Agent Memory

Provenance-aware memory for AI agents: quarantine, abstention gate, supersession-with-history.

Local-first semantic memory for MCP agents. Recall, remember, forget, echo, drift, stats over stdio.

Memory for AI agents that tracks beliefs over time and surfaces contradictions

Convert, validate, and inspect AI agent memories across formats

Local-first, source-traceable agent memory — no LLM at ingest, fully offline

Temporal memory MCP server with LanceDB vector search, weight-decay scoring, and LLM consolidation

Team engineering memory for AI coding assistants. 47 MCP tools, pgvector semantic search.

Persistent memory for AI agents: Markdown entries, hybrid search, typed graph links

Cognitive memory for AI agents — semantic search, Hebbian learning, knowledge graphs.

Intelligent agent memory with automatic extraction, consolidation, and bi-temporal recall.

Event-sourced, auditable agent memory over MCP: cited checkout, replayable provenance.

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

Persistent memory tools for Claude Desktop. Search your vault or Obsidian notes mid-conversation.

Local-first memory system for AI agents with hybrid search and graph reasoning

A lightweight, structured, token-efficient local-first MCP memory server

Persistent memory for AI agents. Store context, retrieve it semantically.

Live context MCP server: resolves git, services, and tests into agent context. Local-first, MIT.

Persistent memory for AI agents. 36+ MCP tools: encryption, decay, hybrid search, knowledge graph.

RAG memory for LLM agents over Garnet Vector Sets: store text as embeddings, recall by meaning.

Corrections that outlive the session. A guard blocks the edit that writes the old value back.