Stars
Lightweight coding agent that runs in your terminal
A Simple and Universal Swarm Intelligence Engine, Predicting Anything. 简洁通用的群体智能引擎，预测万物
微舆：人人可用的多Agent舆情分析助手，打破信息茧房，还原舆情原貌，预测未来走向，辅助决策！从0实现，不依赖任何框架。
Gorilla: Training and Evaluating LLMs for Function Calls (Tool Calls)
[ICLR 2026] The Tool Decathlon: Benchmarking Language Agents for Diverse, Realistic, and Long-Horizon Task Execution
Meta Agents Research Environments is a comprehensive platform designed to evaluate AI agents in dynamic, realistic scenarios. Unlike static benchmarks, this platform introduces evolving environment…
[ICLR 2026] VitaBench: Benchmarking LLM Agents with Versatile Interactive Tasks in Real-world Applications
A new tool learning benchmark aiming at well-balanced stability and reality, based on ToolBench.
The official implementation of "EnvScaler: Scaling Tool-Interactive Environments for LLM Agent via Programmatic Synthesis".
Agent World Model: Infinity Synthetic Environments for Agentic Reinforcement Learning
Professional Antigravity Account Manager & Switcher. One-click seamless account switching for Antigravity Tools. Built with Tauri v2 + React (Rust).专业的 Antigravity 账号管理与切换工具。为 Antigravity 提供一键无缝账号切…
The RL Bridge for LLM-based Agent Applications. Made Simple & Flexible.
Official repo for the paper "Scaling Synthetic Data Creation with 1,000,000,000 Personas"
Official repo of Toucan: Synthesizing 1.5M Tool-Agentic Data from Real-World MCP Environments
τ-Bench: A Benchmark for Tool-Agent-User Interaction in Real-World Domains
Model Context Protocol Servers
An all-in-one enhancement suite for Google Gemini & AI Studio - timeline navigation, folder management, prompt library, and chat export in one powerful extension. / Google Gemini & AI Studio 全能增强插件…
💻 vibe coding 2026 | Your first modern programming course for beginners to master step by step.
Implementation of "YOLOv13: Real-Time Object Detection with Hypergraph-Enhanced Adaptive Visual Perception".
A Retrieval-Augmented Generation system built on 50k+ Formula 1 records — ask natural language questions, get fast, accurate, confidence-scored answers.
用于大模型 RLHF 进行人工数据标注排序的工具。A tool for manual response data annotation sorting in RLHF stage.
A Chinese medical ChatGPT based on LLaMa, training from large-scale pretrain corpus and multi-turn dialogue dataset.
CMB, A Comprehensive Medical Benchmark in Chinese
HuatuoGPT, Towards Taming Language Models To Be a Doctor. (An Open Medical GPT)