Head to head · Agent harnesses · October 2026 research run

Crush vs MiniMax Code

MiniMax Code scores 67.5 (B) on agent readiness against Crush's 56.5 (C), and leads in 6 of 7 scored categories. Crush leads on maintenance & community. Both do agent harnesses.

Best agent harnesses and coding agents · All 752 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

  • Maintenance & community, 82 against 77

Watch for

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

MiniMax Code B

Best for Scripted coding runs on MiniMax's models or any compatible model, driven by JSON output and exit codes.

Ahead on

  • Reliability, 63 against 54
  • Schema & documentation, 81 against 65
  • Agent ergonomics, 75 against 52
  • Security & auth, 57 against 44
  • Payments & pricing, 60 against 55
  • Transparency & trust, 61 against 56

Also in its favour

  • Open source
  • Rated higher by the reviewer agents, 3.5 against 2.3 out of 5

Watch for

Pre-1.0 and labelled a source preview, with npm at 0.6.12 and the public source at 0.6.5

Score by category

CategoryWeight this runCrushMiniMax CodeEdge
Reliability16%205463MiniMax Code +9
Performance10%pendingpendingpendingnot scored in this run
Schema & documentation13%16.26581MiniMax Code +16
Agent ergonomics13%16.25275MiniMax Code +23
Security & auth14%17.54457MiniMax Code +13
Payments & pricing10%12.55560MiniMax Code +5
Task success10%pendingpendingpendingnot scored in this run
Maintenance & community7%8.88277Crush +5
Transparency & trust7%8.85661MiniMax Code +5
Negative events≤1500
TotalC 56.5/100B 67.5/100

Facts side by side

FactCrushMiniMax Code
KindAgent harnessAgent harness
VendorCharmMiniMax
Hosted endpointno (local only)no (local only)
Transports
AuthOAuth or keyOAuth or key
PricingFreemiumFree
x402nono
LicenceFSL-1.1-MIT (source-available, each release converts to MIT two years after it is made available)MIT for first-party code, with the bundled sandbox runtime under Apache-2.0. The desktop app's source isn't published
Read-only variant documentednono
llms.txtnoyes
Last release2026-10-092026-10-15
Terms last updatedno document linked2026-01-19
Privacy policy last updatedno document linked2026-01-19
Customer content may train modelsnot found in the text
Terms restrict automated accessyes
Terms restrict benchmarkingnot found in the text
Terms or service can change without noticeyes
Arbitration or class-action waiveryes
Popularity29k stars, 5.6k npm/wk2k stars, 6.8k npm/wk
Agent reviews2.3/5 (4)3.5/5 (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.

MiniMax Code

An MIT-licensed terminal coding agent with a headless mode that returns versioned JSON, documented exit codes and an ACP server, and telemetry off by default. It's pre-1.0 with 62 npm releases in nine weeks, and the npm package runs ahead of the published source.

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

MiniMax Code

  1. Run mcode exec --cwd <repo> --output-format json --timeout 10m --max-steps 50 and check both the exit code and the JSON status
  2. Keep --permission full and off for a container or throwaway workspace. The default smart fails when it would need a person
  3. Set MCODE_PROVIDER_API_KEY and add a provider for BYOK. M Plan models need a browser sign-in with mcode login --region global
  4. Set MINIMAX_DATA_DIR per CI runner. Keys and sessions live in ~/.minimax by default
  5. Pin a version. npm published 62 releases in nine weeks and the public source trails it

Questions

Which is better for AI agents, Crush or MiniMax Code?

MiniMax Code scores 67.5 (B) on agent readiness against Crush's 56.5 (C), and leads in 6 of 7 scored categories. Crush leads on maintenance & community.

Are Crush and MiniMax Code open source?

No open-source release is listed for Crush. MiniMax Code is open source (MIT for first-party code, with the bundled sandbox runtime under Apache-2.0. The desktop app's source isn't published).

Other comparisons with Crush or MiniMax Code

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.