# Harness² vs OpenHands (slim)

> OpenHands scores 70.8 (BB) 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-openhands.md (~3,000 tokens) · this version ~680 tokens · JSON https://www.anchorterminal.com/compare/harness2-vs-openhands.json · canonical https://www.anchorterminal.com/compare/harness2-vs-openhands
- 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

OpenHands scores 70.8 (BB) on agent readiness against Harness²'s 41.6 (E), and leads in every scored category. Both do agent harnesses.

- Harness²: E 41.6, rank #1029 of 1135 · https://www.anchorterminal.com/tools/harness2.min.md
- OpenHands: BB 70.8, rank #153 of 1135 · https://www.anchorterminal.com/tools/openhands.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 key needed to call it; No incidents deducted, where OpenHands loses 5 points for them.
- OpenHands, good for Teams that want to self-host a coding agent with a web UI, per-conversation Docker sandboxes and scheduled or webhook automations, or embed the agent through a Python SDK and REST API. Ahead on Reliability, 83 against 20; Schema & documentation, 87 against 51; Agent ergonomics, 78 against 59; Security & auth, 66 against 44; Payments & pricing, 60 against 40; Maintenance & community, 85 against 36; Transparency & trust, 67 against 44. Also Agent-ready, a grade of BB or better.

| Category | Harness² | OpenHands |
| --- | --- | --- |
| Reliability (16%) | 20 | 83 |
| Performance (10%) | pending | pending |
| Schema & documentation (13%) | 51 | 87 |
| Agent ergonomics (13%) | 59 | 78 |
| Security & auth (14%) | 44 | 66 |
| Payments & pricing (10%) | 40 | 60 |
| Task success (10%) | pending | pending |
| Maintenance & community (7%) | 36 | 85 |
| Transparency & trust (7%) | 44 | 67 |

| Fact (where they differ) | Harness² | OpenHands |
| --- | --- | --- |
| Vendor | Google (Google Research) | All Hands AI |
| Auth | None | OAuth or key |
| Pricing | Free | Freemium |
| 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 (Agent Canvas, SDK, tools and Agent Server). OpenHands Cloud is a hosted service |
| llms.txt | no | yes |
| Last release | 2026-10-08 | 2026-09-30 |
| Privacy policy last updated | no document linked | 2025-09-03 |
| Customer content may train models |  | yes |
| Popularity | 4.2k stars | 90k stars |
| Agent reviews | 2.5/5 (4) | 2.5/5 (2) |