Back to Rankings返回排行榜
Top 100 · Large Language Models前 100 · 大语言模型
100 repositories sorted by large language models 按 大语言模型 排序，共 100 个仓库
| # | Repository仓库 | Stars | Forks | Language语言 | Issues | Description描述 | Last Commit最后提交 |
|---|---|---|---|---|---|---|---|
| 1 | ECC affaan-m | 276.6k | 41.2k | JavaScript | 83 | The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.代理利用性能优化系统。 Claude Code、Codex、Opencode、Cursor 等的技能、直觉、记忆、安全性和研究优先的开发。 | 2026-10-11 |
| 2 | hermes-agent NousResearch | 252.6k | 54.6k | Python | 14933 | The agent that grows with you与您共同成长的代理商 | 2026-10-11 |
| 3 | andrej-karpathy-skills multica-ai | 218.4k | 22.0k | N/A | 0 | A single CLAUDE.md file to improve Claude Code behavior, derived from Andrej Karpathy's observations on LLM coding pitfalls.用于改进 Claude 代码行为的单个 CLAUDE.md 文件，源自 Andrej Karpathy 对 LLM 编码陷阱的观察。 | 2026-04-20 |
| 4 | firecrawl firecrawl | 190.3k | 10.1k | TypeScript | 95 | Supercharge your AI agents with data from the web and beyond. Building the library for superintelligence. 🔥 | 2026-10-10 |
| 5 | AutoGPT Significant-Gravitas | 187.5k | 45.9k | Python | 361 | 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 matters.AutoGPT 的愿景是为每个人提供易于使用和构建的人工智能。我们的使命是提供工具，以便您可以专注于重要的事情。 | 2026-10-11 |
| 6 | ollama ollama | 182.7k | 18.2k | Go | 2568 | Get up and running with Kimi, GLM, MiniMax, DeepSeek, gpt-oss, Qwen, Gemma and other models. | 2026-10-11 |
| 7 | prompts.chat f | 172.5k | 22.1k | HTML | 29 | f.k.a. Awesome ChatGPT Prompts. Share, discover, and collect prompts from the community. Free and open source — self-host for your organization with complete privacy.F.K.A.很棒的 ChatGPT 提示。分享、发现并收集社区中的提示。免费和开源——为您的组织自行托管，并具有完全的隐私。 | 2026-10-11 |
| 8 | transformers huggingface | 167.3k | 34.8k | Python | 712 | 🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training. 🤗 Transformers：文本、视觉、音频和多模态模型中最先进的机器学习模型的模型定义框架，用于推理和训练。 | 2026-10-11 |
| 9 | ponytail DietrichGebert | 160.6k | 8.6k | JavaScript | 19 | Makes your AI agent think like the laziest senior dev in the room. The best code is the code you never wrote.让你的人工智能代理像房间里最懒的高级开发人员一样思考。最好的代码是你从未编写过的代码。 | 2026-10-10 |
| 10 | dify langgenius | 158.1k | 25.0k | TypeScript | 484 | Build Agentic workflows, RAG pipelines, with rich AI model and tool support on one collaborative workspace. Deploy on cloud, VPC, or self-hosted, so teams move from prototype to production without rebuilding the stack.在一个协作工作空间上构建 Agentic 工作流程、RAG 管道，并提供丰富的 AI 模型和工具支持。在云、VPC 或自托管上部署，因此团队无需重建堆栈即可从原型转向生产。 | 2026-10-11 |
| 11 | open-webui open-webui | 154.2k | 22.6k | Python | 159 | User-friendly AI Interface (Supports Ollama, OpenAI API, ...)用户友好的 AI 界面（支持 Ollama、OpenAI API...） | 2026-10-10 |
| 12 | langchain langchain-ai | 147.6k | 24.8k | Python | 530 | The agent engineering platform.代理工程平台。 | 2026-10-10 |
