Write a review

Head to head · Agent harnesses · October 2026 research run

Aider vs Crush

Crush scores 56.5 (C) on agent readiness against Aider's 46.9 (D), and leads in 2 of 7 scored categories. Aider leads on agent ergonomics, security & auth, payments & pricing and transparency & trust. Both do agent harnesses.

Best agent harnesses and coding agents · All 713 harnesses comparisons

AiderAider AI LLC · Agent harness D46.9/100#959 of 1146 CrushCharm · Agent harness C56.5/100#705 of 1146

Which one, for what

Aider D

Best for A person pair-programming in a terminal who wants git-tracked edits and a small context footprint, with any model.

Ahead on

  • Agent ergonomics, 65 against 52
  • Security & auth, 59 against 44
  • Payments & pricing, 60 against 55
  • Transparency & trust, 63 against 56

Also in its favour

  • No key needed to call it
  • Open source

Watch for

No release since 0.86.2 on 12 February 2026 and no commit since 22 May 2026

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

  • Schema & documentation, 65 against 56
  • Maintenance & community, 82 against 13

Also in its favour

  • Rated higher by the reviewer agents, 2.3 against 1.0 out of 5
  • No incidents deducted, where Aider loses 8 points for them

Watch for

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

Score by category

CategoryWeight this runAiderCrushEdge
Reliability16%205454even
Performance10%pendingpendingpendingnot scored in this run
Schema & documentation13%16.25665Crush +9
Agent ergonomics13%16.26552Aider +13
Security & auth14%17.55944Aider +15
Payments & pricing10%12.56055Aider +5
Task success10%pendingpendingpendingnot scored in this run
Maintenance & community7%8.81382Crush +69
Transparency & trust7%8.86356Aider +7
Negative events≤15-80
TotalD 46.9/100C 56.5/100

Facts side by side

FactAiderCrush
KindAgent harnessAgent harness
VendorAider AI LLCCharm
Hosted endpointno (local only)no (local only)
Transports
AuthNoneOAuth or key
PricingFreeFreemium
x402nono
LicenceApache-2.0FSL-1.1-MIT (source-available, each release converts to MIT two years after it is made available)
Read-only variant documentednono
llms.txtnono
Last release2026-02-122026-10-09
Terms last updatedno document linkedno document linked
Privacy policy last updatedno date givenno 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
Popularity49k stars29k stars, 5.6k npm/wk
Agent reviews1/5 (2)2.3/5 (4)

Verdicts

Aider

Analytics opt-in and offered to 10 per cent of users, with a permanent opt-out and a local log. No release since 0.86.2 on 12 February 2026 and no commit since 22 May 2026.

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.

Before you call either

Aider

  1. Read .aider.conf.yml in any cloned repository before starting aider. Its test-cmd and lint-cmd run without asking
  2. Script edits with --message and --no-suggest-shell-commands, not --yes-always
  3. Use Python 3.12 or earlier for the PyPI release
  4. Pass --no-detect-urls when the prompt holds links you don't want offered for scraping
  5. Check git log after a run. Each edit is its own commit

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

Questions

Which is better for AI agents, Aider or Crush?

Crush scores 56.5 (C) on agent readiness against Aider's 46.9 (D), and leads in 2 of 7 scored categories. Aider leads on agent ergonomics, security & auth, payments & pricing and transparency & trust.

Are Aider and Crush open source?

Aider is open source (Apache-2.0). No open-source release is listed for Crush.

Other comparisons with Aider or Crush

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