| 1 |
dify |
126680 |
19734 |
TypeScript |
441 |
Production-ready platform for agentic workflow development. |
2026-01-21T03:36:50Z |
| 2 |
langchain |
124696 |
20527 |
Python |
223 |
🦜🔗 The platform for reliable agents. |
2026-01-21T01:55:21Z |
| 3 |
open-webui |
121323 |
17112 |
Python |
180 |
User-friendly AI Interface (Supports Ollama, OpenAI API, …) |
2026-01-20T18:28:12Z |
| 4 |
awesome-llm-apps |
88396 |
12671 |
Python |
4 |
Collection of awesome LLM apps with AI Agents and RAG using OpenAI, Anthropic, Gemini and opensource models. |
2026-01-20T02:19:23Z |
| 5 |
ragflow |
71831 |
7898 |
Python |
3059 |
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 LLMs |
2026-01-21T03:31:26Z |
| 6 |
lobe-chat |
70363 |
14437 |
TypeScript |
1005 |
🤯 LobeHub - an open-source, modern design AI Agent Workspace. Supports multiple AI providers, Knowledge Base (file upload / RAG ), one click install MCP Marketplace and Artifacts / Thinking. One-click FREE deployment of your private AI Agent application. |
2026-01-21T03:58:03Z |
| 7 |
Prompt-Engineering-Guide |
69349 |
7403 |
MDX |
160 |
🐙 Guides, papers, lessons, notebooks and resources for prompt engineering, context engineering, RAG, and AI Agents. |
2026-01-16T00:12:04Z |
| 8 |
PaddleOCR |
68473 |
9671 |
Python |
218 |
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. |
2026-01-20T07:15:02Z |
| 9 |
pathway |
57779 |
1551 |
Python |
26 |
Python ETL framework for stream processing, real-time analytics, LLM pipelines, and RAG. |
2026-01-20T16:59:13Z |
| 10 |
llm-app |
54469 |
1284 |
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. |
2026-01-07T11:59:38Z |
| 11 |
anything-llm |
53594 |
5754 |
JavaScript |
250 |
The all-in-one Desktop & Docker AI application with built-in RAG, AI agents, No-code agent builder, MCP compatibility, and more. |
2026-01-20T21:11:37Z |
| 12 |
Flowise |
48405 |
23625 |
TypeScript |
635 |
Build AI Agents, Visually |
2026-01-21T03:01:33Z |
| 13 |
llama_index |
46498 |
6718 |
Python |
249 |
LlamaIndex is the leading framework for building LLM-powered agents over your data. |
2026-01-19T11:50:30Z |
| 14 |
mem0 |
45753 |
5013 |
Python |
376 |
Universal memory layer for AI Agents |
2026-01-13T07:39:14Z |
| 15 |
JeecgBoot |
45055 |
15777 |
Java |
25 |
🔥AI low-code platform empowers enterprises to quickly develop low-code solutions and build AI applications. 助力企业快速实现低代码开发和构建AI应用！ AI应用平台涵盖：AI应用、AI模型、AI聊天助手、知识库、AI流程编排、MCP和插件，聊天式业务操作等。 强大代码生成器：实现前后端一键生成，无需手写代码! 显著提升效率节省成本，又不失灵活~ |
2026-01-20T04:03:03Z |
| 16 |
milvus |
42330 |
3773 |
Go |
779 |
Milvus is a high-performance, cloud-native vector database built for scalable vector ANN search |
2026-01-21T03:45:30Z |
| 17 |
chatgpt-on-wechat |
40710 |
9666 |
Python |
315 |
基于大模型搭建的聊天机器人，同时支持 微信公众号、企业微信应用、飞书、钉钉 等接入，可选择ChatGPT/Claude/DeepSeek/文心一言/讯飞星火/通义千问/ Gemini/GLM-4/Kimi/LinkAI，能处理文本、语音和图片，访问操作系统和互联网，支持基于自有知识库进行定制企业智能客服。 |
2025-10-22T10:32:10Z |
| 18 |
quivr |
38860 |
3721 |
Python |
1 |
Opiniated RAG for integrating GenAI in your apps 🧠 Focus on your product rather than the RAG. Easy integration in existing products with customisation! Any LLM: GPT4, Groq, Llama. Any Vectorstore: PGVector, Faiss. Any Files. Anyway you want. |
