v10.44 — Now Available

MCP Memory Service

Persistent memory for AI agents. Semantic search, knowledge graph, automatic consolidation — now accessible from Claude.ai via Streamable HTTP.

GitHub PyPI Package

What's New in v10.44

Mistake Notes — structured error replay: agents record mistake patterns and retrieve them before similar tasks. Backend-agnostic, auto-deduplicating. ~1,737 tests.

Mistake Notes

Two new MCP tools — mistake_note_add and mistake_note_search — let agents record error patterns and retrieve them before similar tasks. Implements the structured error replay pattern from Mistake Notebook Learning. (PR #786, @filhocf)

Auto-Deduplication

When a similar mistake pattern already exists (similarity ≥ MCP_MISTAKE_NOTE_DEDUP_THRESHOLD, default 0.85), mistake_note_add increments failure_count in metadata instead of creating a duplicate. Clean, append-free history.

📊

Backend-Agnostic

Reuses the existing memory store with memory_type='mistake'. No new tables, no schema migrations — works on all backends: SQLite-vec, Cloudflare, Hybrid, and Milvus. Ontology updated: mistake registered as subtype of error.

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

Get Started in Seconds

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

Click to copy pip install mcp-memory-service