| 13 | awesome-llm-apps Shubhamsaboo | 141.2k | 20.8k | Python | 8 | 100+ AI Agents, Agent Skills and RAG Apps - Free and Open Source.100 多个 AI 代理、代理技能和 RAG 应用程序 - 免费且开源。 | 2026-09-30 |
| 14 | llama.cpp ggml-org | 130.8k | 24.3k | C++ | 834 | LLM inference in C/C++C/C++ 中的 LLM 推理 | 2026-10-10 |
| 15 | MoneyPrinterTurbo harry0703 | 129.5k | 20.3k | Python | 17 | 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.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. | 2026-10-10 |
| 16 | graphify Graphify-Labs | 125.3k | 12.1k | Python | 697 | Turn any codebase, with its docs, SQL schemas, configs, and PDFs, into a queryable knowledge graph. A /graphify skill for Claude Code, Cursor, Codex, and Gemini CLI: local deterministic AST parsing, every edge explained, no vector store.将任何代码库及其文档、SQL 架构、配置和 PDF 转换为可查询的知识图。适用于 Claude Code、Cursor、Codex 和 Gemini CLI 的 /graphify 技能：本地确定性 AST 解析，每条边均已解释，无向量存储。 | 2026-10-10 |
| 17 | browser-use browser-use | 117.6k | 13.0k | Python | 169 | Agents that use the browser.使用浏览器的代理。 | 2026-10-09 |
| 18 | pi earendil-works | 114.1k | 14.5k | TypeScript | 237 | AI agent toolkit: unified LLM API, agent loop, TUI, coding agent CLIAI代理工具包：统一LLM API、代理循环、TUI、编码代理CLI | 2026-10-10 |
| 19 | caveman JuliusBrussee | 110.9k | 6.4k | Go | 34 | 🪨 why use many token when few token do trick. Viral skill + proxy for coding agents that cuts 65% of tokens by talking like a caveman. | 2026-10-10 |
| 20 | TradingAgents TauricResearch | 110.5k | 21.3k | Python | 42 | TradingAgents: Multi-Agents LLM Financial Trading FrameworkTradingAgents：多代理LLM金融交易框架 | 2026-10-03 |
| 21 | LLMs-from-scratch rasbt | 106.3k | 16.4k | Jupyter Notebook | 2 | Implement a ChatGPT-like LLM in PyTorch from scratch, step by step在 PyTorch 中从头开始一步步实现类似 ChatGPT 的 LLM | 2026-10-02 |
| 22 | vllm vllm-project | 93.5k | 23.2k | Python | 2575 | A high-throughput and memory-efficient inference and serving engine for LLMs适用于法学硕士的高吞吐量和内存高效推理和服务引擎 | 2026-10-11 |
| 23 | ragflow infiniflow | 92.0k | 10.9k | Go | 981 | RAGFlow is a leading open-source Retrieval-Augmented Generation (RAG) engine that fuses cutting-edge RAG with Agent capabilities to create a superior context layer for LLMsRAGFlow 是一款领先的开源检索增强生成 (RAG) 引擎，它将尖端的 RAG 与代理功能相融合，为法学硕士创建卓越的上下文层 | 2026-10-11 |
| 24 | PaddleOCR PaddlePaddle | 90.9k | 11.5k | Python | 166 | Turn any PDF or image document into structured data for your AI. A powerful, lightweight OCR toolkit that bridges the gap between images/PDFs and LLMs. Supports 100+ languages.将任何 PDF 或图像文档转换为 AI 的结构化数据。一款功能强大、轻量级的 OCR 工具包，可弥合图像/PDF 和法学硕士之间的差距。支持 100 多种语言。 | 2026-09-16 |
| 25 | OpenHands OpenHands | 90.5k | 12.0k | TypeScript | 495 | 🙌 OpenHands: AI-Driven Development🙌 OpenHands：人工智能驱动的开发 | 2026-10-11 |
| 26 | crawl4ai unclecode | 85.2k | 8.8k | Python | 47 | Open-source web crawler and scraper for LLMs and AI agents: any website into clean, LLM-ready Markdown. Run it yourself, or use Crawl4AI Cloud with one key. | 2026-10-05 |
