deepseek-ai/deepseek-harness
DeepSeek Harness: Everything is a Plugin.
About the project
Open-source agent harness by DeepSeek AI written in TypeScript, built on an everything-is-a-plugin architecture powered by Cordis. It runs as a web UI via npx and serves as a base for composing AI agents from plugins.
Useful for
- Run the agent web UI locally with npx @deepseek-ai/dsh web
- Build a custom agent from plugins tagged with the dsh-plugin topic
- Deploy the harness on a remote server and access it over an SSH tunnel
README summarized by DeepSeek V4.1 Flash. Details may be inaccurate.
Why it’s trending
- 697 stars today.
- The repository is 31 days old and already has 222,542 stars.
- Top new repositories in the last 4 months: #1.
- Hacker News: “DeepSeek Harness” — 5 points, 2 days ago.
- About 94 forks a day — people are taking the code.
Stars per day
Bars are daily stars, the line is the usual pace. Red marks spike days.
Numbers
- Total stars
- 222,542
- Stars in a day
- 705
- Forks
- 26,426
- Issues and pull requests
- 0
- Watchers
- 952
- Language
- TypeScript
- License
- MIT
- Latest release
- dsh-v0.1.5-rc.2 · September 10, 2026
- Created
- August 13, 2026
- Last push
- September 11, 2026
Star trust
Growth looks organic: forks and discussion are in line with active projects, and stars arrive unevenly, the way people give them.
These are heuristics, not a verdict: we judge by the repository’s behavior, not by a list of stargazers.
Hacker News discussions
- DeepSeek Harness5 points, September 11, 2026
Spotted in
- September 13, 2026Top new repositories in the last 4 months: #1
Similar projects
-
6.8
melgarafael/DeskcommCRM
Self-hosted CRM with native AI agents for selling over WhatsApp: agents reply, qualify leads and close sales while your data stays on your server. An open alternative to Kommo, Octadesk and Intercom.
-
6.2
kruzovic7/ai-data-extractor
Python tool that extracts local chat histories from AI coding assistants (Claude Code, Cursor, Windsurf, Aider, Cline/Roo Code and more) into a single normalized JSONL format.
-
6.2
ayghri/i-have-adhd
A skill for a coding agent (Claude Code) that makes it lead with the answer and numbered steps, without preamble or filler. Helps you get concrete actions instead of long-winded reasoning.
-
6.1
tech-leads-club/agent-skills
A registry of validated skills (instruction plugins) for AI coding agents: extends Claude Code, Cursor, Copilot and others with secure, tested capabilities.
-
6.1
jordan-gibbs/hyperresearch
A deep research harness for Claude Code: turns one prompt into a report with verified citations and a persistent source vault. Every source lands in a searchable store reused by later sessions.
-
6.0
NVlabs/SoL-Pi
An extension for Pi that cuts token usage and redundant turns of coding agents via four mechanisms: action fusion, observation packing, log reduction, and context compaction.