Stars
A curated collection of resources, tools, and frameworks for developing GUI Agents.
InternAgent-1.5: A Unified Agentic Framework for Long-Horizon Autonomous Scientific Discovery
XPlaneGymEnvs is a Gymnasium environment that integrates with X-Plane for reinforcement learning without requiring third-party plugins.
🐹 An Intelligent Phone That Never Sleeps.
Official Codebase for "Neural Thickets: Diverse Task Experts Are Dense Around Pretrained Weights"
The open-source execution engine for AI agents. 412 modules, MCP-native, triggers, queue, versioning, metering.
MemoryBear Equip AI with human-like memory capability
MLEvolve is an open-source autonomous system for end-to-end machine learning algorithm design and optimization powered by progressive search and experience-driven memory.
Air Travel Service Platform. A modern web application built with Vue.js and JavaScript, offering flight search, ticket booking, itinerary planning, and comprehensive travel services in one integrat…
Text and code embeddings research from CodeFuse: C2LLM, D2LLM, E2LLM, F2LLM
Paper accepted by CIKM 2024. Codes of GongBU, a LLM fine-tuning platform for domain-specific adaptation.
A simple, fast and robust program-aware agentic inference system.
🏭 Mega Scale Multimodal DataPipeline for SOTA Foundation Models
The Best AI Agent Framework for Agent Collaboration.
Lightweight 2D game engine for WebAssembly and WeChat MiniGames
UI-Venus is a native UI agent designed to perform precise GUI element grounding and effective navigation using only screenshots as input.
Multimodal deep-research MLLM and benchmark. The first long-horizon multimodal deep-research MLLM, extending the number of reasoning turns to dozens and the number of search-engine interactions to …
Turn paper/text/topic into editable research figures, technical route diagrams, and presentation slides.
A-Daily-TradingAgents 是一个轻量化的、更适合个人定制化使用的、专为 A 股市场打造的现代化量化决策系统。它不仅仅是一个选股工具，更是一个集成了数据清洗、量化分析、AI 深度解读与实时风控的完整交易辅助平台。
Self‑calibrated neuromorphic hyperspectral imaging pipeline for event cameras with diffractive illumination. Includes end‑to‑end tools for RAW segmentation, multi‑window time‑warping compensation, …
High Performance Redis-API Compatible Distributed Database with Persistency, Scalability, Full ACID Transactions, and Tiered S3 Storage Cost Efficiency
A user-friendly YOLOv10 Web UI that supports training and inference. 一个用户友好的YOLOv10 Web UI，支持训练和推理。
LingEcho is an intelligent voice interaction platform that provides a comprehensive AI voice interaction solution. It integrates advanced speech recognition (ASR), text-to-speech (TTS), large langu…
Personal Website with Obsidian-like knowledge graph