One governed graph for AI agents — GraphQL + MCP over your databases, files, APIs, and code

SkillsVote: Lifecycle Governance of Agent Skills from Collection, Recommendation to Evolution

📚 Two books on harness engineering — the design philosophies behind Claude Code & Codex: constraints, query loops, context governance, multi-agent verification. harness-books.agentway.dev

Local-first, evidence-controlled academic writing workflows for AI agents, with bounded revision, clean-room review, and release governance.

Shared, persistent memory for AI agents. Self-hosted MCP server with semantic search, vector RAG, and live updates. Works with Claude, Cursor, Codex, and any MCP client.