Self-evolving Context Database for AI Agents. Unify Agent Memory, Knowledge RAG and Skills.
- context-database
- agentic-rag
- agent-memory
- self-evolving
47,133 repositories indexed
1–16 of 16 · Most stars
Self-evolving Context Database for AI Agents. Unify Agent Memory, Knowledge RAG and Skills.
[EMNLP2025] LightRAG: Simple and Fast Retrieval-Augmented Generation
TranslatedLangchain-Chatchat (formerly langchain-ChatGLM), local knowledge based LLM (like ChatGLM, Qwen and Llama) RAG and Agent app with langchain
Cognee is the open-source AI memory platform for agents. Give your AI agents persistent long-term memory with small models for free
Translated🔥 MaxKB is an open-source platform for building enterprise-grade agents. A powerful and easy-to-use open-source enterprise-grade agent platform.
Pocket Flow: Codebase to Tutorial
Run 35B MoE models in ~2.5 GB of RAM. Weights stream from SSD; a trained router predicts loads a step ahead. Mac, iPhone, Android, Windows supported
EdgeRock: Strong Reasoning at Constant Memory. Multimodal models with O(N) generation and O(1) persistent history. Inference and evaluation code.
Ontology-Augmented Generation for AI agents.
Extract knowledge from all information sources using gpt and other language models. Index and make Q&A session with information sources.
Feather agent harness, training integrations, and evaluation tools for knowledge work
The World's Most Comprehensive, Authoritative, and Structured Open Source Data Source Knowledge Base
🔍A cutting edge context aware GraphQL API fuzzing tool!
AI-powered platform for OSINT intelligence analysis. Features archive discovery with hypothesis-driven investigation, GLiNER entity extraction, Mapbox geospatial visualization, network analysis, and document processing. Built with FastAPI, Next.js, Weaviate, and DSPy.
Agentic memory for CTI in Python — STIX knowledge graphs, threat-actor alias resolution, offline-first RAG, MCP server for Claude Code and LangChain agents
Open-source simulation harness for testing AI agents. Simulate LLM and tool calls to test edge cases, failure paths, and agent logic without live API calls.