PsChina/deepseek-as-subagent

README preview

# deepseek-as-subagent

**English** · [简体中文](README.zh-CN.md)

[![Python](https://img.shields.io/badge/python-3.10--3.12-blue.svg)](https://www.python.org/)
[![License: MIT](https://img.shields.io/badge/license-MIT-green.svg)](LICENSE)
[![GitHub stars](https://img.shields.io/github/stars/PsChina/deepseek-as-subagent?style=social)](https://github.com/PsChina/deepseek-as-subagent)
[![Glama MCP server](https://glama.ai/mcp/servers/PsChina/deepseek-as-subagent/badges/score.svg)](https://glama.ai/mcp/servers/PsChina/deepseek-as-subagent)
[![MCP](https://img.shields.io/badge/protocol-MCP-purple)](https://modelcontextprotocol.io/)
[![Mentioned in Awesome MCP Servers](https://awesome.re/mentioned-badge.svg)](https://github.com/punkpeye/awesome-mcp-servers)
[![Platforms](https://img.shields.io/badge/platforms-macOS%20%7C%20Linux%20%7C%20Windows-lightgrey)](https://github.com/PsChina/deepseek-as-subagent)

> Run DeepSeek as a **real sub-agent** inside Claude Code / Codex CLI — not just an LLM endpoint.
> The host agent keeps the main conversation, planning, judgment, and verification.
> DeepSeek gets its own agent loop for execution-heavy work.
> Coding APIs use workspace-scoped writes and bounded trusted-host Bash; separate read-only APIs provide pure file analysis without command execution.

### Full coding delegation

```text

View full repository on GitHub →