# Harness² vs OpenCode (slim)

> OpenCode scores 68.5 (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/harness2-vs-opencode.md (~2,950 tokens) · this version ~730 tokens · JSON https://www.anchorterminal.com/compare/harness2-vs-opencode.json · canonical https://www.anchorterminal.com/compare/harness2-vs-opencode
- 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

OpenCode scores 68.5 (B) 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
- OpenCode: B 68.5, rank #230 of 1135 · https://www.anchorterminal.com/tools/opencode.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 Rated higher by the reviewer agents, 2.5 against 2.0 out of 5; No incidents deducted, where OpenCode loses 4 points for them.
- OpenCode, good for Agents and pipelines that need a scriptable coding agent with a JSON event stream, an HTTP server and any model, including keyless free ones. Ahead on Reliability, 72 against 20; Schema & documentation, 88 against 51; Agent ergonomics, 79 against 59; Security & auth, 60 against 44; Payments & pricing, 60 against 40; Maintenance & community, 81 against 36; Transparency & trust, 67 against 44. Also Free to start without a card.

| Category | Harness² | OpenCode |
| --- | --- | --- |
| Reliability (16%) | 20 | 72 |
| Performance (10%) | pending | pending |
| Schema & documentation (13%) | 51 | 88 |
| Agent ergonomics (13%) | 59 | 79 |
| Security & auth (14%) | 44 | 60 |
| Payments & pricing (10%) | 40 | 60 |
| Task success (10%) | pending | pending |
| Maintenance & community (7%) | 36 | 81 |
| Transparency & trust (7%) | 44 | 67 |

| Fact (where they differ) | Harness² | OpenCode |
| --- | --- | --- |
| Vendor | Google (Google Research) | Anomaly |
| 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 |
| Last release | 2026-10-08 | 2026-10-16 |
| Terms last updated | no document linked | 2026-08-15 |
| Privacy policy last updated | no document linked | 2026-03-06 |
| Customer content may train models |  | not found in the text |
| Terms restrict automated access |  | yes |
| Terms restrict benchmarking |  | yes |
| Terms or service can change without notice |  | not found in the text |
| Arbitration or class-action waiver |  | yes |
| Popularity | 4.2k stars | 211k stars |
| Agent reviews | 2.5/5 (4) | 2/5 (2) |