| 27 | deer-flow bytedance | 83.7k | 11.6k | Python | 522 | An open-source long-horizon SuperAgent harness that researches, codes, and creates. With the help of sandboxes, memories, tools, skill, subagents and message gateway, it handles different levels of tasks that could take minutes to hours.一个开源的长期 SuperAgent 工具，用于研究、编码和创建。借助沙箱、内存、工具、技能、子代理和消息网关，它可以处理可能需要几分钟到几小时的不同级别的任务。 | 2026-10-11 |
| 28 | llm-course mlabonne | 83.5k | 9.7k | N/A | 67 | Course to get into Large Language Models (LLMs) with roadmaps and Colab notebooks.通过路线图和 Colab 笔记本进入大型语言模型 (LLM) 的课程。 | 2026-02-05 |
| 29 | rtk rtk-ai | 82.9k | 5.3k | Rust | 846 | CLI proxy that reduces LLM token consumption by 60-90% on common dev commands. Single Rust binary, zero dependenciesCLI 代理可将常见开发命令的 LLM 令牌消耗减少 60-90%。单个 Rust 二进制文件，零依赖 | 2026-10-09 |
| 30 | hello-agents datawhalechina | 82.5k | 10.2k | Python | 78 | 📚 《从零开始构建智能体》——从零开始的智能体原理与实践教程 | 2026-10-08 |
| 31 | archify tt-a1i | 81.7k | 5.5k | JavaScript | 123 | Turn any idea, plan, or codebase into a beautiful interactive diagram. An agent skill for Claude Code, Codex, and more. | 2026-10-11 |
| 32 | MinerU opendatalab | 81.4k | 6.8k | Python | 9 | Transforms complex documents like PDFs and Office docs into LLM-ready markdown/JSON for your Agentic workflows.将 PDF 和 Office 文档等复杂文档转换为适合您的 Agentic 工作流程的 LLM 就绪 Markdown/JSON。 | 2026-10-11 |
| 33 | learn-claude-code shareAI-lab | 78.3k | 12.5k | Python | 41 | Bash is all you need - A nano claude code–like 「agent harness」, built from 0 to 1Bash 就是你所需要的 - 一个 Nano claude 代码——类似“代理工具”，从 0 到 1 构建 | 2026-09-28 |
| 34 | unsloth unslothai | 77.7k | 7.2k | Python | 447 | Local UI to run and train LLMs and diffusion models. Supports GGUF, MLX, Qwen3.8, DeepSeek-V4, MiniMax-H3, Gemma 4, FLUX and more.Error 500 (Server Error)!!1500.That’s an error.There was an error. Please try again later.That’s all we know. | 2026-10-11 |
| 35 | gpt4all nomic-ai | 77.4k | 8.3k | C++ | 731 | GPT4All: Run Local LLMs on Any Device. Open-source and available for commercial use.GPT4All：在任何设备上运行本地 LLM。开源并可用于商业用途。 | 2025-05-27 |
| 36 | rea morluto | 76.5k | 16.3k | TypeScript | 83 | Reverse engineer anything with agents, from app behavior down to native binaries. | 2026-10-11 |
| 37 | LlamaFactory hiyouga | 75.4k | 9.2k | Python | 1004 | Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024)100多个LLM和VLM的统一高效微调（ACL 2024） | 2026-10-10 |
| 38 | headroom headroomlabs-ai | 75.0k | 5.8k | Python | 201 | 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 answers. Library, proxy, MCP server.在工具输出、日志、文件和 RAG 块到达 LLM 之前对其进行压缩。编码代理的标记减少了 20%，JSON 的标记减少了 60-95%，答案相同。库、代理、MCP 服务器。 | 2026-10-11 |
| 39 | gpt_academic binary-husky | 71.4k | 8.3k | Python | 297 | 为GPT/GLM等LLM大语言模型提供实用化交互接口，特别优化论文阅读/润色/写作体验，模块化设计，支持自定义快捷按钮&函数插件，支持Python和C++等项目剖析&自译解功能，PDF/LaTex论文翻译&总结功能，支持并行问询多种LLM模型，支持chatglm3等本地模型。接入通义千问, deepseekcoder, 讯飞星火, 文心一言, llama2, rwkv, claude2, moss等。 | 2026-01-25 |
