DEDUPED Hot AI repos, turned into use cases Get the Monday 5

How to use DeepSeek Harness Docker: what you can do with it

What is DeepSeek Harness Docker? A community Docker, Compose, Podman, and Helm packaging of the official DeepSeek Harness (@deepseek-ai/dsh) agent runtime, with a Web UI and a headless CLI.

How do I use it? Run docker compose pull in the repository directory; then run DSH_WORKSPACE=/absolute/path/to/your/project docker compose up -d --no-build to mount your project as the workspace; run docker compose ps and confirm the service is healthy. Full steps below.

Trended earlier

View repo on GitHub

Third-party repos we don't own. AI-written use cases can be wrong. Disclaimer

What do you want to do?

4 use cases

  • Run the DeepSeek Harness Web UI locally with Compose

    Start the official DSH Web UI in a container on your own machine in a few commands.

    View prompt
    Using the repository runzhliu/deepseek-harness-docker, start the Compose stack with DSH_WORKSPACE set to <project-path>, then print the dsh web URL from the container logs. Expected output: a URL on 127.0.0.1:3080 that includes a token query parameter. Verify that a request to the root path without the token returns 401.

  • Deploy DeepSeek Harness on Kubernetes with the Helm chart

    Run one DSH instance as a StatefulSet with persistent state and a workspace claim.

    View prompt
    Using the Helm chart in runzhliu/deepseek-harness-docker, lint and install it into the namespace <namespace> as release <release-name>. Expected output: a StatefulSet with one replica, a dsh-home PVC, and a Headless Service. Verify that the pod reaches Ready and that the chart still shows exactly one replica.

  • Run DeepSeek Harness headless for batch and CI jobs

    Use the headless profile for one-shot or automated agent runs without the Web UI.

    View prompt
    Using the image from runzhliu/deepseek-harness-docker, run `dsh --profile headless` against the workspace <workspace-path> with provider credentials from environment variables. Expected output: a completed task with a zero exit code and changed files in the workspace. Verify that no saved credential file was needed for the run.

  • Run DeepSeek Harness rootless with Podman Compose

    Start the stack under a rootless Podman user with the workspace owned by you.

    View prompt
    Using runzhliu/deepseek-harness-docker, verify Podman is rootless and start the stack with compose.yaml and compose.podman.yaml, using <project-path> as DSH_WORKSPACE. Expected output: running containers and a Rootless value of true. Verify that a file the agent creates in the workspace is owned by the invoking user on the host.

Quick start with DeepSeek Harness Docker

  1. Check you have what it needs: Docker with Compose, or Rootless Podman 4.5 with podman-compose 1.6.0 or newer; A local project directory to mount as the workspace, or leave the default named volume; Model provider credentials to enter in the Settings page or supply as environment variables.
  2. Open runzhliu/deepseek-harness-docker on GitHub and read the README and license.
  3. Run docker compose pull in the repository directory.
  4. Run DSH_WORKSPACE=/absolute/path/to/your/project docker compose up -d --no-build to mount your project as the workspace.
  5. Run docker compose ps and confirm the service is healthy.
  6. Run docker compose logs --no-color deepseek-harness | grep 'dsh web:' and copy the full URL that includes the token.

These steps come from our top use case, Run the DeepSeek Harness Web UI locally with Compose, which also has a copy-paste agent prompt.

Use this in your AI agent

Ask your agent

Using the Deduped MCP, get the setup steps for runzhliu/deepseek-harness-docker

Add Deduped to Claude Code once

claude mcp add --transport http deduped https://dedupedai.com/mcp

Cursor, ChatGPT, others

DeepSeek Harness Docker alternatives · Best AI repos for Software and DevOps

About this repo

Requirements

  • Docker with Compose, or Rootless Podman 4.5 with podman-compose 1.6.0 or newer
  • A local project directory to mount as the workspace, or leave the default named volume
  • Model provider credentials to enter in the Settings page or supply as environment variables
  • A Kubernetes cluster and Helm for the chart deployment

Add this badge to your README

Maintain DeepSeek Harness Docker? Show readers where to find these use cases. Use cases on Deduped

Markdown 

[![Use cases on Deduped](https://dedupedai.com/badge/runzhliu/deepseek-harness-docker.svg)](https://dedupedai.com/use-cases/runzhliu-deepseek-harness-docker/?utm_source=github&utm_medium=badge&utm_campaign=runzhliu-deepseek-harness-docker)

HTML 

<a href="https://dedupedai.com/use-cases/runzhliu-deepseek-harness-docker/?utm_source=github&amp;utm_medium=badge&amp;utm_campaign=runzhliu-deepseek-harness-docker"><img src="https://dedupedai.com/badge/runzhliu/deepseek-harness-docker.svg" alt="Use cases on Deduped" height="20"></a>

A static image, no tracking script. About the badge

Questions about DeepSeek Harness Docker

What is DeepSeek Harness Docker?

A community Docker, Compose, Podman, and Helm packaging of the official DeepSeek Harness (@deepseek-ai/dsh) agent runtime, with a Web UI and a headless CLI. It is an open-source project on GitHub: https://github.com/runzhliu/deepseek-harness-docker.

How do I use DeepSeek Harness Docker?

Run docker compose pull in the repository directory; then run DSH_WORKSPACE=/absolute/path/to/your/project docker compose up -d --no-build to mount your project as the workspace; run docker compose ps and confirm the service is healthy. The use cases on this page give the full steps and a copy-paste agent prompt for each job.

Who is DeepSeek Harness Docker for?

Developers and platform engineers who want to run the DeepSeek Harness agent runtime in a container on a laptop, a Podman host, or a Kubernetes cluster.

What can I do with DeepSeek Harness Docker?

4 use cases so far, for example: Run the DeepSeek Harness Web UI locally with Compose; Deploy DeepSeek Harness on Kubernetes with the Helm chart; Run DeepSeek Harness headless for batch and CI jobs. Each has steps and a copy-paste agent prompt.

What do I need to run DeepSeek Harness Docker?

Docker with Compose, or Rootless Podman 4.5 with podman-compose 1.6.0 or newer; A local project directory to mount as the workspace, or leave the default named volume; Model provider credentials to enter in the Settings page or supply as environment variables; A Kubernetes cluster and Helm for the chart deployment.

What are alternatives to DeepSeek Harness Docker?

Other hot AI repos in Software and DevOps: Deep Infer, Harness2, Orca, Opencode, Graphify.

Is DeepSeek Harness Docker safe to run?

Deduped does not own, audit or vouch for it. Read the README and license, run it on your own systems first and review every command before you run it.