mcp-memory-service v10.64 — 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.

GitHub PyPI Package

What's New in v10.64

Incremental memory consolidation for session Stop hooks + quality trends endpoint fix. ~1,828 tests.

Incremental Consolidation

New time_horizon="incremental" for memory_consolidate processes only memories created since the last run. DB-based atomic lock prevents concurrent runs across processes; 10-second timeout makes it safe to invoke from session Stop hooks. Bootstraps with a 24-hour window on first run, then advances a cursor. (@filhocf, PR #985)

📈

Quality Trends Endpoint Fixed

The GET /api/quality/trends endpoint returned a 500 error on every storage backend due to two stacked AttributeError bugs. Both are resolved — the endpoint now uses the correct storage interface and returns accurate trend data. (PR #982, reported by @TonbiLX)

📄

Contradiction Resolution Docs

New research document docs/research/contradiction-resolution-approaches.md — a system-neutral comparison of invalidation models, detection mechanisms, and a decision guide for RFC #732. Contributed by @rudi193-cmd / Sean Campbell (PR #984).

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