# mini-swe-agent vs Mirror CLI (slim)

> mini-swe-agent scores 56.7 (C) to Mirror CLI's 54.2 (C) for agent harnesses. Prices, MCP, x402, uptime and agent notes side by side.

- Full: https://www.anchorterminal.com/compare/mini-swe-agent-vs-reflection-mirror.md (~3,650 tokens) · this version ~580 tokens · JSON https://www.anchorterminal.com/compare/mini-swe-agent-vs-reflection-mirror.json · canonical https://www.anchorterminal.com/compare/mini-swe-agent-vs-reflection-mirror
- 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 scores 56.7 (C) on agent readiness against Mirror CLI's 54.2 (C), and leads in 3 of 7 scored categories. Mirror CLI leads on schema & documentation and transparency & trust. Both do agent harnesses.

- mini-swe-agent: C 56.7, rank #698 of 1146 · https://www.anchorterminal.com/tools/mini-swe-agent.min.md
- Mirror CLI: C 54.2, rank #772 of 1146 · https://www.anchorterminal.com/tools/reflection-mirror.min.md
- 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 37; Agent ergonomics, 69 against 58. Also No key needed to call it.
- Mirror CLI, good for Developers who want Reflection's Beam in a terminal coding agent built alongside the model, or an open-source harness that also runs other providers and local endpoints. Ahead on Schema & documentation, 65 against 58; Transparency & trust, 58 against 51. Also No incidents deducted, where mini-swe-agent loses 4 points for them.

| Category | mini-swe-agent | Mirror CLI |
| --- | --- | --- |
| Reliability (16%) | 70 | 37 |
| Performance (10%) | pending | pending |
| Schema & documentation (13%) | 58 | 65 |
| Agent ergonomics (13%) | 69 | 58 |
| Security & auth (14%) | 56 | 58 |
| Payments & pricing (10%) | 60 | 60 |
| Task success (10%) | pending | pending |
| Maintenance & community (7%) | 49 | 47 |
| Transparency & trust (7%) | 51 | 58 |

| Fact (where they differ) | mini-swe-agent | Mirror CLI |
| --- | --- | --- |
| Vendor | SWE-bench team (Princeton and Stanford) | Reflection |
| Auth | None | API key |
| Licence | MIT | Apache-2.0 |
| llms.txt | no | yes |
| Last release | 2026-07-23 | 2026-10-16 |
| Terms last updated | no document linked |  |
| Privacy policy last updated | no document linked |  |
| Popularity | 8.6k stars, 4.4M PyPI/wk | none |