Drop-in, MCP-native working memory for AI agents: gameplans, phases, a dependency graph, and post-hoc cascade — over plain markdown.
Memory you can verify — a trust layer between an AI coding agent and its own past: per-hit staleness verdicts, claim-level use attribution, measured effectiveness, episodic run-state. MCP-native, local-first, MIT, no cloud.
graph8 MCP server - GTM operations for AI agents
MCP server for swafra — Leiden-chunked, graph-linked semantic memory for Claude AI and ChatGPT
A universal interface for AI agents with persistent memory, where every conversation has a home
