Sign in
DeepSeek Harness logo

DeepSeek Harness

Beta

DeepSeek's open-source, plugin-based harness for running AI coding agents locally

Visit website
Caution

DeepSeek Harness is a free, MIT-licensed way to run a coding agent from a local web UI, reading and editing files and running commands with DeepSeek, Anthropic, OpenAI, Kimi, GLM or custom compatible models. Caution because DeepSeek's own safety notice calls it unaudited and not secure or production-ready, and a critical flaw, CVE-2026-82533, let a sandboxed agent switch off its own sandbox on unpatched installs. Right for experimenters in a disposable VM; wrong for machines holding credentials or production code.

AI-Native

An agent loop sends model requests and runs tool calls that read and edit workspace files and run commands in a sandbox.

Is it right for you?

Good for

  • Running a coding agent from a local browser UI: npx @deepseek-ai/dsh web starts it at http://127.0.0.1:3080, and the agent can read and edit workspace files, run commands, delegate work and keep a plan
  • Choosing your model: besides a DeepSeek API key, built-in provider ids include anthropic, openai, moonshotai for Kimi and zai for GLM, and custom providers can speak openai-completions, openai-responses or anthropic-messages
  • Developers who want to rework the agent itself, since everything is a plugin on the Cordis framework, including model adapters, tools, persistence, sandbox and approval policy
  • Zero software cost under the MIT licence

Not good for

  • Production or sensitive machines: DeepSeek's SAFETY.md says it has not undergone a security audit, must not be treated as secure or production-ready, and recommends a disposable virtual machine, container or dedicated environment
  • Stable integrations, since the README warns of compatibility-breaking changes in the developer preview
  • Agents that read untrusted content on unpatched installs: under CVE-2026-82533, attacker-supplied text the agent read could get it to disable its own sandbox with one shell command, on shipped defaults and with no network exposure
  • Trusting the CVE record's fix version on npm: The Hacker News reports 0.1.2-alpha.1 was fixed on GitHub only and never published to npm, so npm users need 0.1.2-alpha.2 or later

Our experience

We haven't tested DeepSeek Harness ourselves. This profile is based on public documentation, user reviews, and community feedback.

Pricing

Open Source
Open source (MIT)$0
  • MIT licensed harness
  • Requires a DeepSeek API key or another configured model provider
  • Custom OpenAI- or Anthropic-compatible endpoints supported
View full pricing

Workflow recipes

Try it in an isolated environment

Run the developer preview the way DeepSeek's safety notice recommends

  1. Start from a disposable virtual machine, container or dedicated environment with only the files the agent needs
  2. Install Node.js and run npx @deepseek-ai/dsh web
  3. Open http://127.0.0.1:3080 and enter a DeepSeek API key or configure another provider
  4. Choose the workspace directory where you started dsh
  5. Confirm the installed version is 0.1.2-alpha.2 or later before letting the agent read untrusted material

No verdict changes yet

The clock starts day one — changes land here as our verdict evolves.

Sources

Verification log

  • Status— No changes

    Automated agent

  • Profile— No changes

    Automated agent

How we evaluate

Want this running in your business?

We tested this tool and we build with tools like it every day. Tell us the workflow and we will set it up, integrate it and hand it over working.

Tell us what you need (opens in new tab)See what we build

The conversation runs on Gnosari, one of the tools in this directory. A real conversation, not a sales script.