11st of 19 in Agent backends

deepseek-harness

Plugin-based agent harness from DeepSeek with a local Web UI

Stars
249.7k
License
MIT
Last commit
Oct 2026
Language
TypeScript
Stars, last 9 weeks+249,708
12 Aug 2026: 0 stars19 Aug 2026: 167,810 stars26 Aug 2026: 196,770 stars2 Sept 2026: 208,386 stars9 Sept 2026: 216,450 stars16 Sept 2026: 225,818 stars23 Sept 2026: 233,534 stars30 Sept 2026: 240,480 stars7 Oct 2026: 244,919 stars14 Oct 2026: 249,708 stars

0 on 12 Aug 2026249,708 on 14 Oct 2026

From GitHub's daily star counts.

Checked on GitHub.

Overview

DeepSeek Harness (`dsh`) is a TypeScript agent harness built on the Cordis plugin framework, where every component is a plugin. It runs via `npx @deepseek-ai/dsh web` or from a source checkout with pnpm, and serves a Web UI at 127.0.0.1:3080 by default. It is a developer preview, and the README warns of compatibility-breaking changes.

Who it is for: Developers building agents through plugins, tolerant of breaking changes

Strengths

  • Starts with one npx command; no Docker or database mentioned
  • Everything-is-a-plugin design on Cordis, with a dsh-plugin topic for discovery
  • MIT license, documentation site and third-party license notices
  • Web UI binds to 127.0.0.1 by default; --no-open skips the browser

Weaknesses

  • Developer preview; README warns of compatibility-breaking changes
  • No tagged release published
  • README does not list supported models, providers or system requirements
  • Safety notice must be read before running; its contents are not in the README

What it needs

  • TypeScript
  • Needs Node.js, pnpm (source build)

Head to head

Also in Agent backends

See all 19
Also in Agent backends
RankProjectScore
2eve-software-factory-templateeve pipeline that turns GitHub or Linear issues into reviewed draft PRs1.2k starsMIT61 out of 100
3marketing-team-eve-templateeve lead agent delegating to five marketing specialists with approval gates453 starsMIT56 out of 100
#4personal-agent-templateeve and Nuxt personal agent with Slack, GitHub, Linear and per-user memory475 starsMIT53 out of 100
#5adk-recipesRunnable Agent Development Kit recipes, from single patterns to deployable agents10.5k starsApache-2.051 out of 100
#6ai-townGenerative-agents town simulation on Convex with Ollama by default Live demo ↗ (opens in a new tab)10.6k starsMIT47 out of 100