Enables teams of AI coding agents (Claude Code, Cursor, Codex) to share persistent, time-aware graph memory and coordinate their work via MCP, so agents recall verified fixes at the moment of failure, learn procedures automatically, avoid file conflicts, claim tasks race-free, and hand off facts and decisions between sessions.
Enables coding agents to read and write team-shared, versioned project memory — atomic claims, numbered ADRs, and long-form docs — over MCP, with a budgeted session-start digest and hybrid search that keep token use low. Agents can also draw on an org-wide shared space written by humans through a web UI.
Local-first, source-traceable memory for AI agents — no LLM at ingest, $0 per message, zero data egress. Gives Claude Code, Cursor, and any MCP client one shared persistent memory with semantic recall, belief revision, selective forgetting, and a provenance guard that blocks acting on stale or unconfirmed memories.
Enables AI apps like Claude, ChatGPT, Copilot, Claude Code and Codex to read and write a shared company wiki over MCP, where meetings, work sessions and notes become living pages about people, projects and decisions. It also serves search, briefs, transcripts, decisions and action items, and lets teams connect their own git-hosted team wiki.
Gives any MCP client (Claude, ChatGPT, Cursor, and others) one shared knowledge-graph memory where agents record decisions, problems, and approaches together with their reasoning, then retrieve them by meaning rather than keyword. Spreading activation pulls in linked context and decay lets unused knowledge fade without deleting it.