2025-07-09T12:55:23Z |
| 19 |
mindsdb |
38294 |
6084 |
Python |
67 |
Federated Query Engine for AI - The only MCP Server you’ll ever need |
2026-01-21T00:31:29Z |
| 20 |
Langchain-Chatchat |
37137 |
6133 |
Python |
21 |
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 |
2025-11-10T09:27:42Z |
| 21 |
khoj |
32232 |
1931 |
Python |
77 |
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. |
2026-01-06T20:15:01Z |
| 22 |
graphrag |
30431 |
3215 |
Python |
36 |
A modular graph-based Retrieval-Augmented Generation (RAG) system |
2026-01-21T01:49:37Z |
| 23 |
LightRAG |
27497 |
3914 |
Python |
161 |
[EMNLP2025] “LightRAG: Simple and Fast Retrieval-Augmented Generation” |
2026-01-19T07:59:17Z |
| 24 |
FastGPT |
26946 |
6894 |
TypeScript |
162 |
FastGPT is a knowledge-based platform built on the LLMs, offers a comprehensive suite of out-of-the-box capabilities such as data processing, RAG retrieval, and visual AI workflow orchestration, letting you easily develop and deploy complex question-answering systems without the need for extensive setup or configuration. |
2026-01-20T07:02:37Z |
| 25 |
ai-engineering-hub |
26910 |
4399 |
Jupyter Notebook |
28 |
In-depth tutorials on LLMs, RAGs and real-world AI agent applications. |
2026-01-10T11:41:19Z |
| 26 |
sim |
25804 |
3223 |
TypeScript |
98 |
Open-source platform to build and deploy AI agent workflows. |
2026-01-21T03:26:50Z |
| 27 |
chroma |
25639 |
2010 |
Rust |
267 |
Open-source search and retrieval database for AI applications. |
2026-01-21T03:20:04Z |
| 28 |
kotaemon |
24853 |
2054 |
Python |
207 |
An open-source RAG-based tool for chatting with your documents. |
2025-07-04T11:31:58Z |
| 29 |
happy-llm |
24670 |
2262 |
Jupyter Notebook |
33 |
📚 从零开始的大语言模型原理与实践教程 |
2026-01-03T03:28:57Z |
| 30 |
RAG_Techniques |
24287 |
2814 |
Jupyter Notebook |
8 |
This repository showcases various advanced techniques for Retrieval-Augmented Generation (RAG) systems. RAG systems combine information retrieval with generative models to provide accurate and contextually rich responses. |
2026-01-19T12:39:02Z |
| 31 |
haystack |
23933 |
2559 |
MDX |
87 |
AI orchestration framework to build customizable, production-ready LLM applications. Connect components (models, vector DBs, file converters) to pipelines or agents that can interact with your data. With advanced retrieval methods, it’s best suited for building RAG, question answering, semantic search or conversational agent chatbots. |
2026-01-20T17:15:47Z |
| 32 |
langgraph |
23553 |
4131 |
Python |
167 |
Build resilient language agents as graphs. |
2026-01-19T06:47:12Z |
| 33 |
pandas-ai |
23049 |
2265 |
Python |
14 |
Chat with your database or your datalake (SQL, CSV, parquet). PandasAI makes data analysis conversational using LLMs and RAG. |
2025-10-28T10:02:13Z |
| 34 |
Scrapegraph-ai |
22334 |
1944 |
Python |
2 |
Python scraper based on AI |
2026-01-20T13:02:34Z |
| 35 |
vanna |
22327 |
2145 |
Python |
218 |
🤖 Chat with your SQL database 📊. Accurate Text-to-SQL Generation via LLMs using Agentic Retrieval 🔄. |
2026-01-19T20:26:05Z |
| 36 |
graphiti |
22152 |
2166 |
Python |
154 |
Build Real-Time Knowledge Graphs for AI Agents |
2026-01-16T19:56:15Z |
| 37 |
