Skip to main content
AdOpenFree logoPromote your productReach more potential users and drive product growth and revenue.Advertise
Favicon of DeepSeek Harness

DeepSeek Harness

Free Listing

DeepSeek Harness (dsh) is an open-source agent harness in developer preview. Every agent capability is implemented as a composable Cordis plugin for models, tools, skills, sessions, sandboxes, storage, loops, scheduling, and the UI.

Visit deepseek-ai/deepseek-harness

Overview

DeepSeek Harness is an open-source agent harness developed by DeepSeek AI and built on the Cordis plugin system. It is in developer preview with source code available. In DeepSeek Harness, every agent capability is implemented as a plugin that can be swapped or recomposed, and every run is recorded in an append-only session log for traceability.

Key Features

  • Everything is a plugin: models, tools, skills, sessions, sandboxes, storage, loops, scheduling, and the UI are provided by Cordis plugins that can be selected, swapped, or extended in configuration.
  • Every run is traceable through an append-only session log that records system prompts, reasoning, tool calls and results, subagent scheduling, and context injections.
  • Multiple runtime modes: Standard mode includes the full toolset; Code mode orchestrates multi-step tool calls through the Code Mode SDK; Minimal mode keeps only a shell tool and a file editor; Creator mode supports runtime inspection and plugin experiments.
  • The Cordis kernel manages plugin mounting, unmounting, and dependencies, with Cordis services and events connecting plugins.
  • A Web UI and command-line runtime are available, with quick launch through npx @deepseek-ai/dsh web or source installation options.

Use Cases

  • Building and customizing agent harnesses for tasks such as file editing, shell commands, file and web search, skills, planning, goals, subagents, and workflows.
  • Benchmarking models in a minimal environment with a two-tool coding agent.
  • Creating custom agent presets and experimenting with Cordis plugins in Creator mode.
  • Inspecting, resuming, forking, searching, and replaying agent runs from session logs.

Getting Started

  • Install Node.js, then run npx @deepseek-ai/dsh web to start the Web UI.
  • To run from source, clone the repository, run pnpm install, run pnpm run build, and then run pnpm dsh web.

Deployment & Requirements

  • Node.js is required for the npm launch method.
  • Running from source requires pnpm, a repository checkout, and built artifacts prepared by pnpm run build before pnpm dsh web.

Before You Adopt

  • License: MIT. Review its terms before using, modifying, or distributing the project.
  • The project remains in developer preview, is still being tested, and its core plugins and APIs will continue to evolve.
  • The append-only session log records everything the model sees, including system prompts, reasoning, tool calls and results, subagent scheduling, and context injections, which is relevant when handling sensitive data.

Comments

Sign in to leave a comment.

More like DeepSeek Harness

Favicon of OpenHuman

OpenHuman

Free ListingStars: 40.1K

Open-source personal AI that runs on your laptop

Agent Frameworks

OpenHuman is a free, open-source personal AI for Mac, Windows and Linux that keeps data local and orchestrates fleets of agents. Built in Rust, it is positioned as a fast, efficient open-source agent harness.

Favicon of Browser Harness

Browser Harness

Free ListingStars: 18.1K

Self-healing browser agents built directly on CDP

Agent Frameworks

Browser Harness is a thin, self-healing harness for browser agents built directly on CDP. Agents can edit their own helpers mid-task, so the harness improves with every task and enables LLMs to complete browser tasks.

Favicon of Harbor

Harbor

Free ListingStars: 5.6K

Evaluate and optimize sandboxed agents and models.

Agent Frameworks

Harbor is a framework from the creators of Terminal-Bench for evaluating and optimizing agents and language models in container environments. It supports arbitrary agents, custom benchmarks, parallel cloud experiments, and rollouts for RL