| 40 | MetaGPT FoundationAgents | 70.8k | 9.0k | Python | 9 | 🌟 The Multi-Agent Framework: First AI Software Company, Towards Natural Language Programming🌟 多代理框架：第一家人工智能软件公司，迈向自然语言编程 | 2026-01-21 |
| 41 | system_prompts_leaks asgeirtj | 69.4k | 11.3k | Python | 21 | Documented system prompts from Anthropic - Claude Fable 5.1, Opus 5.5, Claude Design, Claude Code. OpenAI - ChatGPT GPT-6-Astra, Codex. Google - Gemini 3.8 Flash, 3.1 Pro, Antigravity. xAI - Grok, Grok Bot, Cursor, Kimi and more! Updated regularly. | 2026-10-10 |
| 42 | mem0 mem0ai | 67.0k | 7.9k | Python | 377 | The Memory Layer for AI Agents - Drop-in memory infrastructure for AI agents and apps. Context that persists. Built for production.AI 代理的内存层 - AI 代理和应用程序的嵌入式内存基础架构。持续存在的上下文。专为生产而打造。 | 2026-10-09 |
| 43 | anything-llm Mintplex-Labs | 66.9k | 7.5k | JavaScript | 309 | Stop renting your intelligence. Own it with AnythingLLM. Everything you need for a powerful local-first agent experience 别再出租你的智力了。 AnythingLLM 拥有它。强大的本地优先代理体验所需的一切 | 2026-10-09 |
| 44 | ai-engineering-from-scratch rohitg00 | 66.8k | 11.7k | Python | 16 | Learn AI Engineering! Learn it. Build it. Ship it for others. | 2026-10-10 |
| 45 | daily_stock_analysis ZhuLinsen | 66.2k | 55.1k | Python | 25 | 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, decision dashboard, automated notifications, and cost-free scheduled runs. | 2026-10-05 |
| 46 | minimind jingyaogong | 63.5k | 8.3k | Python | 31 | 🧠 Train a 64M-parameter LLM from scratch in just 2h!🧠 只需 2 小时从头开始训练 64M 参数的 LLM！ | 2026-09-22 |
| 47 | context7 upstash | 62.9k | 3.1k | TypeScript | 13 | Context7 Platform -- Up-to-date code documentation for LLMs and AI code editorsContext7 Platform——法学硕士和人工智能代码编辑器的最新代码文档 | 2026-10-10 |
| 48 | TrendRadar sansan0 | 62.8k | 24.9k | Python | 34 | ⭐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，支持关键词精准筛选。AI 智能筛选新闻 + AI 翻译 + AI 分析简报直推手机，也支持接入 MCP 架构，赋能 AI 自然语言对话分析、情感洞察与趋势预测等。支持 Docker ，数据本地/云端自持。集成微信/飞书/钉钉/Telegram/邮件/ntfy/bark/slack 等渠道智能推送。⭐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，支持关键词精准筛选。 AI 智能筛选新闻 + AI 翻译 + AI 分析简报直推手机，也支持接入 MCP 架构，赋能 AI 自然语言对话分析、情感洞察与趋势预测等。支持 Docker ，数据本地/云端自持。集成微信/飞书/钉钉/Telegram/邮件/ntfy/bark/slack 等渠道智能推送。 | 2026-10-10 |
| 49 | pathway pathwaycom | 62.1k | 1.7k | Python | 29 | Python ETL framework for stream processing, real-time analytics, LLM pipelines, and RAG.用于流处理、实时分析、LLM 管道和 RAG 的 Python ETL 框架。 | 2026-10-10 |
| 50 | litellm BerriAI | 60.9k | 12.2k | Python | 1823 | The fastest, litest AI Gateway. Rust core with Python SDK. Call 100+ LLM APIs in OpenAI (or native) format with cost tracking, guardrails, load balancing, and logging [Bedrock, Azure, OpenAI, Anthropic, OpenAI, VertexAI, vLLM, Nvidia NIM]最快、最精简的AI网关。 Rust 核心与 Python SDK。以 OpenAI（或本机）格式调用 100 多个 LLM API，具有成本跟踪、护栏、负载平衡和日志记录 [Bedrock、Azure、OpenAI、Anthropic、OpenAI、VertexAI、vLLM、Nvidia NIM] | 2026-10-11 |
