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
nhevers/MoltBrain
MoltBrain is a long-term memory layer designed for OpenClaw, MoltBook, and Claude Code agents that automatically learns and recalls project context to enhance productivity and continuity across sessions. It functions by capturing and learning from user interactions, decisions, and code during sessions, then injecting this learned context into future sessions to provide relevant information and insights. This memory system helps agents remember important details such as authentication setups, token structures, and security choices, which are critical for maintaining project continuity and reducing repetitive explanations or setups. The project features an automatic capture mechanism that records discoveries, decisions, and code snippets, enabling a smart semantic search powered by Model Context Protocol (MCP) tools to find relevant context efficiently. Users can browse their history through a web viewer hosted locally, organize observations with custom tags and filters, and bookmark important insights as favorites. Additionally, MoltBrain offers analytics to track tokens, sessions, and concept trends, providing valuable metrics for understanding project evolution. MoltBrain supports exporting data in JSON, CSV, or Markdown formats with customizable templates, allowing users to integrate their memory data into other workflows or documentation. The interface includes dark and light themes with customizable options and supports full keyboard navigation for ease of use. The system operates by injecting context at the start of a session, capturing output and extracting facts during tool use, and generating summaries at the end of sessions to update the memory. Overall, MoltBrain enhances the capabilities of AI agents by providing a persistent, intelligent memory layer that leverages MCP for semantic understanding and context management, making it a valuable tool for developers and teams working on complex projects requiring continuity and context awareness.
https://github.com/nhevers/MoltBrain
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...