Agent Memory

Self-hosted remote MCP memory server for ChatGPT and AI agents.

Shared workspace your AI agent writes to. 184 tools, persistent memory, semantic search.

Local-first durable AI memory with policy-bound recall and a typed project graph.

Two-tier memory: hot cache (0ms) + semantic search. Self-organizing.

Catches when your project drifts from its own decisions. Local-first cross-agent memory MCP.

Universal persistent memory and knowledge retrieval layer for AI agents and LLMs.

Review gate for shared agent memory: an unreviewed or hand-edited memory is never served.

Persistent cross-project memory for Cursor and Claude Code using local semantic search.

Cooperative persistent memory for LLMs: episodes, memories and traits over SQLite (FTS5, Hebbian)

Recall, check, search, timeline, and graph tools for fiction writers via Seizn Memory v3.

Deterministic, token-minimal agent memory: multi-hop [[wikilink]] recall with no LLM in the loop.

Cross-session memory for Claude over MCP — prioritised briefs, supersession, cross-project recall.

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

Local semantic code search with Git history. Works offline, no API key needed.

Bi-temporal, provenance-carrying long-term memory for AI agents, in one SQLite file.

Persistent, governed local memory for MCP-compatible AI clients.

Long-term memory for Claude Code with SQLite FTS5 search and BM25 ranking

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.