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
vectorize-io/hindsight
Hindsight is an advanced agent memory system that enables AI agents to learn and adapt over time, significantly improving upon traditional methods like RAG or knowledge graphs. Unlike systems focused solely on conversational history, Hindsight emphasizes true learning. It achieves state-of-the-art performance on benchmarks like LongMemEval, which measures memory system effectiveness in various conversational AI scenarios, with its results validated by independent research. The system employs a biomimetic architecture, organizing memories into three distinct categories: 'World' (facts), 'Experiences' (agent's own interactions), and 'Mental Models' (learned understandings derived from reflection). Memories are stored in 'banks' and processed to create raw memories and mental models. Hindsight offers flexible integration options, including a simple LLM Wrapper for quick setup with existing agents or a detailed API for fine-grained control. It supports various LLM providers such as OpenAI, Anthropic, Gemini, Groq, Ollama, and LM Studio. The project provides SDKs for Python and Node.js/TypeScript, and can be deployed via Docker or as an embedded Python solution requiring no server. Hindsight is particularly suited for complex conversational AI agents and autonomous task-performing agents that require adaptability, learning from feedback, and the ability to handle open-ended tasks, making it ideal for 'AI employees' or sophisticated AI workflows. It also supports granular features like per-user memories and chat history personalization through custom metadata.
https://github.com/vectorize-io/hindsight
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.
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...
casibase/casibase
Casibase is an open-source enterprise AI knowledge base platform supporting the Model Context Protocol and multiple AI models with features like admin UI, user management, and Single Sign-On.