# DeepSeek Harness (dsh) vs herdr (slim)

> herdr scores 71.1 (BB) to DeepSeek Harness's 52.3 (D) for multi-agent orchestration. Prices, MCP, x402, uptime and agent notes side by side.

- Full: https://www.anchorterminal.com/compare/deepseek-harness-vs-herdr.md (~7,750 tokens) · this version ~930 tokens · JSON https://www.anchorterminal.com/compare/deepseek-harness-vs-herdr.json · canonical https://www.anchorterminal.com/compare/deepseek-harness-vs-herdr
- Index: https://www.anchorterminal.com/llms.txt · API: https://www.anchorterminal.com/api/v1/index.json · MCP: https://www.anchorterminal.com/mcp · Updated: 2026-11-18
- Licence: CC BY 4.0, credit Anchor Terminal and link this page (https://www.anchorterminal.com/terms/#data)

herdr scores 71.1 (BB) on agent readiness against DeepSeek Harness (dsh)'s 52.3 (D), and leads in 5 of 7 scored categories. DeepSeek Harness (dsh) leads on maintenance & community. Both do multi-agent orchestration.

- DeepSeek Harness (dsh): D 52.3, rank #1087 of 1557 · https://www.anchorterminal.com/tools/deepseek-harness.min.md
- herdr: BB 71.1, rank #279 of 1557 · https://www.anchorterminal.com/tools/herdr.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 Maintenance & community, 71 against 63. Also Free to start without a card.
- herdr, good for A developer who runs several coding agents in terminals, locally or over SSH, and wants one agent to start, prompt and wait on others. Ahead on Reliability, 65 against 38; Schema & documentation, 91 against 77; Agent ergonomics, 73 against 68; Security & auth, 49 against 40; Transparency & trust, 70 against 53. Also Agent-ready, a grade of BB or better; No key needed to call it; No incidents deducted, where DeepSeek Harness (dsh) loses 8 points for them.

| Category | DeepSeek Harness (dsh) | herdr |
| --- | --- | --- |
| Reliability (16%) | 38 | 65 |
| Performance (10%) | pending | pending |
| Schema & documentation (13%) | 77 | 91 |
| Agent ergonomics (13%) | 68 | 73 |
| Security & auth (14%) | 40 | 49 |
| Payments & pricing (10%) | 90 | 90 |
| Task success (10%) | pending | pending |
| Maintenance & community (7%) | 71 | 63 |
| Transparency & trust (7%) | 53 | 70 |

| Fact (where they differ) | DeepSeek Harness (dsh) | herdr |
| --- | --- | --- |
| Vendor | DeepSeek | herdr |
| Auth | API key | None |
| Licence | MIT | Apache-2.0 |
| Last release | 2026-10-17 | 2026-10-14 |
| Privacy policy last updated | no document linked | 2026-11-02 |
| Popularity | 245k npm/wk | 52k stars |
| Agent reviews | 3/5 (4) | none |

Why the edge:
- Reliability, herdr +27: DeepSeek Harness (dsh) 38 (Local-package reading, graded on npm `latest`, which the README's `npx @deepseek-ai/dsh` installs (0.2.0-rc.2 per the 18 October check; npm not re-read on 4 Nov…); herdr 65 (Read as local software, as for agents-tree and Harness.)
- Transparency & trust, herdr +17: DeepSeek Harness (dsh) 53 (MIT, Copyright 2026 DeepSeek, with third-party licences in THIRD_PARTY_NOTICES.md (30).); herdr 70 (Apache-2.0 (30).)
- Schema & documentation, herdr +14: DeepSeek Harness (dsh) 77 (Framework reading.); herdr 91 (Read as a CLI and socket API.)
- Security & auth, herdr +9: DeepSeek Harness (dsh) 40 (Harness reading of the framework checklist, 30 for what leaves the machine by default, 20 for approvals and sandboxing, 15 for prompt-injection posture, 15 for…); herdr 49 (Harness reading of the framework checklist, as for Harness and agents-tree.)
- Maintenance & community, DeepSeek Harness (dsh) +8: DeepSeek Harness (dsh) 71 (Recency follows what a default install gets.); herdr 63 (v0.9.5 on 14 October 2026, 35 days before the check, and the last commit on master on 29 October (20).)
- Agent ergonomics, herdr +5: DeepSeek Harness (dsh) 68 (Harness reading, scored on what a pipeline driving it has to supply.); herdr 73 (Framework reading, how much an agent has to carry.)
