Work

• Running

  Multi-agent system with independent audit

  A team of AI agents with split roles, where one agent routes the work and a separate auditor checks it.

• Running

  Memory that survives the session

  One shared, locally hosted memory store, connected to four AI tools and fed from my own notes by a local model.

• Ongoing

  Keeping an AI system honest

  Catching stale facts, false "fixed" claims and over-engineering in an AI agent system, with counts that can be checked.