Stars
DeepInfer: High-performance, large-scale inference framework for DeepSeek models
DeepSeek Harness: Everything is a Plugin.
📚 《从零开始构建智能体》——从零开始的智能体原理与实践教程
[ICLR 2026] VitaBench: Benchmarking LLM Agents with Versatile Interactive Tasks in Real-world Applications
Tongyi Deep Research, the Leading Open-source Deep Research Agent
wdndev / swarm
Forked from openai/swarmEducational framework exploring ergonomic, lightweight multi-agent orchestration. Managed by OpenAI Solution team.
[EMNLP 2025] CompassVerifier: A Unified and Robust Verifier for LLMs Evaluation and Outcome Reward
Train your Agent model via our easy and efficient framework
Elegant reading of real-time and hottest news
wdndev / llama.cpp.tinyllm
Forked from ggml-org/llama.cppTiny LLM inference in C/C++
MultiAgentPPT 是一个集成了 A2A（Agent2Agent）+ MCP（Model Context Protocol）+ ADK（Agent Development Kit） 架构的智能化演示文稿生成系统，支持通过多智能体协作和流式并发机制
《李宏毅生成式人工智能教程》，PDF下载地址：https://github.com/datawhalechina/leegenai-tutorial/releases
electron + vue3 + TypeScript + Vite + electron-builder + pnpm project
Develop LLM Chat Applications with Electron.
Clash for Windows 的前汉化版. 现在提供 Clash for Windows 的改进版本, 这包括 Mihomo 核心替换, AnyTLS 等现代协议兼容
Qwen3-VL is the multimodal large language model series developed by Qwen team, Alibaba Cloud.