Knowledge & Memory

Local long-term memory MCP server (SQLite) for AI coding agents — OpenCode, Claude Code, Cursor

Shared memory and delegation for Codex, Cursor, Claude Code, and OpenCode.

Self-correcting agent memory: recall, supersede, revert, forget, GDPR erasure, audit receipts.

Token-efficient code review knowledge graph: semantic search and call-graph resolution.

Shortest paths, topological order and connected components for directed or undirected graphs

Recognition-first cross-agent memory federation. One shared memory across all your agents.

Local-first persistent memory for AI coding agents - 96.0% R@5 on LongMemEval, zero LLM calls.

Persistent memory for AI agents: connects MCP clients to your Kemory memory vault

Watch RAM and disk on your Windows PC. Cleanup tools return plans only.

The Customer Graph core: one register of the people an account serves, with provenance on every

Persistent knowledge graph: entities, relations, and observations for agents.

Recall campaigns, witnessed: NHTSA's as-served record sealed night by night.

Optional diagnostics MCP server for OpenReflex's ambient project muscle memory.

Remote MCP server (Streamable HTTP, OAuth 2.1) for engineering teams that use AI coding agents: start and monitor delivery workflows, run AI code review on an exact pull-request revision, list findings and record verdicts, query the repository knowledge graph and manage the backlog.

Persistent memory for AI agents — local JSON, zero config, no server required.

Local-first, cloud-friendly memory — 100+ tools, 99.2% LongMemEval-S retrieval@8, hybrid search.

Self-hosted operating layer for AI agents: knowledge, continuity, coordination, and governance.

Local persistent memory for AI agents with recall, search, forgetting, and encrypted storage.

Private on-device memory & retrieval for AI assistants — offline vector + lexical search.

Shared, serverless, conflict-free knowledge-graph memory for AI agents