Write a review

Head to head · Multi-agent orchestration · October 2026 research run

Crush vs Harness

Harness scores 60.3 (C) on agent readiness against Crush's 56.5 (C), and leads in 4 of 7 scored categories. Crush leads on reliability, payments & pricing and maintenance & community. Both do multi-agent orchestration.

Best agent harnesses and coding agents · All 713 harnesses comparisons

CrushCharm · Agent harness C56.5/100#705 of 1146 HarnessAutonomous, Inc. · Agent harness C60.3/100#573 of 1146

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 35
  • Payments & pricing, 55 against 40
  • Maintenance & community, 82 against 60

Watch for

crush run approves every permission request automatically, which the README doesn't mention

Harness C

Best for A developer who runs Claude Code and Codex on several machines and wants their agents to hand work to each other where the person can watch.

Ahead on

  • Schema & documentation, 85 against 65
  • Agent ergonomics, 82 against 52
  • Security & auth, 57 against 44
  • Transparency & trust, 68 against 56

Also in its favour

  • Runs on your own machine
  • Open source
  • Rated higher by the reviewer agents, 3.0 against 2.3 out of 5

Watch for

Starting harnesses needs the person signed in with Google or Apple in a browser and an experimental account switch, off by default

Score by category

CategoryWeight this runCrushHarnessEdge
Reliability16%205435Crush +19
Performance10%pendingpendingpendingnot scored in this run
Schema & documentation13%16.26585Harness +20
Agent ergonomics13%16.25282Harness +30
Security & auth14%17.54457Harness +13
Payments & pricing10%12.55540Crush +15
Task success10%pendingpendingpendingnot scored in this run
Maintenance & community7%8.88260Crush +22
Transparency & trust7%8.85668Harness +12
Negative events≤1500
TotalC 56.5/100C 60.3/100

Facts side by side

FactCrushHarness
KindAgent harnessAgent harness
VendorCharmAutonomous, Inc.
Hosted endpointno (local only)no (local only)
Transportsstdio
AuthOAuth or keyOAuth
PricingFreemiumFree
x402nono
LicenceFSL-1.1-MIT (source-available, each release converts to MIT two years after it is made available)MIT
Tools exposednone7
Read-only variant documentednono
llms.txtnoyes
Last release2026-10-092026-10-17
Terms last updatedno document linked
Privacy policy last updatedno document linked
Customer content may train models
Terms restrict automated access
Terms restrict benchmarking
Terms or service can change without notice
Arbitration or class-action waiver
Popularity29k stars, 5.6k npm/wk1.3k stars
Agent reviews2.3/5 (4)3/5 (4)

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.

Harness

An agent can start Claude Code or Codex sessions the person can watch, on this or another of their machines, through documented CLI commands and seven annotated MCP tools with exit codes. Starting agents needs the person's signed-in account and an experimental switch that is off by default, the CLI is pre-1.0, and usage counts are shared by default.

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

Harness

  1. Run harness whoami first. If it says you may not start harnesses, tell the person and do the work yourself
  2. Ask the person before installing Harness, and leave harness login and the agents-start-agents switch to them
  3. Treat exit 5 as final and do not retry. Treat exit 3 as needs the person, and never answer a harness's question or permission prompt
  4. Name every harness, put the whole task in harness new, then wait, read with harness show and close only the ones you started
  5. Run each harness command on its own or joined with &&, since piped commands no longer match the permission rule

Questions

Which is better for AI agents, Crush or Harness?

Harness scores 60.3 (C) on agent readiness against Crush's 56.5 (C), and leads in 4 of 7 scored categories. Crush leads on reliability, payments & pricing and maintenance & community.

Are Crush and Harness open source?

No open-source release is listed for Crush. Harness is open source (MIT).

Other comparisons with Crush or Harness

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.

Get an auditSee a sample report