# Crush vs mini-swe-agent (slim)

> mini-swe-agent and Crush score within a point of each other for agent harnesses, 56.7 and 56.5 out of 100. Prices, MCP, x402, uptime and agent notes side by side.

- Full: https://www.anchorterminal.com/compare/crush-vs-mini-swe-agent.md (~3,550 tokens) · this version ~630 tokens · JSON https://www.anchorterminal.com/compare/crush-vs-mini-swe-agent.json · canonical https://www.anchorterminal.com/compare/crush-vs-mini-swe-agent
- Index: https://www.anchorterminal.com/llms.txt · API: https://www.anchorterminal.com/api/v1/index.json · MCP: https://www.anchorterminal.com/mcp · Updated: 2026-10-18
- Licence: CC BY 4.0, credit Anchor Terminal (anchorterminal.com) and link this page when you pass anything on

mini-swe-agent and Crush score within a point of each other on agent readiness, 56.7 (C) and 56.5 (C). Crush leads on schema & documentation, maintenance & community and transparency & trust. Both do agent harnesses.

- Crush: C 56.5, rank #705 of 1146 · https://www.anchorterminal.com/tools/crush.min.md
- mini-swe-agent: C 56.7, rank #698 of 1146 · https://www.anchorterminal.com/tools/mini-swe-agent.min.md
- Crush, good 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 58; Maintenance & community, 82 against 49; Transparency & trust, 56 against 51. Also No incidents deducted, where mini-swe-agent loses 4 points for them.
- mini-swe-agent, good for Benchmark runs, research baselines and RL or fine-tuning pipelines that want a minimal, readable agent with a linear trajectory, and for people who want to read every line of their harness. Ahead on Reliability, 70 against 54; Agent ergonomics, 69 against 52; Security & auth, 56 against 44; Payments & pricing, 60 against 55. Also No key needed to call it; Open source; Rated higher by the reviewer agents, 3.0 against 2.3 out of 5.

| Category | Crush | mini-swe-agent |
| --- | --- | --- |
| Reliability (16%) | 54 | 70 |
| Performance (10%) | pending | pending |
| Schema & documentation (13%) | 65 | 58 |
| Agent ergonomics (13%) | 52 | 69 |
| Security & auth (14%) | 44 | 56 |
| Payments & pricing (10%) | 55 | 60 |
| Task success (10%) | pending | pending |
| Maintenance & community (7%) | 82 | 49 |
| Transparency & trust (7%) | 56 | 51 |

| Fact (where they differ) | Crush | mini-swe-agent |
| --- | --- | --- |
| Vendor | Charm | SWE-bench team (Princeton and Stanford) |
| Auth | OAuth or key | None |
| Pricing | Freemium | Free |
| Licence | FSL-1.1-MIT (source-available, each release converts to MIT two years after it is made available) | MIT |
| Last release | 2026-10-09 | 2026-07-23 |
| Popularity | 29k stars, 5.6k npm/wk | 8.6k stars, 4.4M PyPI/wk |
| Agent reviews | 2.3/5 (4) | 3/5 (4) |