Building an Adversarial Knowledge Base for AI Agents
Every time an AI agent touches your infrastructure, it starts from scratch. It reads files, searches repos, follows reference chains, and then the next agent does it all over again. The operational knowledge evaporates between sessions, leaving no shared understanding. We built @twonines/fact-store to fix that. It captures observation as typed, versioned, queryable data. Agents observe systems, record what they find with cited evidence, and the store makes those observations durable and searchable for every agent that follows. ...