Back to directory

DeepSeek Harness

An open-source agent harness from DeepSeek AI built on a plugin-based architecture, with a local web UI started from npm. It is in developer preview.

DeepSeek Harness

DeepSeek Harness (dsh) is an agent harness developed by DeepSeek AI. Its architecture treats everything as a plugin and is powered by Cordis, a framework described in the paper A Programming Paradigm for Spatiotemporal Composability.

Running it with npx starts a web UI on a local port, and it can also be built and run from source with pnpm. Plugin authors can tag their repositories with the dsh-plugin topic for discovery.

The project is in developer preview and warns that compatibility-breaking changes will happen. It is written in TypeScript and MIT licensed.

More in Agent frameworks

See all 902
  • Recurse

    recurse.run

    A serverless harness that lets a coding agent design, test, and deploy its own specialist sub-agents as tools, MCP servers, or bots, defined by a schema-validated manifest.

  • ProofForge

    shulgin.is-a.dev

    An AI-agent pipeline that decomposes a mathematics problem, proves each piece, and formalizes the result in Lean 4 and Mathlib until the Lean kernel accepts it, with six of its proofs already merged into Google DeepMind's formal-conjectures repository.

  • local-coder

    github.com

    Builds a local coding-agent team on top of Ollama and OpenCode by detecting the machine's hardware, recommending models for seven specialist roles, and testing whether each assigned model can actually use tools, edit a repository and pass verification.