Every AI tool I used forgot everything the second a session ended. So I built Willder: one shared memory graph that a team works through together, with real access control gating every read and write. Each person can run multiple customizable AI agents on top of it. Agents can coordinate through the graph without sharing a conversation. Nothing an agent drafts ships without your approval. Built solo. Would love your feedback, happy to talk through the architecture or the access-control model.

Hey Product Hunt 👋 I’m Tri and I built Willder solo, with no team and no funding. I often running past the API credit limits, and have to explain the AI with each new session, while there are no tools that can be easily set up to solve this problem. I also kept running into businesses struggling with access control for their documents and business context. That's my inspiration behind Willder: persistent memory + precise access control + agent and team coordination. I'll happily to go through the architecture, why I built the memory graph this way, or what broke along the way. I’d genuinely love your feedback, especially if you’ve tried other agent or memory tools and hit walls with them.

Willder

AI agents coordinate. People collaborate. One memory.

AI agents coordinate. People collaborate. One memory.