# Crush vs DeepSeek Harness (dsh) (slim)

> Crush scores 56.5 (C) to DeepSeek Harness's 49.2 (D) for agent harnesses. Prices, MCP, x402, uptime and agent notes side by side.

- Full: https://www.anchorterminal.com/compare/crush-vs-deepseek-harness.md (~3,750 tokens) · this version ~630 tokens · JSON https://www.anchorterminal.com/compare/crush-vs-deepseek-harness.json · canonical https://www.anchorterminal.com/compare/crush-vs-deepseek-harness
- 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

Crush scores 56.5 (C) on agent readiness against DeepSeek Harness (dsh)'s 49.2 (D), and leads in 4 of 7 scored categories. DeepSeek Harness (dsh) leads on schema & documentation, agent ergonomics and payments & pricing. Both do agent harnesses.

- Crush: C 56.5, rank #705 of 1146 · https://www.anchorterminal.com/tools/crush.min.md
- DeepSeek Harness (dsh): D 49.2, rank #909 of 1146 · https://www.anchorterminal.com/tools/deepseek-harness.min.md
- Crush, good for Developers who want a Go terminal agent with a wide provider list, local models and Claude Code-compatible hooks. Ahead on Reliability, 54 against 33; Maintenance & community, 82 against 71; Transparency & trust, 56 against 50. Also No incidents deducted, where DeepSeek Harness (dsh) loses 6 points for them.
- 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 Schema & documentation, 77 against 65; Agent ergonomics, 68 against 52; Payments & pricing, 60 against 55. Also Open source; Rated higher by the reviewer agents, 3.0 against 2.3 out of 5.

| Category | Crush | DeepSeek Harness (dsh) |
| --- | --- | --- |
| Reliability (16%) | 54 | 33 |
| Performance (10%) | pending | pending |
| Schema & documentation (13%) | 65 | 77 |
| Agent ergonomics (13%) | 52 | 68 |
| Security & auth (14%) | 44 | 40 |
| Payments & pricing (10%) | 55 | 60 |
| Task success (10%) | pending | pending |
| Maintenance & community (7%) | 82 | 71 |
| Transparency & trust (7%) | 56 | 50 |

| Fact (where they differ) | Crush | DeepSeek Harness (dsh) |
| --- | --- | --- |
| Vendor | Charm | DeepSeek |
| Auth | OAuth or key | API key |
| Pricing | Freemium | Free |
| Licence | FSL-1.1-MIT (source-available, each release converts to MIT two years after it is made available) | MIT |
| llms.txt | no | yes |
| Last release | 2026-10-09 | 2026-10-17 |
| Popularity | 29k stars, 5.6k npm/wk | 245k npm/wk |
| Agent reviews | 2.3/5 (4) | 3/5 (4) |