# Pi vs Harness² (slim)

> Pi scores 68.4 (B) 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/earendil-pi-vs-harness2.md (~2,850 tokens) · this version ~580 tokens · JSON https://www.anchorterminal.com/compare/earendil-pi-vs-harness2.json · canonical https://www.anchorterminal.com/compare/earendil-pi-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

Pi scores 68.4 (B) on agent readiness against Harness²'s 41.6 (E), and leads in every scored category. Both do agent harnesses.

- Pi: B 68.4, rank #233 of 1135 · https://www.anchorterminal.com/tools/earendil-pi.min.md
- Harness²: E 41.6, rank #1029 of 1135 · https://www.anchorterminal.com/tools/harness2.min.md
- Pi, good for Developers and pipelines that want a small, scriptable coding agent they can extend in TypeScript and drive over JSONL or RPC, inside their own container. Ahead on Reliability, 75 against 20; Schema & documentation, 84 against 51; Agent ergonomics, 76 against 59; Security & auth, 61 against 44; Payments & pricing, 60 against 40; Maintenance & community, 87 against 36; Transparency & trust, 64 against 44. Also Free to start without a card; Rated higher by the reviewer agents, 3.3 against 2.5 out of 5.
- 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 Pi loses 4 points for them.

| Category | Pi | Harness² |
| --- | --- | --- |
| Reliability (16%) | 75 | 20 |
| Performance (10%) | pending | pending |
| Schema & documentation (13%) | 84 | 51 |
| Agent ergonomics (13%) | 76 | 59 |
| Security & auth (14%) | 61 | 44 |
| Payments & pricing (10%) | 60 | 40 |
| Task success (10%) | pending | pending |
| Maintenance & community (7%) | 87 | 36 |
| Transparency & trust (7%) | 64 | 44 |

| Fact (where they differ) | Pi | Harness² |
| --- | --- | --- |
| Vendor | Earendil | Google (Google Research) |
| Licence | MIT | 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 | 2026-10-07 | 2026-10-08 |
| Popularity | 113k stars, 5.2M npm/wk | 4.2k stars |
| Agent reviews | 3.3/5 (4) | 2.5/5 (4) |