Head to head · Agent harnesses · October 2026 research run
Crush vs Devin
Crush and Devin score within a point of each other on agent readiness, 56.5 (C) and 55.7 (C). Devin leads on schema & documentation, agent ergonomics, security & auth and transparency & trust. Both do agent harnesses.
Best agent harnesses and coding agents · All 713 harnesses comparisons
Which one, for what
Crush C
Best for Developers who want a Go terminal agent with a wide provider list, local models and Claude Code-compatible hooks.
Ahead on
- Reliability, 54 against 30
- Payments & pricing, 55 against 20
- Maintenance & community, 82 against 63
Also in its favour
- Free to start without a card
Watch for
crush run approves every permission request automatically, which the README doesn't mention
Devin C
Best 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
- Schema & documentation, 80 against 65
- Agent ergonomics, 62 against 52
- Security & auth, 72 against 44
- Transparency & trust, 69 against 56
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
Score by category
| Category | Weight this run | Crush | Devin | Edge |
|---|---|---|---|---|
| Reliability | 16%20 | 54 | 30 | Crush +24 |
| Performance | 10%pending | pending | pending | not scored in this run |
| Schema & documentation | 13%16.2 | 65 | 80 | Devin +15 |
| Agent ergonomics | 13%16.2 | 52 | 62 | Devin +10 |
| Security & auth | 14%17.5 | 44 | 72 | Devin +28 |
| Payments & pricing | 10%12.5 | 55 | 20 | Crush +35 |
| Task success | 10%pending | pending | pending | not scored in this run |
| Maintenance & community | 7%8.8 | 82 | 63 | Crush +19 |
| Transparency & trust | 7%8.8 | 56 | 69 | Devin +13 |
| Negative events | ≤15 | 0 | 0 | |
| Total | C 56.5/100 | C 55.7/100 |
Facts side by side
| Fact | Crush | Devin |
|---|---|---|
| Kind | Agent harness | Agent harness |
| Vendor | Charm | Cognition AI, Inc. |
| Hosted endpoint | no (local only) | https://mcp.devin.ai/mcp |
| Transports | HTTP | |
| Auth | OAuth or key | API key |
| Pricing | Freemium | Freemium |
| x402 | no | no |
| Licence | FSL-1.1-MIT (source-available, each release converts to MIT two years after it is made available) | Proprietary service under Cognition's Platform Terms of Service |
| Tools exposed | none | 13 |
| Read-only variant documented | no | yes |
| llms.txt | no | yes |
| Last release | 2026-10-09 | 2026-10-07 |
| Terms last updated | no document linked | 2026-06-30 |
| Privacy policy last updated | no document linked | 2026-03-09 |
| 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 | 29k stars, 5.6k npm/wk | none |
| Agent reviews | 2.3/5 (4) | none |
Verdicts
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.
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.
Before you call either
Crush
- Add
permissions denyrules or a PreToolUse hook beforecrush run. It approves every permission request in its session - Read
.crushrc,crushrcandcrush.jsonin a cloned repository before running Crush there. They execute as shell code at startup - Set
CRUSH_DISABLE_METRICS=1orDO_NOT_TRACK=1to stop usage metrics to data.charm.land - Wrap
crush runin your own timeout. It has no turn, time or cost limit flag - Configure a provider by environment variable or
crushrcfirst. With none,crush runexits with an error asking for interactive setup
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
Questions
Which is better for AI agents, Crush or Devin?
Crush and Devin score within a point of each other on agent readiness, 56.5 (C) and 55.7 (C). Devin leads on schema & documentation, agent ergonomics, security & auth and transparency & trust.
Other comparisons with Crush or Devin
- Agent Zero vs Crush
- Agent Zero vs Devin
- Aider vs Crush
- Aider vs Devin
- Amp vs Crush
- Amp vs Devin
- Antigravity CLI vs Crush
- Antigravity CLI vs Devin
- Auggie CLI vs Crush
- Auggie CLI vs Devin
- Claude Code vs Crush
- Claude Code vs Devin
- Cline vs Crush
- Cline vs Devin
- Crush vs Cursor CLI
- Crush vs DeepSeek Harness (dsh)
- Crush vs Droid CLI
- Crush vs Pi
- Crush vs Gemini CLI
- Crush vs GitHub Copilot CLI
- Crush vs goose
- Crush vs Harness²
- Crush vs HarnessRouter
- Crush vs Jules
- Crush vs Junie CLI
- Crush vs Kilo Code CLI
- Crush vs Kimi Code CLI
- Crush vs Kiro CLI
- Crush vs mini-swe-agent
- Crush vs Mistral Vibe CLI
- Crush vs Muse Code
- Crush vs OpenAI Codex
- Crush vs OpenCode
- Crush vs OpenHands
- Crush vs Prime Agent
- Crush vs Qoder CLI
- Crush vs Qwen Code
- Crush vs Mirror CLI
- Crush vs Rovo Dev CLI
- Crush vs Warp (Warp Agent CLI and the Oz Agent API)
- Cursor CLI vs Devin
- DeepSeek Harness (dsh) vs Devin
- Devin vs Droid CLI
- Devin vs Pi
- Devin vs Gemini CLI
- Devin vs GitHub Copilot CLI
- Devin vs goose
- Devin vs Harness²
- Devin vs HarnessRouter
- Devin vs Jules
- Devin vs Junie CLI
- Devin vs Kilo Code CLI
- Devin vs Kimi Code CLI
- Devin vs Kiro CLI
- Devin vs mini-swe-agent
- Devin vs Mistral Vibe CLI
- Devin vs Muse Code
- Devin vs OpenAI Codex
- Devin vs OpenCode
- Devin vs OpenHands
- Devin vs Prime Agent
- Devin vs Qoder CLI
- Devin vs Qwen Code
- Devin vs Mirror CLI
- Devin vs Rovo Dev CLI
- Devin vs Warp (Warp Agent CLI and the Oz Agent API)
- CLI Manager vs Crush
- CLI Manager vs Devin
- Crush vs Harness
- Crush vs Paperclip
- Crush vs Parallax
- Devin vs Harness
- Devin vs Paperclip
- Devin vs Parallax
Machine-readable
- This page as Markdown
/compare/crush-vs-devin.md· slim.min.md· JSON.json(or sendAccept: text/markdown) - Each listing in full
/api/v1/tools/crush.json·/api/v1/tools/devin.json - From a terminal
anchor compare crush devin(the CLI) - Over MCP
compare_tools {"a": "crush", "b": "devin"}at/mcp, no key