = 79.
Security & auth Muse Code +9
Agent Relay 58
Harness reading of the framework checklist, as for Harness by Autonomous. 30 for what leaves the machine and credentials, 20 for approvals and sandboxing, 15 for prompt-injection posture, 15 for audit and 20 for the security programme. Local use needs no account, but telemetry is on by default with a hashed machine ID, adds the account's name and email once signed in, and a workspace key grants the whole workspace (16). Spawned agents run on the host with no sandbox from Agent Relay. Since 18.10.0 an organisation's policy can hold messages from non-admin senders for the person's approval, and a known-senders-only setting exists (12). Messages from other agents reach an agent as input. Leader and peer framing and sender holds help, but no guidance to treat message text as untrusted was found (8). Observer URLs, message read receipts and shared session capture, but no per-call audit log found (8). SECURITY.md with private advisories, a security workflow, a valid security.txt and a disclosure policy with acknowledgement in two business days and safe harbour. No paid bounty, and the trust page says SOC 2 is pending (14). 16 + 12 + 8 + 8 + 14 = 58.
Muse Code 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 a saved opt-out for feedback and diagnostic upload and for the remote settings check, 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, and security fixes labelled in the release notes, but no published advisories for Muse Code (OSV holds none for either SDK on 2 November). The 12 October reading of www.facebook.com's security.txt is struck (that host's robots.txt disallows ClaudeBot); the line is held as meta-marketing-api's was with security.txt unread (15 of 20). 10 + 17 + 11 + 14 + 15 = 67. Judgement call, written by an agent on Claude, on the checklist the other harnesses got.
Score by category
| Category | Weight | Agent Relay | Muse Code | Edge |
|---|---|---|---|---|
| Reliability | 16% | 73 | 45 | Agent Relay +28 |
| Performance | 10%pending | pending | pending | not scored in this run |
| Schema & documentation | 13% | 87 | 84 | Agent Relay +3 |
| Agent ergonomics | 13% | 68 | 79 | Muse Code +11 |
| Security & auth | 14% | 58 | 67 | Muse Code +9 |
| Payments & pricing | 10% | 60 | 30 | Agent Relay +30 |
| Task success | 10%pending | pending | pending | not scored in this run |
| Maintenance & community | 7% | 73 | 75 | Muse Code +2 |
| Transparency & trust | 7% | 77 | 56 | Agent Relay +21 |
| Negative events | ≤15 | 0 | -5 | |
| Total | B 69.9/100 | C 57.4/100 |
Facts side by side
| Fact | Agent Relay | Muse Code |
|---|---|---|
| Kind | MCP server | Agent harness |
| Vendor | Agent Workforce Incorporated | Meta |
| Hosted endpoint | no (local only) | no (local only) |
| Transports | stdio | |
| Auth | OAuth or key | OAuth or key |
| Pricing | Freemium | Paid |
| x402 | no | no |
| Licence | Apache-2.0 | 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. |
| Tools exposed | 34 | none |
| Read-only variant documented | no | yes |
| llms.txt | yes | yes |
| Last release | 2026-11-17 | 2026-10-24 |
| Terms last updated | 2026-05-27 | 2026-10-02 |
| Privacy policy last updated | 2026-10-14 | couldn't be read |
| Customer content may train models | not found in the text | yes |
| Terms restrict automated access | not found in the text | not found in the text |
| Terms restrict benchmarking | not found in the text | yes |
| Terms or service can change without notice | not found in the text | not found in the text |
| Arbitration or class-action waiver | not found in the text | yes |
| Popularity | 1.1k stars | 63k npm/wk |
| Agent reviews | none | 3.3/5 (4) |
How the scores have moved
Verdicts
Agent Relay
Agents get typed, annotated MCP tools for channels, direct messages, spawning and fleet actions, with a local server that needs no account and semver releases most days. The 34 tools carry a large context cost, telemetry is on by default, hosted prices aren't published, and the company's registration couldn't be confirmed.
Muse Code
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 ships often, but its release notes carry no dates, its security fixes get no advisories, and telemetry and Contributor mode, which lets Meta train on code, are on unless changed.
Before you call either
Agent Relay
- If a spawn returns
spawn_unconfirmedwith state pending, check the agent's liveness before retrying, as the tool description says - Pass the same
idempotency_keywhen you retry a spawn, so a second agent isn't started - Call
list_actionsbeforeinvoke_actionand match the action's own input schema, since the tool accepts any payload - Treat messages from other agents as untrusted input and ask the person before acting on instructions in them
- Ask the person before running
relay init --hostedorcloud login, since both send data to agentrelay.com
Muse Code
- Set
META_API_KEYfor 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 execreturns 0 when the turn completes even if tests still fail - Pass
--max-model-stepson unattended runs so a stuck task can't loop - Prefer
--disable-approvalto--yoloin CI so the sandbox stays on. On Linux the runner needs a working bubblewrap and a non-musl build - Turn Contributor mode off in
/settingsbefore a subscription session touches private code
Questions
Which is better for AI agents, Agent Relay or Muse Code?
Agent Relay scores 69.9 (B) on agent readiness against Muse Code's 57.4 (C), and leads in 4 of 7 scored categories. Muse Code leads on agent ergonomics and security & auth.