crawlee |
21212 |
1156 |
TypeScript |
136 |
Crawlee—A web scraping and browser automation library for Node.js to build reliable crawlers. In JavaScript and TypeScript. Extract data for AI, LLMs, RAG, or GPTs. Download HTML, PDF, JPG, PNG, and other files from websites. Works with Puppeteer, Playwright, Cheerio, JSDOM, and raw HTTP. Both headful and headless mode. With proxy rotation. |
2026-01-20T15:53:02Z |
| 38 |
MaxKB |
19905 |
2598 |
Python |
66 |
🔥 MaxKB is an open-source platform for building enterprise-grade agents. 强大易用的开源企业级智能体平台。 |
2026-01-20T10:33:01Z |
| 39 |
coze-studio |
19562 |
2783 |
TypeScript |
424 |
An AI agent development platform with all-in-one visual tools, simplifying agent creation, debugging, and deployment like never before. Coze your way to AI Agent creation. |
2026-01-20T08:06:49Z |
| 40 |
llama-cookbook |
18160 |
2690 |
Jupyter Notebook |
23 |
Welcome to the Llama Cookbook! This is your go to guide for Building with Llama: Getting started with Inference, Fine-Tuning, RAG. We also show you how to solve end to end problems using Llama model family and using them on various provider services |
2025-11-03T16:25:20Z |
| 41 |
DB-GPT |
18026 |
2528 |
Python |
438 |
AI Native Data App Development framework with AWEL(Agentic Workflow Expression Language) and Agents |
2026-01-20T13:18:20Z |
| 42 |
12-factor-agents |
17821 |
1362 |
TypeScript |
11 |
What are the principles we can use to build LLM-powered software that is actually good enough to put in the hands of production customers? |
2025-09-21T14:37:40Z |
| 43 |
DocsGPT |
17650 |
1983 |
Python |
22 |
Private AI platform for agents, assistants and enterprise search. Built-in Agent Builder, Deep research, Document analysis, Multi-model support, and API connectivity for agents. |
2026-01-16T10:10:29Z |
| 44 |
eliza |
17370 |
5424 |
TypeScript |
95 |
Autonomous agents for everyone |
2026-01-21T03:56:50Z |
| 45 |
opik |
17364 |
1303 |
Python |
83 |
Debug, evaluate, and monitor your LLM applications, RAG systems, and agentic workflows with comprehensive tracing, automated evaluations, and production-ready dashboards. |
2026-01-21T00:28:10Z |
| 46 |
hello-agents |
17184 |
1912 |
Python |
22 |
📚 《从零开始构建智能体》——从零开始的智能体原理与实践教程 |
2026-01-19T01:48:08Z |
| 47 |
onyx |
17089 |
2299 |
Python |
109 |
Open Source AI Platform - AI Chat with advanced features that works with every LLM |
2026-01-21T04:07:06Z |
| 48 |
CV |
16160 |
1890 |
Jupyter Notebook |
15 |
✔（已完结）超级全面的 深度学习 笔记【土堆 Pytorch】【李沐 动手学深度学习】【吴恩达 深度学习】【大飞 大模型Agent】 |
2026-01-12T11:08:33Z |
| 49 |
RagaAI-Catalyst |
16104 |
3673 |
Python |
10 |
Python SDK for Agent AI Observability, Monitoring and Evaluation Framework. Includes features like agent, llm and tools tracing, debugging multi-agentic system, self-hosted dashboard and advanced analytics with timeline and execution graph view |
2026-01-16T19:28:24Z |
| 50 |
LangBot |
14938 |
1260 |
Python |
109 |
Production-grade platform for building IM bots - 生产级多平台 LLM 机器人开发平台. 提供 Agent、知识库编排、插件系统 / Bots for QQ / QQ频道 / Discord / LINE / WeChat(企业微信, 企微智能机器人, 公众号) / Telegram / 飞书 / 钉钉 / Slack e.g. Integrated with ChatGPT(GPT), DeepSeek, Dify, n8n, Langflow, Coze, Claude, Google Gemini, Nano Banana, MiniMax, Ollama, SiliconFlow, Moonshot, Mimo |
