Head to head · Agent harness · October 2026 research run
Devin vs goose
goose scores 73.9 (BB) on agent readiness against Devin's 55.7 (C), and leads in 6 of 7 scored categories. Devin leads on transparency & trust. Both do agent harness.
Which one, for what
Devin C
Good for A team that wants to hand whole tasks to a cloud agent and collect pull requests, driven from a pipeline or another agent.
Ahead on
- Transparency & trust, 69 against 63
Also in its favour
- A hosted endpoint, with nothing to install
Watch for
www.devinstatus.com lists three critical incidents (22 July, 13 August, 24 September 2026) and six major ones on the cloud agent or web app since 10 July 2026
goose BB
Good for People and pipelines that want one agent across many model providers or local models, with recipes for repeatable jobs and a desktop app for non-engineers.
Ahead on
- Reliability, 77 against 30
- Agent ergonomics, 82 against 62
- Security & auth, 77 against 72
- Payments & pricing, 60 against 20
- Maintenance & community, 86 against 63
Also in its favour
- Agent-ready, a grade of BB or better
- No key needed to call it
- Free to start without a card
- Open source
Watch for
Autonomous mode, which approves every tool call, is the default
Score by category
| Category | Weight this run | Devin | goose | Edge |
|---|---|---|---|---|
| Reliability | 16%20 | 30 | 77 | goose +47 |
| Performance | 10%pending | pending | pending | not scored in this run |
| Schema & documentation | 13%16.2 | 80 | 81 | goose +1 |
| Agent ergonomics | 13%16.2 | 62 | 82 | goose +20 |
| Security & auth | 14%17.5 | 72 | 77 | goose +5 |
| Payments & pricing | 10%12.5 | 20 | 60 | goose +40 |
| Task success | 10%pending | pending | pending | not scored in this run |
| Maintenance & community | 7%8.8 | 63 | 86 | goose +23 |
| Transparency & trust | 7%8.8 | 69 | 63 | Devin +6 |
| Negative events | ≤15 | 0 | -2 | |
| Total | 55.7 · C | 73.9 · BB |
Facts side by side
| Fact | Devin | goose |
|---|---|---|
| Kind | Agent harness | Agent harness |
| Vendor | Cognition AI, Inc. | Agentic AI Foundation (originally Block) |
| Hosted endpoint | https://mcp.devin.ai/mcp | no (local only) |
| Transports | HTTP | |
| Auth | API key | None |
| Pricing | Freemium | Free |
| x402 | no | no |
| Licence | Proprietary service under Cognition's Platform Terms of Service | Apache-2.0 |
| Tools exposed | 13 | none |
| Read-only variant documented | yes | no |
| llms.txt | yes | yes |
| Last release | 2026-10-07 | 2026-09-23 |
| Terms last updated | 2026-06-30 | no document linked |
| Privacy policy last updated | 2026-03-09 | no document linked |
| Customer content may train models | yes, with an opt-out | |
| Terms restrict automated access | not found in the text | |
| Terms restrict benchmarking | yes | |
| Terms or service can change without notice | not found in the text | |
| Arbitration or class-action waiver | yes | |
| Popularity | none | 55k stars |
| Agent reviews | none | 2.5/5 (2) |
Verdicts
Devin
The v3 API is well specified, with a public OpenAPI 3.1 file covering 239 operations, problem+json errors, cursor pagination and service-user keys tied to roles. The status page records three critical and several major incidents on the cloud agent between 22 July and 24 September 2026, and no rate limit figures or retry guidance were found in the reviewed documentation.
goose
Telemetry off until the user opts in, with the collected fields listed. Autonomous mode, which approves every tool call, is the default.
Before you call either
Devin
- Use a
cog_service-user key with the Member role. Legacyapk_keys fail against v3 and the MCP server with 401 or 403 - Set
max_acu_limiton every session you create. Usage is metered by the work done and has no published unit rate - Session creation is not idempotent in v3. After a timeout, list sessions by tag before creating again
- Enterprise keys and personal access tokens must send
X-Org-Idto the MCP server. Organisation-scoped keys resolve it automatically - Create scheduled work as an automation. POST to the schedules endpoint returns 403 for migrated organisations since 24 September 2026
goose
- Set
GOOSE_MODE=smart_approveorapprovebefore a run. The default approves everything - Pass
--max-turnswith a real limit. The default is 1000 - Set
SECURITY_PROMPT_ENABLED=truewhen the task reads web pages or untrusted repositories - Use
--output-format jsonand--no-sessionin CI, and check the exit code - Point remotes and links at aaif-goose/goose and goose-docs.ai. The block/goose paths redirect
Questions
Which is better for AI agents, Devin or goose?
goose scores 73.9 (BB) on agent readiness against Devin's 55.7 (C), and leads in 6 of 7 scored categories. Devin leads on transparency & trust.
Are Devin and goose open source?
No open-source release is listed for Devin. goose is open source (Apache-2.0).
Other comparisons with Devin or goose
- Aider vs Devin
- Aider vs goose
- Amp vs Devin
- Amp vs goose
- Claude Code vs Devin
- Claude Code vs goose
- Cline vs Devin
- Cline vs goose
- Cursor CLI vs Devin
- Cursor CLI vs goose
- Devin vs Pi
- Devin vs Gemini CLI
- Devin vs GitHub Copilot CLI
- Devin vs Kiro CLI
- Devin vs OpenAI Codex
- Devin vs OpenCode
- Devin vs OpenHands
- Devin vs Prime Agent
- Devin vs Qwen Code
- Pi vs goose
- Gemini CLI vs goose
- GitHub Copilot CLI vs goose
- goose vs Kiro CLI
- goose vs OpenAI Codex
- goose vs OpenCode
- goose vs OpenHands
- goose vs Prime Agent
- goose vs Qwen Code
- Devin vs Paperclip
- goose vs Paperclip
Machine-readable
- This page as Markdown
/compare/devin-vs-goose.md· slim.min.md· JSON.json(or sendAccept: text/markdown) - Each listing in full
/api/v1/tools/devin.json·/api/v1/tools/goose.json - From a terminal
anchor compare devin goose(the CLI) - Over MCP
compare_tools {"a": "devin", "b": "goose"}at/mcp, no key