Building a listed tool

Yifan Shi

Cordis architecture paper first author; Peking University and DeepSeek-AI, named behind the DeepSeek Harness (dsh) listing on Anchor Terminal.

Cordis architecture paper first author; Peking University and DeepSeek-AI

No about written yet. If this is you, you can send us one, with a photo if you like, at the address below.

What Yifan builds

DeepSeek Harness (dsh) D · Agent harnesses
DeepSeek Harness (dsh) is DeepSeek's MIT-licensed agent harness, a developer preview built from plugins over the Cordis framework. It runs as a local Web UI, a one-shot headless command, an ACP server or a JSON-RPC server for its Python SDK.
Cordis architecture paper first author; Peking University and DeepSeek-AI, researched 27 October 2026 · the people behind it

Works with

Liang Wenfeng Founder
Tianyi Cui Cordis architecture paper coauthor; DeepSeek-AI

Questions

Who is Yifan Shi?

Yifan Shi is cordis architecture paper first author; Peking University and DeepSeek-AI.

What does DeepSeek make?

Anchor Terminal lists DeepSeek Harness (dsh) from DeepSeek. DeepSeek Harness (dsh) is DeepSeek's MIT-licensed agent harness, a developer preview built from plugins over the Cordis framework. It runs as a local Web UI, a one-shot headless command, an ACP server or a JSON-RPC server for its Python SDK.

How are Yifan's tools graded?

DeepSeek Harness (dsh) is graded D, 49.5 out of 100, on Anchor Terminal's benchmark, which scores every listing against the same checklist.

Sources (6)

These are the people building the tools we list, named for their public role in the company or project behind a listing, from public pages, with the date it was researched. They don't work for Anchor Terminal (our own team is on the about page). We show public roles, public profiles and what the listing pages show, nothing private. To correct something, send an about or a photo, or have a page removed, write to privacy@anchorterminal.com.

Do agents find, use and choose your tools?

An agent-readiness audit runs our probes, task suite and eight reviewer agents against your public and internal tools, and comes back with a scorecard, the transcripts of what failed, and a fix list in priority order. From $2,500, re-run included. We never take payment to move a rank. We do help companies earn one.