mcp-memory-service v11.13 — Now Available

Memory for AI Agents

Persistent memory for AI agents — REST API, MCP, OAuth, CLI, dashboard. Semantic search, knowledge graph, automatic consolidation. One self-hosted service, every transport.

Try the Live Demo GitHub PyPI Package

Interactive 3D knowledge graph — every memory a glowing node, every relationship a curved edge.

What's New in v11.13

MINOR release: 19 merged pull requests, most of them from outside the maintainer. Harvested memories now record where they came from, and three storage bugs that only surface at real sizes are closed. ~3,360 tests.

🔍

Harvested Memories Carry Their Provenance

An insight now records how it was produced: a harvest:method:llm or harvest:method:heuristic tag, plus the model, the pipeline version and the session id in metadata, on the store path and the evolve path alike. verify_session_coverage builds on it — before you delete a source transcript, it re-harvests the file in memory, compares each insight against what is stored, and answers safe_to_delete with the ones it could not find. (#1243, #1252)

🧰

Three Storage Bugs That Pass at Small Sizes

Tag-filtered retrieval on Cloudflare borrowed the sqlite-vec KNN ceiling for topK, so any request above 16 results hit Vectorize's metadata cap and raised a 4xx instead of returning. Hybrid pull sync compared counts rather than diffing hashes, so two divergent stores of equal size were reported in sync. And get_by_hash still returned soft-deleted rows on Milvus and Cloudflare, so a re-store saw a tombstone as a live duplicate. (#1259, #1255, #1262)

🌐

Silent Failures Made Audible

The NLI cascade reuses the harvest provider chain, skips the request entirely when no provider is configured, and emits one bounded warning per run instead of degrading to the heuristic without a word. Configuration got the same treatment: an unrecognized path variable such as MCP_MEMORY_DB_PATH was ignored in silence while the database landed on the default path, and now warns once, naming the variable it saw and the one it wanted. (#1265, #1253)

How It Works

Claude.ai connects to your memory server through Streamable HTTP with OAuth 2.1 authentication.

Browser
Claude.ai
Transport
Streamable HTTP
Auth
OAuth 2.1 + PKCE
Server
MCP Memory
Storage
Knowledge Graph
Data flow Auth boundary

Built for Production

Battle-tested with comprehensive testing and optimized for performance.

0
Tests
0
AI Apps Supported
0
Read Latency
0
Cache Speedup

In the Media

Talks and coverage from the community.

Get Started in Seconds

Install from PyPI and connect your AI agents to persistent memory.

Click to copy pip install mcp-memory-service

Deploying for a team?

I help teams run self-hosted memory in production — OAuth, hybrid sync, multi-client rollout. Free 30-minute intro call.

Get in touch