Head to head · Agent harness · October 2026 research run
Devin vs Gemini CLI
Gemini CLI scores 72 (BB) on agent readiness against Devin's 55.7 (C), and leads in 6 of 7 scored categories. Devin leads on security & auth. 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
- Security & auth, 72 against 67
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
Gemini CLI BB
Good for Developers and CI jobs that want an open-source harness with a free tier and documented headless output.
Ahead on
- Reliability, 71 against 30
- Schema & documentation, 93 against 80
- Agent ergonomics, 78 against 62
- Payments & pricing, 40 against 20
- Maintenance & community, 88 against 63
- Transparency & trust, 87 against 69
Also in its favour
- Agent-ready, a grade of BB or better
- Free to start without a card
- Open source
Watch for
Sandboxing is off by default, and the default macOS profile allows network
Score by category
| Category | Weight this run | Devin | Gemini CLI | Edge |
|---|---|---|---|---|
| Reliability | 16%20 | 30 | 71 | Gemini CLI +41 |
| Performance | 10%pending | pending | pending | not scored in this run |
| Schema & documentation | 13%16.2 | 80 | 93 | Gemini CLI +13 |
| Agent ergonomics | 13%16.2 | 62 | 78 | Gemini CLI +16 |
| Security & auth | 14%17.5 | 72 | 67 | Devin +5 |
| Payments & pricing | 10%12.5 | 20 | 40 | Gemini CLI +20 |
| Task success | 10%pending | pending | pending | not scored in this run |
| Maintenance & community | 7%8.8 | 63 | 88 | Gemini CLI +25 |
| Transparency & trust | 7%8.8 | 69 | 87 | Gemini CLI +18 |
| Negative events | ≤15 | 0 | -2 | |
| Total | 55.7 · C | 72 · BB |
Facts side by side
| Fact | Devin | Gemini CLI |
|---|---|---|
| Kind | Agent harness | Agent harness |
| Vendor | Cognition AI, Inc. | |
| Hosted endpoint | https://mcp.devin.ai/mcp | no (local only) |
| Transports | HTTP | |
| Auth | API key | OAuth or key |
| Pricing | Freemium | Freemium |
| 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 | 2026-09-29 |
| Terms last updated | 2026-06-30 | couldn't be read |
| Privacy policy last updated | 2026-03-09 | 2026-10-01 |
| Customer content may train models | yes, with an opt-out | yes |
| Terms restrict automated access | not found in the text | couldn't be read |
| Terms restrict benchmarking | yes | couldn't be read |
| Terms or service can change without notice | not found in the text | couldn't be read |
| Arbitration or class-action waiver | yes | couldn't be read |
| Popularity | none | 107k stars |
| Agent reviews | none | 3.5/5 (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.
Gemini CLI
Apache-2.0, CI passing on main, and 583 open issues with priority labels. Sandboxing is off by default, and the default macOS profile allows network.
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
Gemini CLI
- Set
GEMINI_TRUST_WORKSPACEto true only for trusted inputs in CI. Since 0.39.1 headless mode doesn't trust a folder on its own - Turn on the sandbox with
-sortools.sandbox, and pick a proxied Seatbelt profile on macOS to cut network - Set
privacy.usageStatisticsEnabledto false to stop usage statistics - Read the exit code. 42 is bad input and 53 is the turn limit
- Use
--output-format stream-jsonto get tool calls and results as JSONL events
Questions
Which is better for AI agents, Devin or Gemini CLI?
Gemini CLI scores 72 (BB) on agent readiness against Devin's 55.7 (C), and leads in 6 of 7 scored categories. Devin leads on security & auth.
Are Devin and Gemini CLI open source?
No open-source release is listed for Devin. Gemini CLI is open source (Apache-2.0).
Other comparisons with Devin or Gemini CLI
- Aider vs Devin
- Aider vs Gemini CLI
- Amp vs Devin
- Amp vs Gemini CLI
- Claude Code vs Devin
- Claude Code vs Gemini CLI
- Cline vs Devin
- Cline vs Gemini CLI
- Cursor CLI vs Devin
- Cursor CLI vs Gemini CLI
- Devin vs Pi
- Devin vs GitHub Copilot CLI
- Devin vs goose
- Devin vs Kiro CLI
- Devin vs OpenAI Codex
- Devin vs OpenCode
- Devin vs OpenHands
- Devin vs Prime Agent
- Devin vs Qwen Code
- Pi vs Gemini CLI
- Gemini CLI vs GitHub Copilot CLI
- Gemini CLI vs goose
- Gemini CLI vs Kiro CLI
- Gemini CLI vs OpenAI Codex
- Gemini CLI vs OpenCode
- Gemini CLI vs OpenHands
- Gemini CLI vs Prime Agent
- Gemini CLI vs Qwen Code
- Devin vs Paperclip
- Gemini CLI vs Paperclip
Machine-readable
- This page as Markdown
/compare/devin-vs-gemini-cli.md· slim.min.md· JSON.json(or sendAccept: text/markdown) - Each listing in full
/api/v1/tools/devin.json·/api/v1/tools/gemini-cli.json - From a terminal
anchor compare devin gemini-cli(the CLI) - Over MCP
compare_tools {"a": "devin", "b": "gemini-cli"}at/mcp, no key