repowisedeepseek-ai/dsh-superagent-prototype

deepseek-ai / dsh-superagent-prototype Architecture and code health

Towards a More Autonomous Agent System

TypeScript★ 10,011
Use in your agentAsk this codebase

github.com/deepseek-ai/dsh-superagent-prototypeIndexed at 6337fc8Up to date with upstream

What is dsh-superagent-prototype?

dsh-superagent-prototype is a proactive coding agent for one GitHub repository, packaged as a bundle for DeepSeek Harness. It listens to GitHub and, optionally, Feishu, and when an allowed person asks for work, it opens a work item and carries it out in its own agent session and directory. The agent then replies in the original conversation, for example with a pull request, and its main language is TypeScript.

Written by a model from the README and the source

206 files and 1,784 symbols in 4 modules, led by TypeScript (171 files) and Python (1).

Start reading

Code health

8.7out of 10Excellent
Full health report

On the leaderboards:#7 of 51 TypeScript repos

Use deepseek-ai/dsh-superagent-prototype in your agent

Point Claude Code, Cursor, Codex or VS Code at this repository. Your agent gets the index this page is built from: cited answers, callers, history and health for any file.

  1. 1.In Claude, open Customize → Connectors, click +, then Add custom connector. On a Team or Enterprise plan an owner adds it first under Organization settings → Connectors.
  2. 2.Paste the server URL below as the Remote MCP server URL, then click Add.
  3. 3.Click Connect. A Repowise sign-in window opens. Approve access.
  4. 4.Repowise's tools are now available in your Claude chats.

Connect with one click. Sign in with Repowise (OAuth), no API key to copy. Works in Claude on the web, desktop, and mobile.

Docs
bash
https://api.repowise.dev/mcp/deepseek-ai/dsh-superagent-prototype
Editors need an API key: sign in to create one.Sign in to connect

This repo is public, so anyone with a Repowise account and an API key can connect.

Try asking

  • get_overview()
  • get_answer("how is dsh-superagent-prototype put together?")
  • get_why("why is dsh-superagent-prototype structured this way?")

Explore dsh-superagent-prototype

Key features of dsh-superagent-prototype

  • Listens to GitHub and, optionally, Feishu for requests.
  • Opens a work item when an allowed person asks for work and carries it out in its own agent session and directory.
  • Replies in the original conversation, for example with a pull request.
  • Provides a web panel that shows what needs a person.
  • Acts only when asked or when a rule the team wrote allows it, and speaks only when someone must act or can use a result.

How deepseek-ai/dsh-superagent-prototype works

Requests enter through GitHub and, optionally, Feishu, and the entry points are src/index.ts and src/app/tools/main.ts. Each allowed request becomes a work item that the agent processes in its own session and working directory. The src directory holds 110 files and the tests directory holds 59 files. docs/001-domain.md covers the domain model, and docs/000-philosophy.md explains the principle that the agent acts only when asked or when a team rule allows it. src/client/app.tsx is the entry point for the web panel, which shows what needs a person. SETUP.md is the guide an agent follows to set the system up with a person.

The codebase has 206 files and 1,784 symbols in 4 modules, led by TypeScript and Python. Code health is 8.7 out of 10, rated excellent.

deepseek-ai/dsh-superagent-prototype FAQ

What is dsh-superagent-prototype?

dsh-superagent-prototype is a proactive coding agent for one GitHub repository, packaged as a bundle for DeepSeek Harness. It is a research prototype and not an official DeepSeek product, so review it before using it.

How does dsh-superagent-prototype work?

dsh-superagent-prototype listens to GitHub and optionally Feishu for requests. When an allowed person asks for work, it opens a work item and replies in the original conversation, for example with a pull request.

What language is dsh-superagent-prototype written in?

dsh-superagent-prototype is written in TypeScript, with one Python file also in the repository.

How is the dsh-superagent-prototype code organized?

Its code lives in src, which has 110 files, and its tests live in tests, which has 59 files. Entry points are in src/index.ts, src/app/tools/main.ts and src/client/app.tsx.

When should I use dsh-superagent-prototype?

Use dsh-superagent-prototype when a team wants an agent to act on one GitHub repository only when someone allowed asks for work, or when a rule the team wrote allows it.

What license does dsh-superagent-prototype use?

dsh-superagent-prototype uses the MIT license.

The summary, features and answers on this page are written by a model from the README and the source, and refreshed with each index.

About this page

Get a page like this for your own codebase

Repowise built this map of deepseek-ai/dsh-superagent-prototype from its source and git history. It parses every symbol, draws the dependency graph, scores each file's health from complexity, duplication, coverage and churn, finds hotspots and owners in the history, and writes documentation for every module. Your coding agent reads the same index over MCP, so its answers cite real files.

Index your repo freeSee how Repowise worksFree for 2 public repos, with a page like this one.

Prefer local? pip install repowise && repowise init indexes your own checkout, no account needed.