2026-01-21T02:33:44Z |
| 51 |
claude-mem |
14701 |
994 |
TypeScript |
75 |
A Claude Code plugin that automatically captures everything Claude does during your coding sessions, compresses it with AI (using Claude’s agent-sdk), and injects relevant context back into future sessions. |
2026-01-18T22:17:11Z |
| 52 |
llmware |
14456 |
2968 |
Python |
66 |
Unified framework for building enterprise RAG pipelines with small, specialized models |
2026-01-11T20:20:29Z |
| 53 |
WrenAI |
13509 |
1468 |
TypeScript |
250 |
⚡️ GenBI (Generative BI) queries any database in natural language, generates accurate SQL (Text-to-SQL), charts (Text-to-Chart), and AI-powered business intelligence in seconds. |
2026-01-19T13:24:00Z |
| 54 |
Qwen-Agent |
12989 |
1219 |
Python |
379 |
Agent framework and applications built upon Qwen>=3.0, featuring Function Calling, MCP, Code Interpreter, RAG, Chrome extension, etc. |
2025-09-26T03:53:35Z |
| 55 |
easy-dataset |
12895 |
1267 |
JavaScript |
109 |
A powerful tool for creating datasets for LLM fine-tuning 、RAG and Eval |
2026-01-18T15:05:15Z |
| 56 |
claude-flow |
12573 |
1540 |
TypeScript |
299 |
🌊 The leading agent orchestration platform for Claude. Deploy intelligent multi-agent swarms, coordinate autonomous workflows, and build conversational AI systems. Features enterprise-grade architecture, distributed swarm intelligence, RAG integration, and native Claude Code support via MCP protocol. Ranked #1 in agent-based frameworks. |
2026-01-21T01:40:05Z |
| 57 |
SurfSense |
12537 |
1097 |
Python |
53 |
Connect any LLM to your internal knowledge sources and chat with it in real time alongside your team. OSS alternative to NotebookLM, Perplexity, and Glean. Join our Discord: https://discord.gg/ejRNvftDp9 |
2026-01-20T11:31:52Z |
| 58 |
memvid |
12527 |
1058 |
Rust |
21 |
Memory layer for AI Agents. Replace complex RAG pipelines with a serverless, single-file memory layer. Give your agents instant retrieval and long-term memory. |
2026-01-18T10:49:01Z |
| 59 |
ragas |
12311 |
1213 |
Python |
254 |
Supercharge Your LLM Application Evaluations 🚀 |
2026-01-19T12:27:19Z |
| 60 |
RAG-Anything |
12226 |
1460 |
Python |
95 |
“RAG-Anything: All-in-One RAG Framework” |
2026-01-13T11:55:35Z |
| 61 |
WeKnora |
12192 |
1348 |
Go |
80 |
LLM-powered framework for deep document understanding, semantic retrieval, and context-aware answers using RAG paradigm. |
2026-01-20T10:19:44Z |
| 62 |
txtai |
12042 |
766 |
Python |
9 |
💡 All-in-one AI framework for semantic search, LLM orchestration and language model workflows |
2026-01-20T02:20:35Z |
| 63 |
Memori |
11825 |
929 |
Python |
37 |
SQL Native Memory Layer for LLMs, AI Agents & Multi-Agent Systems |
2026-01-16T20:35:53Z |
| 64 |
llm-universe |
11592 |
1212 |
Jupyter Notebook |
8 |
本项目是一个面向小白开发者的大模型应用开发教程，在线阅读地址：https://datawhalechina.github.io/llm-universe/ |
2026-01-10T15:46:48Z |
| 65 |
cognee |
10973 |
1024 |
Python |
24 |
Memory for AI Agents in 6 lines of code |
2026-01-20T20:30:09Z |
| 66 |
bisheng |
10962 |
1791 |
TypeScript |
91 |
