Agent Memory

Agent memory MCP server with provenance tracking, decay-weighted recall, and feedback loops.

Persistent memory for AI agents — history, context, semantic search, queues. 17 tools, stdio/SSE.

Janus concierge: ask about, price, check, and request a private Kinematic Drive over MCP.

MCP server exposing Polypack as persistent adaptive memory

Memory for AI agents — MLX (Apple Silicon) or CPU (Linux), sqlite-vec + BM25, zero cloud.

Heartwood Memory — governed AI agent memory; signed provenance. BUSL-1.1; not OSI open source.

Durable project-memory MCP: decisions, constraints, and pipelines across Claude sessions.

Knowledge-lifecycle MCP: turn agent work into memory, recall it across projects, promote to org.

Local-first governed MCP memory backend for coding agents.

Persistent memory layer for AI agents. Sub-100ms recall, semantic search, knowledge graphs.

Persistent memory for AI agents and humans. Store, search, and discover patterns.

SQLite-backed MCP server for persistent memory, full-text retrieval, and graph traversal.

Memory, docs, and repo context layer for engineering agents.

Long-term memory for AI agents: local-first PKM with provenance and hybrid search.

Working memory for AI agents: digest-indexed episodes on a git shelf, recalled a section at a time.

Local personal memory for agents as MCP tools — remember, recall, search, context, graph traversal.

Recall locally stored agent memories through an MCP-compatible host.

Behavioral memory layer for AI tools. Learns preferences and context across Claude, Cursor, Codex.

Git-backed long-term memory authority for AI agents via MCP.

Self-hosted long-term memory for AI agents over MCP — hierarchical recall backed by pgvector