SQLite-backed MCP Memory Server with WAL concurrent safety, FTS5 search, session tracking, task management, and cross-machine bridge sync
-
Updated
Oct 17, 2026 - Python
SQLite-backed MCP Memory Server with WAL concurrent safety, FTS5 search, session tracking, task management, and cross-machine bridge sync
Python SDK for Dakera AI agent memory — self-hosted, 88.2% LoCoMo. Vectors, hybrid search, knowledge graphs, sessions.
Python SDK for hierarchical memory management in Graphiti, featuring chainable scope isolation and multi-level context retrieval.
LlamaIndex integration for Dakera AI memory — dakera.ai
AutoGen integration for Dakera AI memory — dakera.ai
Semantic search over Claude Code session transcripts. Recovers information lost to context compression.
CrewAI integration for Dakera AI memory — dakera.ai
LangChain integration for Dakera AI memory — dakera.ai
Agentic AI + RAG (Retrieval-Augmented Generation) chatbot built with LangGraph, LangChain, Google Gemini, and FAISS.
MCP server that gives AI agents a persistent memory: hybrid vector + full-text retrieval and a knowledge graph, backed by PostgreSQL (pgvector + Apache AGE).
Eidetic — a single-process, single-database memory server for AI agents. SQLite-native: vectors + FTS5 + knowledge graph + raw logs. Five-layer memory (L0 raw → L1–L4), three-tier recall, auto-healing. One-command deploy, local-first, works with any MCP-compatible agent (OpenClaw, Claude Code, etc.).
To associate your repository with the memory-server topic, visit your repo's landing page and select "manage topics."