WUPHF — AI employees with a shared brain

Overview

A collaborative office of AI employees who build and maintain their own knowledge base to never lose context for the tasks you give them.

Free and open source. Runs local. No account, no cloud, no per-seat pricing. MIT licensed.

WUPHF runs a small AI office on your machine. Self-evolving agents execute based on how you work. You set the goal. They handle the handoffs.

Key Features

• Drop a goal in a channel.Walk away. Come back to a team that moved the work.
• AI employees with a shared brain
• Agents with roles,not prompts with costumes.
• You type one sentence.They handle the handoffs.
• Stop being the routing layerbetween your own agents.
• Questions the last five skeptics asked.Answered honestly.
• Watch the demo ↓
• Each agent gets its own notebook. The team shares a wiki. When a conclusion in an agent's notebook holds up, it gets promoted to the wiki so the whole office benefits. Built-in markdown wiki, file-over-app, lives as a local git repo. No API key, no hosted backend.
• Mix Claude Code, Codex, Hermes Agent, OpenClaw bridged agents, and OpenClaw Gateway HTTP agents in one channel. They execute your work 24x7.
• Local. Runs on your machine. No cloud in the critical path.
• 7x fewer tokens per session. Fresh sessions, not accumulated context.
• Free and open source. MIT licensed. No seats, no usage fees.

Details

Each agent is a JSON file: a system prompt plus a tool list. Read it. Edit it. Fork it. The coordination between agents is the product. The individual agents are the configs you already know how to change.

Real thread from a founding-team run. You drop the goal. The CEO routes it. ENG declares a dependency, which is what a real engineer does. Then you close the tab.

You did not type anything. You were making coffee. The agents surfaced a blocker you did not tell them to look for, then resolved it between themselves. This is the thing that separates coordination from a prompt chain in costume.