这是范围最广的一组：聊天界面、SDK 和框架、提示词与评测工具，以及各种基于大语言模型的应用。很多项目可以接入多家服务商的模型，有些还能在你自己的硬件上运行模型。
打算用在产品里的话，先确认三件事：许可证——有些热门项目限制商用；是否支持你正在用的模型服务商；以及它是否还在维护。每个项目页上的「秒懂」卡片会根据 GitHub 数据回答许可证和维护这两个问题。
开源连续推理基准研究平台、Kimi K2.7-Code、MiniMax M3、DeepSeekv4、GLM5 - GB200 NVL72 vs MI355X vs B200 vs GB300 NVL72 以及即将推出的 TPUv6e/v7/Trainium2/3 | ，Kimi K2.7-代码 MiniMax M3 DeepSeekv4 GLM5 - GB200 NVL72 vs MI355X vs B200 vs GB300 NVL72 TPUv6e/v7/Trainium2/3。
Lightweight coding agent written in Rust, optimized for memory footprint and performance
TT-NN 运算符库和 TT-Metaium 低级内核编程模型。
Open-source LLM/VLM load balancer and serving platform for self-hosting LLMs (and VLMs) at scale 🏓🦙 Alternative to projects like llm-d, Docker Model Runner, etc but with less moving parts and simple deployments built around ggml ecosystem. Runs on CPU and GPU.
编码代理可以回答您、您的模型、您的机器、您的规则。
Agent-R1: Training Powerful LLM Agents with End-to-End Reinforcement Learning
The all-in-one local AI studio for your desktop: chat, image and video generation and a coding agent in one free, open source app. Windows and Linux. No Docker, no terminal, no cloud required.
Trench — Open-Source Analytics Infrastructure. A single production-ready Docker image built on ClickHouse, Kafka, and Node.js for tracking events. Easily build product analytics dashboards, LLM RAGs, observability platforms, or any other analytics product.
一款包含了 Prompt管理，Skill管理，Agent管理的一站式AI工具箱，助你高效管理提示词，一键分发skills ，一站式管理Agent资产，并实现云同步，备份，版本管理 | An all-in-one AI toolbox for prompt, agent, and skills management. Reuse prompts, distribute skills with one click, manage agent assets, and support cloud sync, backup, and version control
Model compression toolkit engineered for enhanced usability, comprehensiveness, and efficiency.
A collection of AI Agents papers (Updated biweekly)
Real-time visualization of Claude Code agent orchestration — see your agents think, branch, and coordinate as they work.
Route, manage, and analyze your LLM requests across multiple providers with a unified API interface.
playwright for windows computer use
A fast and lightweight framework for creating decentralized agents with ease.
🔥 Real-time NVIDIA GPU dashboard
ROSA 🤖 is an AI Agent designed to interact with ROS1- and ROS2-based robotics systems using natural language queries. ROSA helps robot developers inspect, diagnose, understand, and operate robots.
Demystify RAG by building it from scratch. Local LLMs, no black boxes - real understanding of embeddings, vector search, retrieval, and context-augmented generation.
The classic Sillytavern, now has been rewritten in Tauri/Rust.
This repository provides an advanced Retrieval-Augmented Generation (RAG) solution for complex question answering. It uses sophisticated graph based algorithm to handle the tasks.
The unified multimodal backend for AI data apps. Database, orchestration, and serving in one Python file.
Open Source Implementation of Karpathy's LLM Wiki. Upload documents, connect your Claude account via MCP, and have it write your wiki !
英特尔 AutoRound 是一款用于量化工作流程的模型优化工具包，可降低推理成本，同时保持人工智能部署的准确性。
Fast Multimodal LLM on Mobile Devices