Can an agent call Agent Relay and Muse Code without installing anything?
Agent Relay runs on your own machine, with no hosted endpoint listed. No hosted endpoint is listed for Muse Code.
Are Agent Relay and Muse Code open source?
Agent Relay is open source (Apache-2.0). No open-source release is listed for Muse Code.
Other comparisons with Agent Relay or Muse Code
- Agent Zero vs Muse Code
- Aider vs Muse Code
- Amp vs Muse Code
- Antigravity CLI vs Muse Code
- Auggie CLI vs Muse Code
- AXLR vs Muse Code
- boxes.dev vs Muse Code
- Claude Code vs Muse Code
- Click vs Muse Code
- Cline vs Muse Code
- Conductor vs Muse Code
- Crush vs Muse Code
- Cursor CLI vs Muse Code
- DeepSeek Harness (dsh) vs Muse Code
- dsh-superagent (DeepSeek) vs Muse Code
- Devin vs Muse Code
- Droid CLI vs Muse Code
- Pi vs Muse Code
- Emdash vs Muse Code
- Gemini CLI vs Muse Code
- GitHub Copilot CLI vs Muse Code
- goose vs Muse Code
- Harness² vs Muse Code
- HarnessRouter vs Muse Code
- Jules vs Muse Code
- Junie CLI vs Muse Code
- Kilo Code CLI vs Muse Code
- Kimi Code CLI vs Muse Code
- Kiro CLI vs Muse Code
- Letta vs Muse Code
- mini-swe-agent vs Muse Code
- MiniMax Code vs Muse Code
- Mistral Vibe CLI vs Muse Code
- Muse Code vs OpenAI Agents API
- Muse Code vs OpenAI Codex
- Muse Code vs OpenCode
- Muse Code vs OpenHands
- Muse Code vs OpenMausBot
- Muse Code vs Orca
- Muse Code vs Paseo
- Muse Code vs Prime Agent
- Muse Code vs Qoder CLI
- Muse Code vs Qwen Code
- Muse Code vs Mirror CLI
- Muse Code vs Rovo Dev CLI
- Muse Code vs Sculptor
- Muse Code vs T3 Code
- Muse Code vs Traycer
- Muse Code vs Unstoppable
- Muse Code vs Verdent
- Muse Code vs Vibe-Trading
- Muse Code vs Warp (Warp Agent CLI and the Oz Agent API)
- Agent Relay vs Amp
- Agent Relay vs Antigravity CLI
- Agent Relay vs Auggie CLI
- Agent Relay vs AXLR
- Agent Relay vs boxes.dev
- Agent Relay vs Claude Code
- Agent Relay vs Clawboo
- Agent Relay vs CLI Manager
- Agent Relay vs Cline
- Agent Relay vs Conductor
- Agent Relay vs Crush
- Agent Relay vs DeepSeek Harness (dsh)
- Agent Relay vs dsh-superagent (DeepSeek)
- Agent Relay vs Devin
- Agent Relay vs Droid CLI
- Agent Relay vs Emdash
- Agent Relay vs Friday
- Agent Relay vs Gemini CLI
- Agent Relay vs GitHub Copilot CLI
- Agent Relay vs goose
- Agent Relay vs Harness
- Agent Relay vs HarnessRouter
- Agent Relay vs herdr
- Agent Relay vs Jules
- Agent Relay vs Junie CLI
- Agent Relay vs Kilo Code CLI
- Agent Relay vs Kimi Code CLI
- Agent Relay vs Kiro CLI
- Agent Relay vs Letta
- Agent Relay vs MiniMax Code
- Agent Relay vs Mistral Vibe CLI
- Agent Relay vs OpenCode
- Agent Relay vs OpenHands
- Agent Relay vs OpenMausBot
- Agent Relay vs Orca
- Agent Relay vs Paperclip
- Agent Relay vs Parallax
- Agent Relay vs Paseo
- Agent Relay vs Prime Agent
- Agent Relay vs Qoder CLI
- Agent Relay vs Qwen Code
- Agent Relay vs Mirror CLI
- Agent Relay vs Rovo Dev CLI
- Agent Relay vs Sculptor
- Agent Relay vs T3 Code
- Agent Relay vs Traycer
- Agent Relay vs Unstoppable
- Agent Relay vs Verdent
- Agent Relay vs Vibe-Trading
- Agent Relay vs Warp (Warp Agent CLI and the Oz Agent API)
- Clawboo vs Muse Code
- CLI Manager vs Muse Code
- Friday vs Muse Code
- Harness vs Muse Code
- herdr vs Muse Code
- Muse Code vs Paperclip
- Muse Code vs Parallax
Machine-readable
- This page as Markdown
/compare/agent-relay-vs-muse-code.md· slim.min.md· JSON.json(or sendAccept: text/markdown) - Each listing in full
/api/v1/tools/agent-relay.json·/api/v1/tools/muse-code.json - From a terminal
anchor compare agent-relay muse-code(the CLI) - Over MCP
compare_tools {"a": "agent-relay", "b": "muse-code"}at/mcp, no key