Several AI agents claim tasks, write code, leave evidence, merge and release in parallel; the server enforces the rules, and people step in only to scope work, approve gates and accept results.
In short
KungFuTea is a self-hosted delivery platform for AI coding agents, built by YGG. Claude Code, Codex and other agents connect over HTTP MCP to claim tasks in parallel, write code, file verification evidence, merge under a project lock and release. State transitions, single ownership, gates and evidence are enforced by the server, and people step in only to scope tasks, approve gates and accept results item by item. A perpetual licence costs ¥76,000, on-premise deployment included.
What the agent takes off people's plates
Agents call next_task to claim work. The claim happens inside one database transaction, so a task has exactly one holder at any moment. Each task runs in its own git worktree workspace and renews its lease with a heartbeat; if a slot drops out, another slot takes the task over instead of leaving it stuck halfway.
DB transaction · single lease · takeover
Task states can only move along defined paths; an illegal transition is rejected with a reason, and every write checks the token, session and workspace. The rules live on the server, not in a prompt — an agent that forgets them or tries to skip them still cannot get through.
State machine · holder check · idempotency keys
Protected paths and a per-change file limit live in the project configuration; hitting either stops the task until a person approves it, and gate approvals can only come from people. Production releases are human-only by default, while test environments can be opened to automatic releases by agents.
Protected paths · file limit · production switch
Before submitting, a task needs a passing verification record from the current round — commit, command, scope and result, all four filled in — plus a local screenshot for page tasks. Merges happen one at a time under the project merge lock, and releases are checked against a list first.
Verification record · merge lock · release checklist
Agents connect over HTTP MCP: Claude Code, Codex, Claude Desktop, the YGGLab desktop app and any other agent that speaks HTTP MCP use the same tools to claim tasks, write records and take the merge lock. One token maps to one slot, and one slot can work on several tasks at once in separate workspaces.
HTTP MCP · one token per slot
A single Linux server with Docker Compose and PostgreSQL is enough; no Redis is needed. The platform does not proxy model calls and does not collect source code or full conversations — it hands out tasks, never commands. Every state change is written to an event log, and tokens, passwords and private keys never appear in the logs.
Self-hosted · no model proxying
Workflow
Side by side
| Aspect | KungFuTea | Single AI coding assistant | Task board + manual assignment |
|---|---|---|---|
| Several agents in parallel | Atomic claims and separate workspaces; one holder per task | One thread per session; multiple windows need a person to coordinate | People assign work and spot conflicts by hand |
| Where rules are enforced | On the server: state machine, holder checks, gates | In prompts and habits, which a model may ignore | In process documents, relying on discipline |
| Evidence before merging | A passing verification record from this round is required (commit, command, scope, result) | Depends on whether tests were run in the conversation | Depends on whether a reviewer checked |
| Where people step in | Three points: scoping, gate approvals, item-by-item acceptance | Every step needs watching | Assignment, follow-up and acceptance all by people |
| Deployment | Platform self-hosted; agents still call their own model vendors | No platform layer; the assistant calls its model vendor directly | SaaS or self-built board, independent of AI |
Quantified before / after
How the agent and human supervision collaborate
human
Project owner (scoping · gate approvals · acceptance)
source
KungFuTea server (state machine · leases · gates · merge lock · event log)
agent
AI agent slots (Claude Code / Codex etc., via HTTP MCP)
output
Repository and environments (workspaces · merges · releases)
Flow
Verifiable facts
In the six-step delivery flow, people act only at scoping, gate approval and item-by-item acceptance; agents do the rest
Deployment needs only one Linux server, Docker Compose and PostgreSQL 16 or later, with no Redis dependency
The platform does not proxy model calls or collect source code and full conversations; it hands out tasks, not commands
Maintenance tasks for this website (YGG’s official site) are already dispatched, claimed, verified and merged through KungFuTea
Delivery and pricing
Included
Provided by the client
Add-ons

Scan for the proposal and a demo account
Scan with WeChat to reach the solution lead and request the complete documentation and deployment checklist.
Demo accounts are not handed out publicly: scan the code to reach us on WeChat, tell us what you need, and we will set one up for you.
Where it fits
Further reading
YggLab AI Agent Desktop
One desktop where 20+ CLI agents actually collaborate — assign work solo, form a team, or command them from your phone while work keeps moving 24/7.
ServerManager
Agentless infrastructure management for servers and network devices, with a built-in AI copilot
DataWeaver
Five specialized agents cut cross-database natural-language queries from 2–3 days to 10 seconds.