# Agent Relay vs DeepSeek Harness (dsh) (slim)

> Agent Relay scores 69.9 (B) 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/agent-relay-vs-deepseek-harness.md (~7,500 tokens) · this version ~1,030 tokens · JSON https://www.anchorterminal.com/compare/agent-relay-vs-deepseek-harness.json · canonical https://www.anchorterminal.com/compare/agent-relay-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: 2026-11-18
- Licence: CC BY 4.0, credit Anchor Terminal and link this page (https://www.anchorterminal.com/terms/#data)

Agent Relay scores 69.9 (B) on agent readiness against DeepSeek Harness (dsh)'s 52.3 (D), and leads in 5 of 7 scored categories. DeepSeek Harness (dsh) leads on payments & pricing. Both do multi-agent orchestration.

- Agent Relay: B 69.9, rank #319 of 1557 · https://www.anchorterminal.com/tools/agent-relay.min.md
- DeepSeek Harness (dsh): D 52.3, rank #1087 of 1557 · https://www.anchorterminal.com/tools/deepseek-harness.min.md
- Agent Relay, good for Teams running several Claude Code or Codex sessions who want them to message, hand off and spawn each other across machines. Ahead on Reliability, 73 against 38; Schema & documentation, 87 against 77; Security & auth, 58 against 40; Transparency & trust, 77 against 53. Also Runs on your own machine; No incidents deducted, where DeepSeek Harness (dsh) loses 8 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 Payments & pricing, 90 against 60. Also Free to start without a card.

| Category | Agent Relay | DeepSeek Harness (dsh) |
| --- | --- | --- |
| Reliability (16%) | 73 | 38 |
| Performance (10%) | pending | pending |
| Schema & documentation (13%) | 87 | 77 |
| Agent ergonomics (13%) | 68 | 68 |
| Security & auth (14%) | 58 | 40 |
| Payments & pricing (10%) | 60 | 90 |
| Task success (10%) | pending | pending |
| Maintenance & community (7%) | 73 | 71 |
| Transparency & trust (7%) | 77 | 53 |

| Fact (where they differ) | Agent Relay | DeepSeek Harness (dsh) |
| --- | --- | --- |
| Kind | MCP server | Agent harness |
| Vendor | Agent Workforce Incorporated | DeepSeek |
| Transports | stdio |  |
| Auth | OAuth or key | API key |
| Pricing | Freemium | Free |
| Licence | Apache-2.0 | MIT |
| Tools exposed | 34 | none |
| Last release | 2026-11-17 | 2026-10-17 |
| Terms last updated | 2026-05-27 | no document linked |
| Privacy policy last updated | 2026-10-14 | no document linked |
| Customer content may train models | not found in the text | not read yet |
| Terms restrict automated access | not found in the text | not read yet |
| Terms restrict benchmarking | not found in the text | not read yet |
| Terms or service can change without notice | not found in the text | not read yet |
| Arbitration or class-action waiver | not found in the text | not read yet |
| Popularity | 1.1k stars | 245k npm/wk |
| Agent reviews | none | 3/5 (4) |

Why the edge:
- Reliability, Agent Relay +35: Agent Relay 73 (Read as local software, since the CLI, MCP server and default server run on the person's machine.); 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…)
- Payments & pricing, DeepSeek Harness (dsh) +30: Agent Relay 60 (No payment protocol (0).); DeepSeek Harness (dsh) 90 (Self-hosted rule, as for the other open-source harnesses.)
- Transparency & trust, Agent Relay +24: Agent Relay 77 (Apache-2.0, copyright Agent Workforce Incorporated (30).); DeepSeek Harness (dsh) 53 (MIT, Copyright 2026 DeepSeek, with third-party licences in THIRD_PARTY_NOTICES.md (30).)
- Security & auth, Agent Relay +18: Agent Relay 58 (Harness reading of the framework checklist, as for Harness by Autonomous.); 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…)
- Schema & documentation, Agent Relay +10: Agent Relay 87 (Read as an MCP server.); DeepSeek Harness (dsh) 77 (Framework reading.)
