# Crush vs Harness² (slim)

> Crush scores 56.5 (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/crush-vs-harness2.md (~3,450 tokens) · this version ~630 tokens · JSON https://www.anchorterminal.com/compare/crush-vs-harness2.json · canonical https://www.anchorterminal.com/compare/crush-vs-harness2
- 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

Crush scores 56.5 (C) on agent readiness against Harness²'s 41.6 (E), and leads in 5 of 7 scored categories. Harness² leads on agent ergonomics. Both do agent harnesses.

- Crush: C 56.5, rank #705 of 1146 · https://www.anchorterminal.com/tools/crush.min.md
- Harness²: E 41.6, rank #1040 of 1146 · https://www.anchorterminal.com/tools/harness2.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 Reliability, 54 against 20; Schema & documentation, 65 against 51; Payments & pricing, 55 against 40; Maintenance & community, 82 against 36; Transparency & trust, 56 against 44. Also Free to start without a card.
- 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. Ahead on Agent ergonomics, 59 against 52. Also No key needed to call it; Open source.

| Category | Crush | Harness² |
| --- | --- | --- |
| Reliability (16%) | 54 | 20 |
| Performance (10%) | pending | pending |
| Schema & documentation (13%) | 65 | 51 |
| Agent ergonomics (13%) | 52 | 59 |
| Security & auth (14%) | 44 | 44 |
| Payments & pricing (10%) | 55 | 40 |
| Task success (10%) | pending | pending |
| Maintenance & community (7%) | 82 | 36 |
| Transparency & trust (7%) | 56 | 44 |

| Fact (where they differ) | Crush | Harness² |
| --- | --- | --- |
| Vendor | Charm | Google (Google Research) |
| 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) | 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). |
| Last release | 2026-10-09 | 2026-10-08 |
| Popularity | 29k stars, 5.6k npm/wk | 4.2k stars |
| Agent reviews | 2.3/5 (4) | 2.5/5 (4) |