Tools & Capabilities

oh-my-dsh

my-dsh/oh-my-dsh · ★ 1

my-dsh

Fork notice : This repository is a personal fork of deepseek-harness, for private use. On top of upstream it adds a token statistics panel that tracks per-session and…

License
MIT
Added
2026-08-16
Maintenance
active
Install kind
github
Manifest details
Manifest status
Not verified
Manifest path
-
Manifest checked
2026-08-19
Lifecycle scripts
postinstall

Static manifest checks report declarations only; they are not compatibility or security review.

安装

dsh plugin --profile web add github:my-dsh/oh-my-dsh

GitHub 源码安装:首次需按提示配置 allowBuilds 构建授权后重试

For install and environment setup, plus plugin development tutorials, see DSH community docs ↗

README

Source README · body: en · Read Chinese README

Table of contents
  1. Added features
  2. Token usage dashboard
  3. Session attention reminders
  4. Developer preview
  5. Run
  6. Run from npm
  7. Run from source
  8. Community and support
  9. Contributing
  10. Development
  11. Citation
  12. License

English | 中文

DeepSeek Harness (dsh) is an open-source agent harness developed by DeepSeek AI.

It is built on an everything-is-a-plugin architecture and powered by Cordis, whose design is described in A Programming Paradigm for Spatiotemporal Composability.

Documentation: https://deepseek-harness.github.io/deepseek-harness/

Added on top of upstream — this repository adds two capabilities you won't find in stock DeepSeek Harness: a token-usage dashboard and session-attention reminders.

Added features

This repository adds two capabilities on top of the upstream DeepSeek Harness.

Token usage dashboard

@deepseek-ai/dsh-token-usage persists provider-reported usage for every model call into a SQLite-backed store and aggregates it into daily summaries per (provider, model) — tokens split into uncached input, cache read, cache write, and output, plus TTFT and wall-time averages. The built-in web dashboard (packages/bundle/token-usage-dashboard) surfaces these as cross-session statistics in the Web GUI. See the token-usage subsystem doc.

The token-usage dashboard: per-day cross-session statistics grouped by provider and model

Session attention reminders

When a background session awaits the user — a pending interaction (approval / plan review / question) or a finished AI reply not yet opened — a floating overlay appears in the top-right of the Web GUI. It tags the tab title (N) and plays one of four distinct Canvas2D animations keyed by the highest-priority attention kind, so you can tell at a glance what kind of reminder is owed. The plugin is developed in the standalone dsh-session-attention repository; see the community plugins guide for installation.

The session-attention overlay announcing sessions awaiting the user

Developer preview

DeepSeek Harness is in developer preview and iterating rapidly. THERE WILL BE COMPATIBILITY-BREAKING CHANGES.

Review the safety notice before running the project.

Run

Run from npm

Install Node.js, then run:

npx @deepseek-ai/dsh web

The command starts the Web UI at http://127.0.0.1:3080 by default and opens it in the default browser for a local launch. An SSH launch only prints the host URL because the SSH client or editor owns the local forwarded address. Pass --no-open to run the server without opening a browser. See Web UI guide.

Run from source

To run from a repository checkout:

git clone https://github.com/deepseek-ai/deepseek-harness.git
cd deepseek-harness
pnpm install
pnpm run build
pnpm dsh web

pnpm run build prepares the repository artifacts. pnpm dsh web uses those built artifacts without rebuilding.

Community and support

  • Submit feedback or bug reports through GitHub Discussions.
  • Add the dsh-plugin topic to your plugin repository for discoverability.
  • Join DeepSeek Harness Discord community.

Contributing

See CONTRIBUTING.md.

Development

Start with the development guide and architecture documentation.

pnpm run dev:web builds, serves, and rebuilds client bundles on source edits in one terminal, and make help lists the matching Make targets for Web and Desktop; the guide's application commands section owns the full table.

For agents, follow AGENTS.md.

Citation

@misc{deepseek-harness2026,
  title={DeepSeek Harness: Everything is a Plugin},
  author={DeepSeek-AI},
  year={2026},
  publisher={GitHub},
  howpublished={\url{https://github.com/deepseek-ai/deepseek-harness}},
}

License

MIT

Third-party dependencies and their licenses are disclosed in THIRD_PARTY_NOTICES.md.