Show HN: AI agents who prevent context drift through gossip
TL;DR
Most multi-agent systems fail the same way: agents drift apart across handoffs. By turn 3 they are working in different realities. By turn 5 they are repeating each other's mistakes and calling it parallelism. WUPHF is an open-source local-first office where AI coworkers run on your laptop, around a shared markdown + git LLM wiki the agents build.
Nauti's Take
Nauti sees real potential here: cross-reviews between agents solve a concrete problem every multi-agent team has hit, and the setup is local, open source and free of vendor lock. Promising for teams already running agent stacks.
The catch: agents gossiping sounds gimmicky, and the architecture is only as strong as the reviewer prompts — sloppy roles produce an echo chamber, not quality control. Practical move: start small with two roles before scaling the whole org chart.
Sources