Stars
Claude Code skill implementing Manus-style persistent markdown planning — the workflow pattern behind the $2B acquisition.
Sharp Monocular View Synthesis in Less Than a Second
JavaScript in-page GUI agent. Control web interfaces with natural language.
A next.js web application that integrates AI capabilities with draw.io diagrams. This app allows you to create, modify, and enhance diagrams through natural language commands and AI-assisted visual…
FULL Augment Code, Claude Code, Cluely, CodeBuddy, Comet, Cursor, Devin AI, Junie, Kiro, Leap.new, Lovable, Manus, NotionAI, Orchids.app, Perplexity, Poke, Qoder, Replit, Same.dev, Trae, Traycer AI…
A powerful coding agent toolkit providing semantic retrieval and editing capabilities (MCP server & other integrations)
A clean, modular SDK for building AI agents with OpenHands V1.
OpenCE (Open Context Engineering): A community toolkit to implement, evaluate, and combine LLM context strategies (RAG, ACE, Compression). Evolved from the `ACE-open` reproduction.
🧠 Make your agents learn from experience. Based on the Agentic Context Engineering (ACE) framework.
Weaviate is an open-source vector database that stores both objects and vectors, allowing for the combination of vector search with structured filtering with the fault tolerance and scalability of …
[NeurIPS'24] HippoRAG is a novel RAG framework inspired by human long-term memory that enables LLMs to continuously integrate knowledge across external documents. RAG + Knowledge Graphs + Personali…
An AI agent development platform with all-in-one visual tools, simplifying agent creation, debugging, and deployment like never before. Coze your way to AI Agent creation.
A modular graph-based Retrieval-Augmented Generation (RAG) system
Build multi-agent systems that learn and improve with every interaction.
🤗 smolagents: a barebones library for agents that think in code.
KAG is a logical form-guided reasoning and retrieval framework based on OpenSPG engine and LLMs. It is used to build logical reasoning and factual Q&A solutions for professional domain knowledge ba…
Qlib is an AI-oriented Quant investment platform that aims to use AI tech to empower Quant Research, from exploring ideas to implementing productions. Qlib supports diverse ML modeling paradigms, i…
Build, evaluate and train General Multi-Agent Assistance with ease
Test-time preferenece optimization (ICML 2025).
Build Real-Time Knowledge Graphs for AI Agents
🚀🚀🚀A faster, better and more stable Redis desktop manager [GUI client], compatible with Linux, Windows, Mac.
Official Implementation of "KBLaM: Knowledge Base augmented Language Model"
[EMNLP'25 findings] This is the official repo for the paper, HiRAG: Retrieval-Augmented Generation with Hierarchical Knowledge.
A lightweight, powerful framework for multi-agent workflows
Production-tested AI infrastructure tools for efficient AGI development and community-driven innovation
Standardized Distributed Generative and Predictive AI Inference Platform for Scalable, Multi-Framework Deployment on Kubernetes
Pretraining and inference code for a large-scale depth-recurrent language model