MemPalace/mempalace
MemPalace is an open-source, local-first AI memory system that stores and retrieves conversation history verbatim using semantic search, supporting pluggable backends like ChromaDB and integrating ...
Awesome MCP › Knowledge & Memory
orneryd/Mimir
Mimir (Multi-agent Intelligent Memory and Insight Repository) is a Model Context Protocol server that gives AI assistants a persistent store for tasks, context and the relationships between them. Instead of losing state between conversations, an agent writes into a Neo4j graph database where nodes and edges accumulate over time, and reads back relevant context through semantic search over embeddings. The project ships as a Docker Compose stack: Neo4j, the MCP server and a web UI start with a single npm run start command that detects the host platform and selects the matching compose file. The only required configuration is HOST_WORKSPACE_ROOT, which mounts a source directory into the container so folders can be indexed for retrieval-augmented generation; indexing is per folder and requires an explicit action from the user, and the mount can be made read-only. Additional environment variables select the LLM provider (OpenAI-compatible endpoints such as the GitHub Copilot API, or local Ollama and llama.cpp), the default model, and the embeddings model, endpoint, dimensions and chunk size. The web UI on port 9042 exposes a portal for navigation and file indexing, a beta visual workflow builder called Orchestration Studio, a REST MCP endpoint at /mcp, and OpenAI-compatible chat and embeddings endpoints; Neo4j Browser runs separately on port 7474. Helper npm scripts cover start, stop, restart, logs, status and a no-cache rebuild. An official VS Code extension is published to the marketplace, and the documentation covers VS Code, Cursor and Windsurf integration plus a dev container setup, along with a PCTX Code Mode integration aimed at reducing token use. Prerequisites are Docker Desktop, Node.js 18 or newer, and Git. It targets developers on long-running projects and multi-agent workflows where context must survive across sessions.
https://github.com/orneryd/Mimir
Also in Knowledge & Memory
siyuan-note/siyuan
SiYuan is a privacy-first, self-hosted personal knowledge management system featuring block-level referencing, Markdown WYSIWYG editing, and support for the Model Context Protocol (MCP).
topoteretes/cognee
Cognee is an open-source project that provides scalable and modular memory capabilities for AI agents using ECL pipelines, enabling efficient management and retrieval of past interactions and diverse data types.
vectorize-io/hindsight
Hindsight is an agent memory system designed to create smarter, learning AI agents by moving beyond simple conversation history recall to encompass a biomimetic storage architecture for long-term m...
screenpipe/screenpipe
Screenpipe is a local-first, AI-powered memory tool that records computer activity (screen, audio, accessibility tree) to provide a searchable, automated context for personal AI agents and users, i...
Olow304/memvid
Memvid is a video-based AI memory library that stores millions of text chunks in MP4 files with ultra-fast semantic search, eliminating the need for traditional databases and enabling portable, efficient AI memory management.
EverMind-AI/EverOS
EverOS is an open-source Python framework for self-evolving, portable, long-term memory for AI agents, supporting multimodal ingestion and local-first persistence with Markdown as the source of truth.
MemTensor/MemOS
MemOS is a Memory Operating System for LLMs and AI agents that unifies long-term memory management, offering a single API for structured, multi-modal memory with enterprise-grade optimizations, sig...