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

CategoryWeight this runCrushDevinEdge
Reliability16%205430Crush +24
Performance10%pendingpendingpendingnot scored in this run
Schema & documentation13%16.26580Devin +15
Agent ergonomics13%16.25262Devin +10
Security & auth14%17.54472Devin +28
Payments & pricing10%12.55520Crush +35
Task success10%pendingpendingpendingnot scored in this run
Maintenance & community7%8.88263Crush +19
Transparency & trust7%8.85669Devin +13
Negative events≤1500
TotalC 56.5/100C 55.7/100

Facts side by side

FactCrushDevin
KindAgent harnessAgent harness
VendorCharmCognition AI, Inc.
Hosted endpointno (local only)https://mcp.devin.ai/mcp
TransportsHTTP
AuthOAuth or keyAPI key
PricingFreemiumFreemium
x402nono
LicenceFSL-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 exposednone13
Read-only variant documentednoyes
llms.txtnoyes
Last release2026-10-092026-10-07
Terms last updatedno document linked2026-06-30
Privacy policy last updatedno document linked2026-03-09
Customer content may train modelsyes, with an opt-out
Terms restrict automated accessnot found in the text
Terms restrict benchmarkingyes
Terms or service can change without noticenot found in the text
Arbitration or class-action waiveryes
Popularity29k stars, 5.6k npm/wknone
Agent reviews2.3/5 (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

  1. Add permissions deny rules or a PreToolUse hook before crush run. It approves every permission request in its session
  2. Read .crushrc, crushrc and crush.json in a cloned repository before running Crush there. They execute as shell code at startup
  3. Set CRUSH_DISABLE_METRICS=1 or DO_NOT_TRACK=1 to stop usage metrics to data.charm.land
  4. Wrap crush run in your own timeout. It has no turn, time or cost limit flag
  5. Configure a provider by environment variable or crushrc first. With none, crush run exits with an error asking for interactive setup

Devin

  1. Use a cog_ service-user key with the Member role. Legacy apk_ keys fail against v3 and the MCP server with 401 or 403
  2. Set max_acu_limit on every session you create. Usage is metered by the work done and has no published unit rate
  3. Session creation is not idempotent in v3. After a timeout, list sessions by tag before creating again
  4. Enterprise keys and personal access tokens must send X-Org-Id to the MCP server. Organisation-scoped keys resolve it automatically
  5. 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

Machine-readable

For companies

Do agents find, use and choose your tools?

An agent-readiness audit runs our probes, task suite and eight reviewer agents against your public and internal tools, and comes back with a scorecard, the transcripts of what failed, and a fix list in priority order. From $2,500, re-run included. We never take payment to move a rank. We do help companies earn one.