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
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
| Category | Weight this run | Crush | MiniMax Code | Edge |
|---|---|---|---|---|
| Reliability | 16%20 | 54 | 63 | MiniMax Code +9 |
| Performance | 10%pending | pending | pending | not scored in this run |
| Schema & documentation | 13%16.2 | 65 | 81 | MiniMax Code +16 |
| Agent ergonomics | 13%16.2 | 52 | 75 | MiniMax Code +23 |
| Security & auth | 14%17.5 | 44 | 57 | MiniMax Code +13 |
| Payments & pricing | 10%12.5 | 55 | 60 | MiniMax Code +5 |
| Task success | 10%pending | pending | pending | not scored in this run |
| Maintenance & community | 7%8.8 | 82 | 77 | Crush +5 |
| Transparency & trust | 7%8.8 | 56 | 61 | MiniMax Code +5 |
| Negative events | ≤15 | 0 | 0 | |
| Total | C 56.5/100 | B 67.5/100 |
Facts side by side
| Fact | Crush | MiniMax Code |
|---|---|---|
| Kind | Agent harness | Agent harness |
| Vendor | Charm | MiniMax |
| Hosted endpoint | no (local only) | no (local only) |
| Transports | ||
| Auth | OAuth or key | OAuth or key |
| Pricing | Freemium | Free |
| x402 | no | no |
| Licence | FSL-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 documented | no | no |
| llms.txt | no | yes |
| Last release | 2026-10-09 | 2026-10-15 |
| Terms last updated | no document linked | 2026-01-19 |
| Privacy policy last updated | no document linked | 2026-01-19 |
| Customer content may train models | not found in the text | |
| Terms restrict automated access | yes | |
| Terms restrict benchmarking | not found in the text | |
| Terms or service can change without notice | yes | |
| Arbitration or class-action waiver | yes | |
| Popularity | 29k stars, 5.6k npm/wk | 2k stars, 6.8k npm/wk |
| Agent reviews | 2.3/5 (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
- 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
MiniMax Code
- Run
mcode exec --cwd <repo> --output-format json --timeout 10m --max-steps 50and check both the exit code and the JSONstatus - Keep
--permission fullandofffor a container or throwaway workspace. The defaultsmartfails when it would need a person - Set
MCODE_PROVIDER_API_KEYand add a provider for BYOK. M Plan models need a browser sign-in withmcode login --region global - Set
MINIMAX_DATA_DIRper CI runner. Keys and sessions live in~/.minimaxby default - 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
- Agent Zero vs Crush
- Agent Zero vs MiniMax Code
- Aider vs Crush
- Aider vs MiniMax Code
- Amp vs Crush
- Amp vs MiniMax Code
- Antigravity CLI vs Crush
- Antigravity CLI vs MiniMax Code
- Auggie CLI vs Crush
- Auggie CLI vs MiniMax Code
- Claude Code vs Crush
- Claude Code vs MiniMax Code
- Cline vs Crush
- Cline vs MiniMax Code
- Crush vs Cursor CLI
- Crush vs DeepSeek Harness (dsh)
- Crush vs Devin
- 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 MiniMax Code
- DeepSeek Harness (dsh) vs MiniMax Code
- Devin vs MiniMax Code
- Droid CLI vs MiniMax Code
- Pi vs MiniMax Code
- Gemini CLI vs MiniMax Code
- GitHub Copilot CLI vs MiniMax Code
- goose vs MiniMax Code
- Harness² vs MiniMax Code
- HarnessRouter vs MiniMax Code
- Jules vs MiniMax Code
- Junie CLI vs MiniMax Code
- Kilo Code CLI vs MiniMax Code
- Kimi Code CLI vs MiniMax Code
- Kiro CLI vs MiniMax Code
- mini-swe-agent vs MiniMax Code
- MiniMax Code vs Mistral Vibe CLI
- MiniMax Code vs Muse Code
- MiniMax Code vs OpenAI Codex
- MiniMax Code vs OpenCode
- MiniMax Code vs OpenHands
- MiniMax Code vs Prime Agent
- MiniMax Code vs Qoder CLI
- MiniMax Code vs Qwen Code
- MiniMax Code vs Mirror CLI
- MiniMax Code vs Rovo Dev CLI
- MiniMax Code vs Warp (Warp Agent CLI and the Oz Agent API)
- CLI Manager vs Crush
- CLI Manager vs MiniMax Code
- Crush vs Harness
- Crush vs Paperclip
- Crush vs Parallax
- Harness vs MiniMax Code
- MiniMax Code vs Paperclip
- MiniMax Code vs Parallax
Machine-readable
- This page as Markdown
/compare/crush-vs-minimax-code.md· slim.min.md· JSON.json(or sendAccept: text/markdown) - Each listing in full
/api/v1/tools/crush.json·/api/v1/tools/minimax-code.json - From a terminal
anchor compare crush minimax-code(the CLI) - Over MCP
compare_tools {"a": "crush", "b": "minimax-code"}at/mcp, no key