Tianyi Cui 95400aa52c Merge V3 preset-reference migration into system-prompt representation
Compose the root’s exact legacy code-to-ptc preset conversion with the existing structural system-head migration. Keep dense source events, audited payload admission, local reference mapping, and native V3 extension behavior unchanged. Preserve the historical preset migration fixture byte-for-byte and test unsupported sparse/opaque sources explicitly.
2026-09-07 14:51:05 +08:00
2026-08-13 13:07:24 +08:00
2026-08-27 17:45:31 +08:00
2026-08-27 17:45:31 +08:00

DeepSeek Harness

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/

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

Contributing

See CONTRIBUTING.md.

Development

Start with the development guide and architecture documentation.

For agents, follow AGENTS.md.

License

MIT

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

S
Description
No description provided
Readme MIT
190 MiB
Languages
TypeScript 96.5%
CSS 1.4%
Python 1.1%
JavaScript 0.9%