| 51 | mempalace MemPalace | 59.5k | 7.6k | Python | 361 | The best-benchmarked open-source AI memory system. And it's free.最佳基准的开源人工智能存储系统。而且它是免费的。 | 2026-10-10 |
| 52 | llm-app pathwaycom | 58.8k | 1.5k | Jupyter Notebook | 5 | Ready-to-run cloud templates for RAG, AI pipelines, and enterprise search with live data. 🐳Docker-friendly.⚡Always in sync with Sharepoint, Google Drive, S3, Kafka, PostgreSQL, real-time data APIs, and more.适用于 RAG、AI 管道和带有实时数据的企业搜索的可立即运行的云模板。 🐳Docker 友好。⚡始终与 Sharepoint、Google Drive、S3、Kafka、PostgreSQL、实时数据 API 等同步。 | 2026-07-05 |
| 53 | dive-into-llms Lordog | 56.2k | 6.7k | Jupyter Notebook | 10 | 《动手学大模型Dive into LLMs》系列编程实践教程 | 2025-10-10 |
| 54 | humanizer blader | 55.5k | 4.4k | Python | 0 | Agent skill that removes signs of AI-generated writing from text代理技能可消除文本中人工智能生成的书写痕迹 | 2026-09-28 |
| 55 | awesome-claude-code hesreallyhim | 55.4k | 4.8k | Python | 1096 | A hand-picked collection of the finest of resources for the most awesome of agents, Claude Code, the undisputed champion of coding companions, from the unstoppable team at Anthropic PBC (no affiliation). A delectable showcase of top tier skills, ambidextrous agents, scintillating status lines, top notch developer tooling, and also we have plugins | 2026-10-11 |
| 56 | goose aaif-goose | 55.1k | 6.4k | Rust | 326 | an open source, extensible AI agent that goes beyond code suggestions - install, execute, edit, and test with any LLM开源、可扩展的 AI 代理，超越代码建议 - 使用任何 LLM 安装、执行、编辑和测试 | 2026-10-09 |
| 57 | ai-agent-book bojieli | 53.4k | 6.0k | Python | 12 | 《深入理解 AI Agent：设计原理与工程实践》（李博杰 著）开源主仓库：全书正文、编译版 PDF 与按章配套代码《深入理解 AI Agent：设计原理与工程实践》（李博杰 着）开源主仓库：全书正文、编译版 PDF 与按章配套代码 | 2026-10-08 |
| 58 | cherry-studio CherryHQ | 52.5k | 5.1k | TypeScript | 1140 | AI productivity studio with smart chat, autonomous agents, and 300+ assistants. Unified access to frontier LLMsAI 生产力工作室，配备智能聊天、自主代理和 300 多名助手。统一获取前沿法学硕士 | 2026-10-11 |
| 59 | llama_index run-llama | 52.5k | 8.3k | Python | 271 | LlamaIndex is the document processing platform for AIError 500 (Server Error)!!1500.That’s an error.There was an error. Please try again later.That’s all we know. | 2026-10-08 |
| 60 | new-api QuantumNous | 49.7k | 11.9k | Go | 751 | A unified AI model hub for aggregation & distribution. It supports cross-converting various LLMs into OpenAI-compatible, Claude-compatible, or Gemini-compatible formats. A centralized gateway for personal and enterprise model management.Error 500 (Server Error)!!1500.That’s an error.There was an error. Please try again later.That’s all we know. | 2026-10-10 |
| 61 | LocalAI mudler | 49.5k | 4.5k | Go | 95 | LocalAI is the open-source AI engine. Run any model - LLMs, vision, voice, image, video - on any hardware. No GPU required.LocalAI 是开源人工智能引擎。在任何硬件上运行任何模型 - 法学硕士、视觉、语音、图像、视频。无需 GPU。 | 2026-10-11 |
