
Open-source CMA-compatible agent runtime for any model, with MCP tools, sandboxed sessions, audit, replay, and a local console. Includes a native DeepSeek Harness bundle over stdio MCP.
Install Sandbase Harness
Clean install: prebuilt on npm and declares a `dsh.bundle` layer.
The one-line version
dsh plugin --profile my-profile add managed-agentsThe easy path: this bundle is published to npm, so the install pulls a prebuilt artifact — no build step runs on your machine and no build approval is needed.
From npm — installs a prebuilt artifact, no build step on your machine
# 1. add the bundle to a profile — --profile my-profile points at $DSH_HOME/profiles/my-profile
dsh plugin --profile my-profile add managed-agents
# 2. verify: the bundle should show up as a layer in the resolved config
dsh --profile my-profile --dump-config
# 3. boot the profile
dsh --profile my-profilePackage: managed-agents
Prefer to install from source instead?
From GitHub — pulls source, and may ask for build approval on first run
# 1. add the bundle to a profile — --profile my-profile points at $DSH_HOME/profiles/my-profile
dsh plugin --profile my-profile add github:sandbaseai/sandbase-harness#<commit-sha>
# 2. verify: the bundle should show up as a layer in the resolved config
dsh --profile my-profile --dump-config
# 3. boot the profile
dsh --profile my-profilePrerequisites
- API key
- Required — see the repository README for which provider.
- Network access
- Required at runtime.
- Language
- TypeScript
Install check
Every field the verdict was derived from, so you can re-derive it yourself
| Field checked | Result | Weight | What the spec says about it |
|---|---|---|---|
| lifecycleScripts | pass | info | no install-time scripts |
| dsh.bundle | pass | fatal | package.json declares a `dsh.bundle` layer |
| dsh.bundle.patch file | pass | fatal | patch file present at `examples/deepseek-harness/cordis.yml` |
| npm registry | pass | fatal | published as `managed-agents` — prebuilt artifacts |
- Verdict reason
- on npm with a valid bundle declaration
- package.json read
- package.json
- Rules applied from
- docs/user/develop/basic/publish.md
- Checked at
- 2026-08-15
From the README
Excerpt as published by the author, plain text, unedited
A local-first runtime for AI agents. Sessions, sandboxed tools, memory, credentials, audit trails, and a built-in Console — all running on your machine or in your own infrastructure.
Topics
GitHub topics on this repository
More in Self Hosted Docker Compose
Ranked by similarity inside the cluster, not alphabetically
Dsh Web
Tom6814
🚀 DeepSeek Harness 的网页部署Docker
Deepseek Harness Docker
AlliotTech
deepseek-harness docker部署
Deepseek Harness Docker
Yuanlw
一个 Docker 容器跑起 DeepSeek Harness(dsh Web UI)——自带 HTTPS,内网/局域网友好,支持任意 OpenAI 兼容模型网关。
Dsh Docker
devLythen
Docker image for DeepSeek Harness, with self-hosted deployment supported
Deepseek Harness Docker
runzhliu
Community Docker and Kubernetes packaging for DeepSeek Harness (@deepseek-ai/dsh), with a hardened image, Compose stack, Helm chart, Web UI, and headless CLI.
Dsh Container
NIyueeE
DeepSeek Harness (dsh) container image: universal dev-container base, dsh auto-update on boot, compose + Quadlet examples