MCP server enabling persistent memory for Claude through a local knowledge graph - fork focused on local development
-
Updated
Dec 22, 2025 - JavaScript
MCP server enabling persistent memory for Claude through a local knowledge graph - fork focused on local development
SQLite-backed MCP Memory Server with WAL concurrent safety, FTS5 search, session tracking, task management, and cross-machine bridge sync
Model Context Protocol (MCP) server that provides persistent memory capabilities for AI assistants. It allows AI models to save, retrieve, and manage scoped context across different sessions and projects safely on your local machine.
SQLite-based MCP memory server with WAL mode for concurrent access. Drop-in replacement for @modelcontextprotocol/server-memory
dk — CLI for Dakera self-hosted AI agent memory. Manage memories, namespaces, vectors, knowledge graphs, and sessions.
Go SDK for Dakera AI agent memory — self-hosted, vectors, hybrid search, knowledge graphs, and sessions.
Python SDK for hierarchical memory management in Graphiti, featuring chainable scope isolation and multi-level context retrieval.
Tiny portable memory format for agents: JSONL plus markdown plus MCP examples
Agentic AI + RAG (Retrieval-Augmented Generation) chatbot built with LangGraph, LangChain, Google Gemini, and FAISS.
Semantic memory server for Claude AI with OpenAI embeddings and PostgreSQL pgvector. Deploy on Vercel Edge Functions with zero infrastructure.
A self-hosted MCP server + web UI for storing memories, snippets, and agent configurations persistently across Claude Code sessions.
Python SDK for Dakera AI agent memory — self-hosted, 87.8% LoCoMo. Vectors, hybrid search, knowledge graphs, sessions.
Local-first persistent memory for AI agents — semantic search, smart deduplication, importance decay, and multi-agent isolation. Stores everything as Markdown. No cloud, no API keys, no database.
TypeScript/JavaScript SDK for Dakera AI agent memory — self-hosted, vectors, hybrid search, knowledge graphs, sessions.
Self-hosted Dakera AI memory server — Docker Compose, Kubernetes, Helm, HA cluster setup, and monitoring.
Rust SDK for Dakera AI agent memory — HTTP and gRPC transports, vectors, hybrid search, knowledge graphs, sessions.
Add a description, image, and links to the memory-server topic page so that developers can more easily learn about it.
To associate your repository with the memory-server topic, visit your repo's landing page and select "manage topics."