BISHENG is an open LLM devops platform for next generation Enterprise AI applications. Powerful and comprehensive features include: GenAI workflow, RAG, Agent, Unified model management, Evaluation, SFT, Dataset Management, Enterprise-level System Management, Observability and more. |
2026-01-21T03:33:24Z |
| 67 |
note-gen |
10563 |
763 |
TypeScript |
128 |
A cross-platform Markdown AI note-taking software. |
2026-01-20T05:08:39Z |
| 68 |
langchain4j |
10456 |
1913 |
Java |
558 |
LangChain4j is an open-source Java library that simplifies the integration of LLMs into Java applications through a unified API, providing access to popular LLMs and vector databases. It makes implementing RAG, tool calling (including support for MCP), and agents easy. LangChain4j integrates seamlessly with various enterprise Java frameworks. |
2026-01-20T07:22:04Z |
| 69 |
orama |
10097 |
373 |
TypeScript |
12 |
🌌 A complete search engine and RAG pipeline in your browser, server or edge network with support for full-text, vector, and hybrid search in less than 2kb. |
2025-12-19T22:14:18Z |
| 70 |
promptfoo |
10029 |
880 |
TypeScript |
76 |
Test your prompts, agents, and RAGs. AI Red teaming, pentesting, and vulnerability scanning for LLMs. Compare performance of GPT, Claude, Gemini, Llama, and more. Simple declarative configs with command line and CI/CD integration. |
2026-01-21T04:11:13Z |
| 71 |
LEANN |
9507 |
819 |
Python |
33 |
RAG on Everything with LEANN. Enjoy 97% storage savings while running a fast, accurate, and 100% private RAG application on your personal device. |
2026-01-20T08:59:15Z |
| 72 |
DeepTutor |
9427 |
1227 |
Python |
11 |
“DeepTutor: AI-Powered Personalized Learning Assistant” |
2026-01-21T02:04:12Z |
| 73 |
aichat |
9111 |
600 |
Rust |
22 |
All-in-one LLM CLI tool featuring Shell Assistant, Chat-REPL, RAG, AI Tools & Agents, with access to OpenAI, Claude, Gemini, Ollama, Groq, and more. |
2026-01-06T10:14:26Z |
| 74 |
awesome-ai-apps |
8579 |
1062 |
Python |
23 |
A collection of projects showcasing RAG, agents, workflows, and other AI use cases |
2025-12-30T07:03:52Z |
| 75 |
KAG |
8477 |
653 |
Python |
154 |
KAG is a logical form-guided reasoning and retrieval framework based on OpenSPG engine and LLMs. It is used to build logical reasoning and factual Q&A solutions for professional domain knowledge bases. It can effectively overcome the shortcomings of the traditional RAG vector similarity calculation model. |
2025-12-02T03:25:28Z |
| 76 |
reor |
8467 |
515 |
JavaScript |
111 |
Private & local AI personal knowledge management app for high entropy people. |
2025-05-13T21:28:59Z |
| 77 |
paper-qa |
8009 |
817 |
Python |
126 |
High accuracy RAG for answering questions from scientific documents with citations |
2026-01-16T19:13:04Z |
| 78 |
Upsonic |
7744 |
714 |
Python |
52 |
Agent Framework For Fintech and Banks |
2026-01-20T19:47:03Z |
| 79 |
R2R |
7605 |
625 |
Python |
100 |
SoTA production-ready AI retrieval system. Agentic Retrieval-Augmented Generation (RAG) with a RESTful API. |
2025-11-07T01:02:44Z |
| 80 |
Verba |
7516 |
833 |
Python |
53 |
Retrieval Augmented Generation (RAG) chatbot powered by Weaviate |
2025-07-14T11:24:41Z |
| 81 |
crawlee-python |
7399 |
543 |
Python |
68 |