| 62 | JeecgBoot jeecgboot | 48.1k | 16.2k | Java | 33 | 【低代码v2.0，一句话即可生成整个系统】企业级AI低代码平台，一键生成前后端代码甚至整个系统。 AI Skills 一句话画流程、设计表单、生成报表、大屏。内置 AI应用平台涵盖：AI聊天、知识库、流程编排、MCP插件等，兼容主流大模型。引领AI低代码「Skills 生成 → 在线配置 → 代码生成 → 手工合并->AI修改」开发模式，解决 Java 项目 90% 重复工作，提高效率又不失灵活。 | 2026-09-22 |
| 63 | textgen oobabooga | 47.7k | 6.0k | Python | 807 | Open-source desktop app for local LLMs. Text, vision, tool-calling, OpenAI/Anthropic-compatible API. 100% private.适用于本地法学硕士的开源桌面应用程序。文本、视觉、工具调用、OpenAI/Anthropic 兼容 API。 100% 私人。 | 2026-08-17 |
| 64 | CowAgent zhayujie | 47.3k | 10.4k | Python | 17 | Open-source personal AI assistant & Agent Harness. Plans tasks, runs tools and skills, self-evolves with memory and knowledge. Multi-agent, multi-model, multi-channel. Lightweight, extensible, one-line install. | 2026-10-10 |
| 65 | paperless-ngx paperless-ngx | 46.5k | 3.2k | Python | 0 | A community-supported supercharged document management system: scan, index and archive all your documentsError 500 (Server Error)!!1500.That’s an error.There was an error. Please try again later.That’s all we know. | 2026-10-11 |
| 66 | milvus milvus-io | 46.3k | 4.3k | Go | 994 | Milvus is a high-performance, cloud-native vector database built for scalable vector ANN searchMilvus 是一个高性能、云原生的矢量数据库，专为可扩展的矢量 ANN 搜索而构建 | 2026-10-10 |
| 67 | open-code-review alibaba | 45.9k | 3.3k | Go | 119 | Secure, fast, efficient, battle-tested at Alibaba's scale. Hybrid architecture code review tool: deterministic pipelines + LLM Agent, precise line-level comments, built-in multi-language ruleset (NPE, thread-safety, XSS, SQL injection), OpenAI & Anthropic compatible. | 2026-10-10 |
| 68 | jan janhq | 44.9k | 3.1k | Rust | 402 | Jan is an open source alternative to ChatGPT that runs 100% offline on your computer.Jan 是 ChatGPT 的开源替代品，可在您的计算机上 100% 离线运行。 | 2026-10-10 |
| 69 | ray ray-project | 44.0k | 8.1k | Python | 2854 | Ray is an AI compute engine. Ray consists of a core distributed runtime and a set of AI Libraries for accelerating ML workloads.Ray 是一个人工智能计算引擎。 Ray 由一个核心分布式运行时和一组用于加速 ML 工作负载的 AI 库组成。 | 2026-10-10 |
| 70 | langgraph langchain-ai | 43.0k | 7.3k | Python | 573 | Build resilient agents.建立有弹性的代理。 | 2026-10-11 |
| 71 | openhuman tinyhumansai | 41.8k | 4.1k | Rust | 244 | The fastest, cheapest, most efficient open-source agent harness. Run more than 500 agents on a $10 VPS. | 2026-10-11 |
| 72 | AstrBot AstrBotDevs | 41.7k | 3.0k | Python | 1119 | AI Agent Assistant & development framework that integrates lots of IM platforms, LLMs, plugins and AI feature, and can be your openclaw alternative. ✨AI Agent Assistant & 开发框架，集成了大量 IM 平台、LLM、插件和 AI 功能，可以成为您的 openclaw 替代方案。 ✨ | 2026-10-11 |
| 73 | BitNet microsoft | 40.6k | 3.8k | C++ | 214 | Official inference framework for 1-bit LLMs1 位 LLM 的官方推理框架 | 2026-07-27 |
