WUPHF is a collaborative office of AI employees who build and maintain their own knowledge base to never lose context for the tasks you give them. Supports Claude Code, Codex, OpenClaw agents and local LLMs via OpenCode. Chat with your agents via TUI, Web or Telegram. Open source. Runs on your machine, with your keys.
No reviews yetBe the first to leave a review for WUPHF by Nex.ai
Love the concept of using a shared markdown wiki for agents instead of just standard vector memory. The promotion flow from an agent's private notebook to the team wiki is a brilliant way to prevent context poisoning. Curious if you've run into issues with agents accidentally overwriting each other's documentation during concurrent tasks?
Each AI agent builds and maintains its own skills and context, how is conflict handled when two agents develop different interpretations of the same playbook?
Love the concept of using a shared markdown wiki for agents instead of just standard vector memory. The promotion flow from an agent's private notebook to the team wiki is a brilliant way to prevent context poisoning. Curious if you've run into issues with agents accidentally overwriting each other's documentation during concurrent tasks?
Mailwarm
Each AI agent builds and maintains its own skills and context, how is conflict handled when two agents develop different interpretations of the same playbook?