推理、部署与运行时
llmgateway
theopenco/llmgateway
Route, manage, and analyze your LLM requests across multiple providers with a unified API interface.
★ 1.6K⑂ 172TypeScript
ToolAI.io · GitHub 频道
GitHub 上的 AI 项目目录
一个基于事实的 LLM、智能体、MCP、RAG 和 AI 开发项目索引；每个条目均包含许可证、设置、下载、截图及相关资源。
公开仓库数据
项目索引
推理、部署与运行时
xLLM：面向多类 AI 加速器的高性能推理引擎
xllm-ai/xllm
xLLM 是一个 C++ 推理框架，支持 LLM、VLM、DiT 和 REC 模型。它面向多个 AI 加速器系列提供高吞吐、低延迟部署，并将服务层的调度与可用性职责同引擎层计算分离。
★ 1.5K⑂ 279C++
智能体与多智能体
connectonion
openonion/connectonion
The Best AI Agent Framework for Agent Collaboration.
★ 1.4K⑂ 201Python
智能体与多智能体
adk-js
google/adk-js
An open-source, code-first Typescript toolkit for building, evaluating, and deploying sophisticated AI agents with flexibility and control.
★ 1.4K⑂ 190TypeScript
MCP 与工具调用
awesome-agentic-ai-zh
wenyuchiou/awesome-agentic-ai-zh
A trilingual (繁中 / English / 简中) learning roadmap for agentic AI: from LLM basics to multi-agent systems, with 240+ curated resources and hands-on examples. 中文 AI agent 學習地圖。
★ 6.1K⑂ 814Python
MCP 与工具调用
Rapid-MLX
raullenchai/rapid-mlx
The fastest local AI engine for Apple Silicon. 4.2x faster than Ollama, 0.08s cached TTFT, 100% tool calling. 17 tool parsers, prompt cache, reasoning separation, cloud routing. Drop-in OpenAI replacement. Works with Claude Code, Cursor, Aider.
★ 3.5K⑂ 401Python
LLM 与基础模型
PaddleNLP
PaddlePaddle/PaddleNLP
Easy-to-use and powerful LLM and SLM library with awesome model zoo.
★ 13K⑂ 3KPython
LLM 与基础模型
GLM-5
zai-org/GLM-5
GLM-5: From Vibe Coding to Agentic Engineering
★ 6.8K⑂ 848—
AI 应用与自动化
qlib
microsoft/qlib
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, including supervised learning, market dynamics modeling, and RL, and is now equipped with https://github.com/microsoft/RD-Agent to automate R&D process.
★ 46.7K⑂ 7.4KPython
微调、训练与数据
DeepSpeed
deepspeedai/deepspeed
DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.
★ 43K⑂ 4.9KPython
推理、部署与运行时
TensorRT
NVIDIA/TensorRT
NVIDIA® TensorRT™ is an SDK for high-performance deep learning inference on NVIDIA GPUs. This repository contains the open source components of TensorRT.
★ 13.2K⑂ 2.4KC++
智能体与多智能体
UFO
microsoft/UFO
UFO³: Weaving the Digital Agent Galaxy
★ 9.3K⑂ 1KPython
第 9 / 25 页 · 295 个项目