| 74 | LightRAG HKUDS | 40.1k | 5.7k | Python | 211 | [EMNLP2025] LightRAG: Simple and Fast Retrieval-Augmented Generation[EMNLP2025] LightRAG：简单快速的检索增强生成 | 2026-10-08 |
| 75 | ChatTTS 2noise | 39.9k | 4.3k | Python | 59 | A generative speech model for daily dialogue.用于日常对话的生成语音模型。 | 2026-04-10 |
| 76 | quivr The-Vibe-Company | 39.6k | 3.7k | Go | 9 | An open-source engine that turns continuous content streams into search and monitoring. Durable ingestion, hybrid search, alerts, and plugins for formats, models and business rules. | 2026-10-10 |
| 77 | PageIndex VectifyAI | 39.0k | 3.4k | Python | 38 | 📑 PageIndex: Document Index for Vectorless, Reasoning-based RAG📑 PageIndex：无向量、基于推理的 RAG 的文档索引 | 2026-10-10 |
| 78 | langextract google | 38.9k | 2.7k | Python | 72 | A Python library for extracting structured information from unstructured text using LLMs with precise source grounding and interactive visualization.一个 Python 库，用于使用具有精确源基础和交互式可视化的法学硕士从非结构化文本中提取结构化信息。 | 2026-10-10 |
| 79 | Langchain-Chatchat chatchat-space | 38.7k | 6.3k | Python | 11 | Langchain-Chatchat（原Langchain-ChatGLM）基于 Langchain 与 ChatGLM, Qwen 与 Llama 等语言模型的 RAG 与 Agent 应用 | Langchain-Chatchat (formerly langchain-ChatGLM), local knowledge based LLM (like ChatGLM, Qwen and Llama) RAG and Agent app with langchain | 2025-11-10 |
| 80 | ai-engineering-hub patchy631 | 38.3k | 6.3k | Jupyter Notebook | 23 | In-depth tutorials on LLMs, RAGs and real-world AI agent applications.有关法学硕士、RAG 和现实世界人工智能代理应用程序的深入教程。 | 2026-09-10 |
| 81 | CopilotKit CopilotKit | 37.9k | 4.7k | TypeScript | 106 | The Frontend Stack for Agents & Generative UI. React, Angular, Mobile, Slack, and more. Makers of the AG-UI Protocol代理和生成式 UI 的前端堆栈。 React、Angular、Mobile、Slack 等等。 AG-UI协议的制定者 | 2026-10-10 |
| 82 | llmfit AlexsJones | 37.8k | 2.4k | Rust | 35 | Hundreds of models & providers. One command to find what runs on your hardware.数百个模型和提供商。一个命令即可查找您的硬件上运行的内容。 | 2026-10-10 |
| 83 | khoj khoj-ai | 37.6k | 2.5k | Python | 106 | Your AI second brain. Self-hostable. Get answers from the web or your docs. Build custom agents, schedule automations, do deep research. Turn any online or local LLM into your personal, autonomous AI (gpt, claude, gemini, llama, qwen, mistral). Get started - free.你的人工智能第二大脑。可自行托管。从网络或文档中获取答案。构建自定义代理、安排自动化、进行深入研究。将任何在线或本地法学硕士转变为您个人的自主人工智能（gpt、claude、gemini、llama、qwen、mistral）。开始使用 - 免费。 | 2026-08-02 |
| 84 | LLM101n karpathy | 37.5k | 2.1k | N/A | 0 | LLM101n: Let's build a StorytellerLLM101n：让我们构建一个讲故事的人 | 2024-08-01 |
| 85 | prompt-optimizer linshenkx | 37.4k | 4.3k | TypeScript | 6 | An AI prompt optimizer for writing better prompts and getting better AI results.人工智能提示优化器，用于编写更好的提示并获得更好的人工智能结果。 | 2026-10-09 |
| 86 | Vane ItzCrazyKns | 37.2k | 4.1k | TypeScript | 240 | Vane is an AI-powered answering engine.Vane 是一款人工智能驱动的应答引擎。 | 2026-09-01 |