Crawlee—A web scraping and browser automation library for Python to build reliable crawlers. Extract data for AI, LLMs, RAG, or GPTs. Download HTML, PDF, JPG, PNG, and other files from websites. Works with BeautifulSoup, Playwright, and raw HTTP. Both headful and headless mode. With proxy rotation. |
2026-01-21T02:32:06Z |
| 82 |
awesome-LLM-resources |
7345 |
717 |
None |
0 |
🧑🚀 全世界最好的LLM资料总结（多模态生成、Agent、辅助编程、AI审稿、数据处理、模型训练、模型推理、o1 模型、MCP、小语言模型、视觉语言模型） | Summary of the world’s best LLM resources. |
2026-01-20T06:08:14Z |
| 83 |
deep-searcher |
7332 |
705 |
Python |
40 |
Open Source Deep Research Alternative to Reason and Search on Private Data. Written in Python. |
2025-11-19T06:04:16Z |
| 84 |
vespa |
6733 |
693 |
Java |
220 |
AI + Data, online. https://vespa.ai |
2026-01-20T20:43:30Z |
| 85 |
postgresml |
6676 |
355 |
Rust |
82 |
Postgres with GPUs for ML/AI apps. |
2025-07-01T12:26:02Z |
| 86 |
rags |
6527 |
664 |
Python |
29 |
Build ChatGPT over your data, all with natural language |
2024-04-05T05:36:59Z |
| 87 |
rag-from-scratch |
6336 |
1673 |
Jupyter Notebook |
22 |
None |
2025-06-26T03:16:10Z |
| 88 |
LaVague |
6269 |
572 |
Python |
92 |
Large Action Model framework to develop AI Web Agents |
2025-01-21T13:41:48Z |
| 89 |
refly |
5992 |
580 |
TypeScript |
87 |
Vibe Workflow Platform for Non-technical Creators. |
2026-01-21T04:11:25Z |
| 90 |
cocoindex |
5898 |
432 |
Rust |
50 |
Data transformation framework for AI. Ultra performant, with incremental processing. 🌟 Star if you like it! |
2026-01-21T04:12:49Z |
| 91 |
PageIndex |
5872 |
478 |
Python |
29 |
📑 PageIndex: Document Index for Vectorless, Reasoning-based RAG |
2026-01-08T06:05:21Z |
| 92 |
pyspur |
5657 |
423 |
TypeScript |
26 |
A visual playground for agentic workflows: Iterate over your agents 10x faster |
2025-07-20T19:18:16Z |
| 93 |
pgai |
5626 |
289 |
PLpgSQL |
11 |
A suite of tools to develop RAG, semantic search, and other AI applications more easily with PostgreSQL |
2026-01-16T19:28:55Z |
| 94 |
airweave |
5557 |
678 |
Python |
36 |
Open-source context retrieval layer for AI agents |
2026-01-21T00:46:08Z |
| 95 |
kreuzberg |
5471 |
218 |
HTML |
4 |
A polyglot document intelligence framework with a Rust core. Extract text, metadata, and structured information from PDFs, Office documents, images, and 50+ formats. Available for Rust, Python, Ruby, Java, Go, PHP, Elixir, C#, TypeScript (Node/Bun/Wasm/Deno)- or use via CLI, REST API, or MCP server. |
2026-01-21T03:55:28Z |
| 96 |
genkit |
5381 |
643 |
TypeScript |
634 |
Open-source framework for building AI-powered apps in JavaScript, Go, and Python, built and used in production by Google |
2026-01-21T03:06:38Z |
| 97 |
TaskingAI |
5360 |
355 |
Python |
27 |
The open source platform for AI-native application development. |
2024-12-02T22:18:38Z |
| 98 |
SQLBot |
5304 |
557 |
JavaScript |
64 |
🔥 基于大模型和 RAG 的智能问数系统，对话式数据分析神器。Text-to-SQL Generation via LLMs using RAG. |
2026-01-20T09:07:13Z |
| 99 |
LLMForEverybody |
5258 |
515 |
Jupyter Notebook |
0 |
每个人都能看懂的大模型知识分享，LLMs春/秋招大模型面试前必看，让你和面试官侃侃而谈 |
2026-01-12T12:24:47Z |
| 100 |
superduper |
5248 |
533 |
Python |
26 |
Superduper: End-to-end framework for building custom AI applications and agents. |
2025-09-01T15:20:18Z |