Agent Memory

Fully local memory for AI agents: zero-LLM ingest, semantic recall, air-gapped, auditable.

Compresses AI chat sessions into a typed knowledge graph. Local/offline via Ollama.

Durable agentic memory, encrypted at rest. Fully offline: no network, no API key, no cloud.

Cross-session memory for Claude Code — context capture, semantic search, recall

Local-first persistent memory for coding agents and MCP clients.

Persistent, encrypted, deterministic memory for AI agents. Local-first, 173 canonical tools.

Hierarchical markdown memory palace for AI agents — structured palace navigation via MCP tools.

AI that remembers. Local-first cross-session, cross-project long-term memory for coding tools.

Persistent memory for AI assistants with semantic search and knowledge graph relationships.

One shared, persistent memory across AI agents and systems, with semantic recall and live updates.

Local-first AI memory layer with hybrid search. Postgres + pgvector. Self-hosted, MIT.

Memori MCP server — persistent AI memory with recall and augmentation tools

Persistent, agent-owned memory with encrypted storage and shared knowledge commons.

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

Local-first personal memory and model server for trusted MCP agents on macOS.

Graph-based memory system for LLMs with knowledge graphs and semantic search.

Universal MCP Server with advanced AI memory capabilities and semantic search.

Shared, cited knowledge-graph memory for agents — ask, search, remember, keep standing instructions

Local-first MCP memory server for persistent LLM knowledge with BM25 retrieval.

Offline persistent memory for AI coding agents — 35 tools, 80% fewer calls, no LLM