| 87 | one-api songquanpeng | 37.1k | 6.9k | JavaScript | 935 | LLM API 管理 & 分发系统，支持 OpenAI、Azure、Anthropic Claude、Google Gemini、DeepSeek、字节豆包、ChatGLM、文心一言、讯飞星火、通义千问、360 智脑、腾讯混元等主流模型，统一 API 适配，可用于 key 管理与二次分发。单可执行文件，提供 Docker 镜像，一键部署，开箱即用。LLM API management & key redistribution system, unifying multiple providers under a single API. Single binary, Docker-ready, with an English UI.LLM API 管理 & 分发系统，支持 OpenAI、Azure、Anthropic Claude、Google Gemini、DeepSeek、字节豆包、ChatGLM、文心一言、讯飞星火、通义千问、360 智脑、腾讯混元等主流模型，统一 API 适配，可用于 key 管理与二次分发。单可执行文件，提供 Docker 镜像，一键部署，开箱即用。 LLM API management & key redistribution system, unifying multiple providers under a single API. Single binary, Docker-ready, with an English UI. | 2026-01-09 |
| 88 | sglang sgl-project | 37.0k | 9.4k | Python | 930 | SGLang is a high-performance serving framework for large language models and multimodal models.SGLang 是一个用于大型语言模型和多模态模型的高性能服务框架。 | 2026-10-11 |
| 89 | AgentGPT reworkd | 36.3k | 9.2k | TypeScript | 132 | 🤖 Assemble, configure, and deploy autonomous AI Agents in your browser.🤖 在浏览器中组装、配置和部署自主 AI 代理。 | 2025-04-29 |
| 90 | graphrag microsoft | 36.3k | 3.8k | Python | 18 | A modular graph-based Retrieval-Augmented Generation (RAG) system基于模块化图的检索增强生成（RAG）系统 | 2026-10-08 |
| 91 | airllm lyogavin | 36.0k | 3.8k | Jupyter Notebook | 110 | AirLLM 70B inference with single 4GB GPU使用单个 4GB GPU 进行 AirLLM 70B 推理 | 2026-10-10 |
| 92 | DeepSeek-Reasonix esengine | 35.8k | 2.4k | Go | 351 | A reliable coding agent for complex software engineering tasks. | 2026-10-11 |
| 93 | langfuse langfuse | 35.6k | 4.0k | TypeScript | 322 | 🪢 Open source agent evals & observability: Trace, evaluate, and improve LLM applications with one open platform.Error 500 (Server Error)!!1500.That’s an error.There was an error. Please try again later.That’s all we know. | 2026-10-11 |
| 94 | Vibe-Trading HKUDS | 35.2k | 5.7k | Python | 10 | "Vibe-Trading: Your Personal Trading Agent"“Vibe-Trading：您的个人交易代理” | 2026-10-10 |
| 95 | oh-my-pi can1357 | 34.9k | 3.8k | TypeScript | 2180 | ⌥ Coding agent with the IDE wired in. Built by Stencil Labs. | 2026-10-11 |
| 96 | heretic p-e-w | 34.5k | 3.9k | Python | 56 | Fully automatic censorship removal for language models | 2026-10-07 |
| 97 | ChatDev OpenBMB | 34.5k | 4.3k | Python | 54 | ChatDev 2.0: Dev All through LLM-powered Multi-Agent CollaborationChatDev 2.0：通过 LLM 支持的多代理协作进行开发 | 2026-07-24 |
| 98 | book-to-skill virgiliojr94 | 34.5k | 3.6k | Python | 15 | Turn any technical book PDF into a Claude Code skill — ready to study, reference, and use while you work.将任何 PDF 技术书籍转化为 Claude Code 技能 — 可供您在工作时学习、参考和使用。 | 2026-10-05 |
| 99 | SillyTavern SillyTavern | 34.3k | 6.4k | JavaScript | 444 | LLM Frontend for Power Users.面向高级用户的 LLM 前端。 | 2026-10-02 |
| 100 | happy-llm datawhalechina | 34.3k | 3.2k | Jupyter Notebook | 55 | 📚 从零开始构建大模型 | 2026-08-08 |
No repositories match your search
没有匹配的仓库