# Harness² vs HarnessRouter (slim)

> HarnessRouter scores 53.2 (D) 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-harnessrouter.md (~3,300 tokens) · this version ~780 tokens · JSON https://www.anchorterminal.com/compare/harness2-vs-harnessrouter.json · canonical https://www.anchorterminal.com/compare/harness2-vs-harnessrouter
- 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

HarnessRouter scores 53.2 (D) on agent readiness against Harness²'s 41.6 (E), and leads in 6 of 7 scored categories. Harness² leads on payments & pricing. Both do agent harnesses.

- Harness²: E 41.6, rank #1029 of 1135 · https://www.anchorterminal.com/tools/harness2.min.md
- HarnessRouter: D 53.2, rank #797 of 1135 · https://www.anchorterminal.com/tools/harnessrouter.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. Ahead on Payments & pricing, 40 against 25. Also No key needed to call it; No incidents deducted, where HarnessRouter loses 5 points for them.
- HarnessRouter, good for A product team that wants to run Codex, Claude Code, Hermes or 23 other harnesses server-side behind one task, session and file contract, and switch between them by changing an ID. Ahead on Reliability, 35 against 20; Schema & documentation, 83 against 51; Agent ergonomics, 73 against 59; Security & auth, 58 against 44; Maintenance & community, 72 against 36; Transparency & trust, 72 against 44. Also A hosted endpoint, with nothing to install.

| Category | Harness² | HarnessRouter |
| --- | --- | --- |
| Reliability (16%) | 20 | 35 |
| Performance (10%) | pending | pending |
| Schema & documentation (13%) | 51 | 83 |
| Agent ergonomics (13%) | 59 | 73 |
| Security & auth (14%) | 44 | 58 |
| Payments & pricing (10%) | 40 | 25 |
| Task success (10%) | pending | pending |
| Maintenance & community (7%) | 36 | 72 |
| Transparency & trust (7%) | 44 | 72 |

| Fact (where they differ) | Harness² | HarnessRouter |
| --- | --- | --- |
| Vendor | Google (Google Research) | HarnessRouter (Lumentree Corporation) |
| Hosted endpoint | no (local only) | `https://api.harnessrouter.ai` |
| Transports |  | HTTP |
| Auth | None | API key |
| Pricing | Free | Pay per use |
| 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). | Apache-2.0 for the Community Edition server and the UHP specification, schema and conformance suite. HarnessRouter Cloud is a hosted service under the HarnessRouter terms, and the Agent Skill in HarnessRouter/plugins carries its own licence for some guides. |
| Tools exposed | none | 0 |
| llms.txt | no | yes |
| Last release | 2026-10-08 | 2026-10-16 |
| Terms last updated | no document linked |  |
| Privacy policy last updated | no document linked |  |
| Popularity | 4.2k stars | 3.1k stars |