AI 大模型 · GitHub star 排行 Top 30
大语言模型的推理引擎、微调框架与应用脚手架。下表按 GitHub star 数从高到低排列，共收录 55 个相关开源项目， 使用上方的筛选器可以按活跃度、编程语言进一步过滤。
| 排名 | 项目 | Star | 语言 | 最后更新 |
|---|---|---|---|---|
| 1 | Significant-Gravitas/AutoGPT AutoGPT is the vision of accessible AI for everyone, to use and to build on. Our mission is to provide the tools, so that you can focus on what matte… | 186k | Python | 2026-08 |
| 2 | ollama/ollama Get up and running with Kimi-K2.6, GLM-5.2, MiniMax, DeepSeek, gpt-oss, Qwen, Gemma and other models. | 178k | Go | 2026-08 |
| 3 | f/prompts.chat f.k.a. Awesome ChatGPT Prompts. Share, discover, and collect prompts from the community. Free and open source — self-host for your organization with … | 167k | HTML | 2026-08 |
| 4 | huggingface/transformers 🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both … | 163k | Python | 2026-08 |
| 5 | firecrawl/firecrawl The context API to search, scrape, and interact with the web at scale. 🔥 | 161k | TypeScript | 2026-08 |
| 6 | langgenius/dify Build Agentic workflows, RAG pipelines, with rich AI model and tool support on one collaborative workspace. Deploy on cloud, VPC, or self-hosted, so … | 151k | TypeScript | 2026-08 |
| 7 | open-webui/open-webui User-friendly AI Interface (Supports Ollama, OpenAI API, ...) | 148k | Python | 2026-08 |
| 8 | langchain-ai/langchain The agent engineering platform. | 143k | Python | 2026-08 |
| 9 | browser-use/browser-use 🌐 Make websites accessible for AI agents. Automate tasks online with ease. | 108k | Python | 2026-08 |
| 10 | harry0703/MoneyPrinterTurbo 利用 AI 大模型和自动化工作流，根据主题或关键词一键生成高清短视频。Generate HD short videos from a topic or keyword with an automated AI workflow. | 102k | Python | 2026-08 |
| 11 | rasbt/LLMs-from-scratch Implement a ChatGPT-like LLM in PyTorch from scratch, step by step | 101k | Jupyter Notebook | 2026-07 |
| 12 | JuliusBrussee/caveman 🪨 why use many token when few token do trick — Claude Code skill that cuts 65% of tokens by talking like caveman | 96k | JavaScript | 2026-08 |
| 13 | TauricResearch/TradingAgents TradingAgents: Multi-Agents LLM Financial Trading Framework | 96k | Python | 2026-07 |
| 14 | vllm-project/vllm A high-throughput and memory-efficient inference and serving engine for LLMs | 88k | Python | 2026-08 |
| 15 | OpenHands/OpenHands 🙌 OpenHands: AI-Driven Development | 83k | TypeScript | 2026-08 |
| 16 | mlabonne/llm-course Course to get into Large Language Models (LLMs) with roadmaps and Colab notebooks. | 81k | — | 2026-02 |
| 17 | bytedance/deer-flow An open-source long-horizon SuperAgent harness that researches, codes, and creates. With the help of sandboxes, memories, tools, skill, subagents and… | 79k | Python | 2026-08 |
| 18 | rtk-ai/rtk CLI proxy that reduces LLM token consumption by 60-90% on common dev commands. Single Rust binary, zero dependencies | 75k | Rust | 2026-08 |
| 19 | hiyouga/LlamaFactory Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024) | 74k | Python | 2026-08 |
| 20 | shareAI-lab/learn-claude-code Bash is all you need - A nano claude code–like 「agent harness」, built from 0 to 1 | 73k | Python | 2026-07 |
| 21 | datawhalechina/hello-agents 📚 《从零开始构建智能体》——从零开始的智能体原理与实践教程 | 71k | Python | 2026-08 |
| 22 | FoundationAgents/MetaGPT 🌟 The Multi-Agent Framework: First AI Software Company, Towards Natural Language Programming | 70k | Python | 2026-01 |
| 23 | unslothai/unsloth Unsloth is a local UI for training and running Kimi K3, Gemma 4, Qwen3.6, DeepSeek-V4, GLM and other models. | 70k | Python | 2026-08 |
| 24 | headroomlabs-ai/headroom Compress tool outputs, logs, files, and RAG chunks before they reach the LLM. 20% fewer tokens for coding agents, 60-95% fewer tokens for JSON, same … | 65k | Python | 2026-08 |
| 25 | Mintplex-Labs/anything-llm Stop renting your intelligence. Own it with AnythingLLM. Everything you need for a powerful local-first agent experience | 64k | JavaScript | 2026-08 |
| 26 | mem0ai/mem0 Universal memory layer for AI Agents | 63k | Python | 2026-08 |
| 27 | asgeirtj/system_prompts_leaks Extracted system prompts from Anthropic - Claude Fable 5, Opus 5, Claude Design, Claude Code. OpenAI - ChatGPT GPT-5.6-Sol, Codex. Google - Gemini 3.… | 62k | JavaScript | 2026-07 |
| 28 | sansan0/TrendRadar ⭐AI-driven public opinion & trend monitor with multi-platform aggregation, RSS, and smart alerts.🎯 告别信息过载，你的 AI 舆情监控助手与热点筛选工具！聚合多平台热点 + RSS 订阅，支持关键词… | 61k | Python | 2026-07 |
| 29 | upstash/context7 Context7 Platform -- Up-to-date code documentation for LLMs and AI code editors | 60k | TypeScript | 2026-08 |
| 30 | ZhuLinsen/daily_stock_analysis LLM 驱动的多市场股票智能分析系统：多源行情、实时新闻、决策看板与自动推送，支持零成本定时运行。 LLM-powered multi-market stock analysis system with multi-source market data, real-time news, decis… | 60k | Python | 2026-08 |
怎么看这份榜单
star 数反映的是知名度而不是代码质量——教程、清单类仓库天然更容易积累 star， 而一些工程质量极高的底层库反而不显眼。选型时建议把「最后更新」这一列一起看： 超过一年没有提交的项目，往往意味着维护已经停滞，接入前需要评估风险。
想看其他方向的排行，可以返回GitHub 高星项目榜切换维度。