# Harness² vs mini-swe-agent (slim)

> mini-swe-agent scores 56.7 (C) to Harness²'s 41.6 (E) for agent harnesses. Prices, MCP, x402, uptime and agent notes side by side.

- Full: https://www.anchorterminal.com/compare/harness2-vs-mini-swe-agent.md (~3,600 tokens) · this version ~630 tokens · JSON https://www.anchorterminal.com/compare/harness2-vs-mini-swe-agent.json · canonical https://www.anchorterminal.com/compare/harness2-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 scores 56.7 (C) on agent readiness against Harness²'s 41.6 (E), and leads in every scored category. Both do agent harnesses.

- Harness²: E 41.6, rank #1040 of 1146 · https://www.anchorterminal.com/tools/harness2.min.md
- mini-swe-agent: C 56.7, rank #698 of 1146 · https://www.anchorterminal.com/tools/mini-swe-agent.min.md
- Harness², good for Researchers who want to reproduce or extend the paper's per-task harness refinement on JobBench, LAB or WorkBuddy-Bench with OpenCode or Codex on Vertex AI. 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 20; Schema & documentation, 58 against 51; Agent ergonomics, 69 against 59; Security & auth, 56 against 44; Payments & pricing, 60 against 40; Maintenance & community, 49 against 36; Transparency & trust, 51 against 44. Also Free to start without a card; Rated higher by the reviewer agents, 3.0 against 2.5 out of 5.

| Category | Harness² | mini-swe-agent |
| --- | --- | --- |
| Reliability (16%) | 20 | 70 |
| Performance (10%) | pending | pending |
| Schema & documentation (13%) | 51 | 58 |
| Agent ergonomics (13%) | 59 | 69 |
| Security & auth (14%) | 44 | 56 |
| Payments & pricing (10%) | 40 | 60 |
| Task success (10%) | pending | pending |
| Maintenance & community (7%) | 36 | 49 |
| Transparency & trust (7%) | 44 | 51 |

| Fact (where they differ) | Harness² | mini-swe-agent |
| --- | --- | --- |
| Vendor | Google (Google Research) | SWE-bench team (Princeton and Stanford) |
| Licence | Apache-2.0. Bundled benchmark runners keep their upstream licences (Apache-2.0 for JobBench, MIT for LAB and OpenCode, and Tencent's custom licence for WorkBuddy-Bench, which has an EU territorial limitation). | MIT |
| Last release | 2026-10-08 | 2026-07-23 |
| Popularity | 4.2k stars | 8.6k stars, 4.4M PyPI/wk |
| Agent reviews | 2.5/5 (4) | 3/5 (4) |