multi-agent

zhikuncode: Self‑hosted multi‑agent coding AI for teams

Name: zhikuncode: Self‑hosted multi‑agent coding AI for teams
Author: zhikunqingtao

Deploy zhikuncode on your server and let any browser—desktop or mobile—run AI‑assisted coding with CLI and web UI, secure sandboxing, and native Chinese LLMs.

From the repo · “Claude Code / Cursor 开源替代。部署在你自己的服务器上，团队用浏览器打开就能编程——包括手机。CLI & Web UI 双入口，Multi-Agent 协作，原生直连千问/DeepSeek 等国产大模型。SWE-bench Lite 56%，不是玩具。技能/插件/跨会话记忆，8 层安全沙箱，数据不离开你的机器。Docker 一键部署，MIT 开源，零锁定。”

528 stars+7★ this week142 forksJavaGuide quality 8/10 · reviewed Oct 21Updated 10/19/2026100% free · open source

What it does

Zhikuncode is an open-source alternative to Claude Code/Cursor that allows teams to program collaboratively through a web browser or CLI, with support for multi-agent collaboration and native connection to large models like Thousand Questions and DeepSeek.

When to use it

•When you need a self-hosted, open-source coding platform for your team to collaborate on projects
•When you want to utilize large models like Thousand Questions and DeepSeek for your coding tasks
•When you require a high level of security and data control, with an 8-layer security sandbox and data that never leaves your machine

Ready-to-paste prompt

docker run -d -p 8080:8080 zhikunqingtao/zhikuncode && docker exec -it <container_id> bash -c 'zhikuncode init myproject && zhikuncode add thousand-questions'

Heads up: Make sure you have Docker installed and running on your system before attempting to install and run Zhikuncode, as it relies on Docker for deployment and execution

Saves to your device

Use with Claude

New

Skip the builder — one click puts this in Claude, Cursor, Antigravity and more.

✅ Light setup

Installs with a command or two; your AI agent can do it for you.

Try it instantly — no install

Claude Code

mkdir -p ~/.claude/skills/zhikuncode && curl -fsSL https://workflowstacks.com/api/skills/zhikuncode/claude-skill -o ~/.claude/skills/zhikuncode/SKILL.md

Open in another AI app

Opens the app with this repo with the prompt ready to go — no copy-paste needed.

Connect the whole catalog (MCP)

claude mcp add --transport http workflowstacks https://workflowstacks.com/api/mcp

Adds a WorkflowStacks connector to Claude Code: search and load any skill here by chatting.

What's inside — free to inspect

No purchase needed

Read the entire source before you build — unlike paid marketplaces that hide it behind a buy button.

top-level files

folders

502.4M

source size

MIT

license

Key files

.editorconfig

README.md

File tree

.github/

.zhikun/

backend/

configuration/

docs/

frontend/

python-service/

scripts/

tools/

workspace/

.dockerignore

.editorconfig

.env.example

.gitattributes

.gitignore

.nvmrc

CHANGELOG.md

CODE_OF_CONDUCT.md

CONTRIBUTING.md

docker-compose.yml

docker-entrypoint.sh

Dockerfile

LICENSE

README.md

Use with Claude

New

Skip the builder — one click puts this in Claude, Cursor, Antigravity and more.

✅ Light setup

Installs with a command or two; your AI agent can do it for you.

Try it instantly — no install

Claude Code

mkdir -p ~/.claude/skills/zhikuncode && curl -fsSL https://workflowstacks.com/api/skills/zhikuncode/claude-skill -o ~/.claude/skills/zhikuncode/SKILL.md

Open in another AI app

Opens the app with this repo with the prompt ready to go — no copy-paste needed.

Connect the whole catalog (MCP)

claude mcp add --transport http workflowstacks https://workflowstacks.com/api/mcp

Adds a WorkflowStacks connector to Claude Code: search and load any skill here by chatting.

Quick Actions

Details

Creator

zhikunqingtao

Language

Java