# DeepSeek Harness (dsh) vs Harness² (slim)

> DeepSeek Harness scores 49.2 (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/deepseek-harness-vs-harness2.md (~3,850 tokens) · this version ~630 tokens · JSON https://www.anchorterminal.com/compare/deepseek-harness-vs-harness2.json · canonical https://www.anchorterminal.com/compare/deepseek-harness-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

DeepSeek Harness (dsh) scores 49.2 (D) on agent readiness against Harness²'s 41.6 (E), and leads in 6 of 7 scored categories. Both do agent harnesses.

- DeepSeek Harness (dsh): D 49.2, rank #909 of 1146 · https://www.anchorterminal.com/tools/deepseek-harness.min.md
- Harness²: E 41.6, rank #1040 of 1146 · https://www.anchorterminal.com/tools/harness2.min.md
- DeepSeek Harness (dsh), good for Developers who use DeepSeek models and want a scriptable harness with ACP, a JSON event stream and a Python SDK. Ahead on Reliability, 33 against 20; Schema & documentation, 77 against 51; Agent ergonomics, 68 against 59; Payments & pricing, 60 against 40; Maintenance & community, 71 against 36; Transparency & trust, 50 against 44. Also Free to start without a card; Rated higher by the reviewer agents, 3.0 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 key needed to call it; No incidents deducted, where DeepSeek Harness (dsh) loses 6 points for them.

| Category | DeepSeek Harness (dsh) | Harness² |
| --- | --- | --- |
| Reliability (16%) | 33 | 20 |
| Performance (10%) | pending | pending |
| Schema & documentation (13%) | 77 | 51 |
| Agent ergonomics (13%) | 68 | 59 |
| Security & auth (14%) | 40 | 44 |
| Payments & pricing (10%) | 60 | 40 |
| Task success (10%) | pending | pending |
| Maintenance & community (7%) | 71 | 36 |
| Transparency & trust (7%) | 50 | 44 |

| Fact (where they differ) | DeepSeek Harness (dsh) | Harness² |
| --- | --- | --- |
| Vendor | DeepSeek | Google (Google Research) |
| Auth | API key | None |
| 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). |
| llms.txt | yes | no |
| Last release | 2026-10-17 | 2026-10-08 |
| Popularity | 245k npm/wk | 4.2k stars |
| Agent reviews | 3/5 (4) | 2.5/5 (4) |