Top 23 Gpt Open-Source Projects

1. AutoGPT

   1 194 187,693 9.9 Python

   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.

   

   Project mention: Agents 101: Reasoning, Actions & Autonomy | dev.to | 2026-05-11

   AutoGPT (agpt.co): Open-source autonomous agent framework, released in 2023. Pioneering example of general-purpose agent architecture; known for demonstrating both promise and limitations of autonomous systems.

2. AppSignal

   www.appsignal.com sponsored

   AppSignal knows why the f*#k it crashed. Stop vibe-debugging. Every exception, every backtrace, grouped so you see patterns, not noise.

   

3. dify

   2 54 158,006 10.0 TypeScript

   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.

   

   Project mention: dify VS cubeplex - a user suggested alternative | libhunt.com/r/dify | 2026-10-09

4. generative-ai-for-beginners

   3 15 121,057 9.6 Jupyter Notebook

   21 Lessons, Get Started Building with Generative AI

   

   Project mention: AI Agents Roadmap 2026: 10 Free Courses in the Right Order | dev.to | 2026-09-30

   Generative AI for Beginners (Microsoft): 21 lessons on prompt engineering, calling LLMs from code, and building chat and search apps. https://github.com/microsoft/generative-ai-for-beginners

5. LLMs-from-scratch

   4 41 106,200 8.2 Jupyter Notebook

   Implement a ChatGPT-like LLM in PyTorch from scratch, step by step

   

   Project mention: What Building Redis, Git and an LLM From Scratch Taught Us About Using Them | dev.to | 2026-10-05

   RAG and agents. LLMs from scratch and Karpathy's Zero to Hero cover tokens, embeddings, attention. Chunking and retrieval choices stop being folklore.

6. vllm

   5 131 93,391 10.0 Python

   A high-throughput and memory-efficient inference and serving engine for LLMs

   

   Project mention: How vLLM CUDA Kernels Write and Read the Paged KV Cache | dev.to | 2026-10-09

   Source: vLLM cache kernels at the referenced commit. The Chinese edition contains the original walkthrough. This DEV edition is a shorter adaptation with a new illustrative mapping example.

7. OpenHands

   6 45 90,449 10.0 TypeScript

   🙌 OpenHands: AI-Driven Development

   

   Project mention: 300+ languages doesn't mean what you think: three tiers of code understanding | dev.to | 2026-08-08

   I am not the first person to look at this. aider evaluated stack-graphs and went with tree-sitter tags plus PageRank instead (#534). So did OpenHands (#742) and SWE-agent (#38). Three serious teams reached the same conclusion: too much work, unmaintained upstream, not worth it.

8. LobeHub

   7 20 83,080 10.0 TypeScript

   The ultimate space for work and life — to find, build, and collaborate with agent teammates that grow with you.

   

   Project mention: Show HN: AI Roundtable – Let 200 models debate your question | news.ycombinator.com | 2026-03-24

   You can set this up yourself with API keys to the corresponding providers and creating an Agent Group in https://github.com/lobehub/lobehub. Agent groups allow you to easily create a room of agents and have them discuss any of your topics. Easily make agents with types and skills, it even assists in drafting starting prompts and even team members depending what your query (and selected model) is.

   You can self-host as well, but not via desktop app. Sever setup required.

   Be careful of your token context, you can easily rack up costs if you leave Opus selected as the model and get lost in some rabbit hole of results.

   Enjoy enjoy!

9. SaaSHub

   www.saashub.com sponsored

   SaaSHub - Software Alternatives and Reviews. SaaSHub helps you find the best software and product alternatives

   

10. LlamaFactory

    8 8 75,363 9.3 Python

    Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024)

    

11. MetaGPT

    9 39 70,766 9.1 Python

    🌟 The Multi-Agent Framework: First AI Software Company, Towards Natural Language Programming

    

12. gpt4free

    10 45 66,764 9.8 Python

    The official gpt4free repository | various collection of powerful language models | opus 4.6 gpt 5.3 kimi 2.5 deepseek v3.2 gemini 3

    

13. awesome-chatgpt-prompts-zh

    11 3 63,191 1.8

    ChatGPT 中文调教指南。各种场景使用指南。学习怎么让它听你的话。

    

14. ChatGPT

    12 54 54,462 5.0 Rust

    ❄️ ChatGPT Desktop Application (Mac, Windows and Linux)

    

    Project mention: ChatGPT VS BotVa - a user suggested alternative | libhunt.com/r/ChatGPT | 2026-03-23

15. jan

    13 52 44,854 9.9 Rust

    Jan is an open source alternative to ChatGPT that runs 100% offline on your computer.

    

    Project mention: Choosing local AI tools for your laptop: five tasks and the setup details to check | dev.to | 2026-09-12

    Jan provides a desktop interface for downloading and chatting with local language models on Windows, macOS and Linux.

16. chatbox

    14 37 41,991 9.8 TypeScript

    Powerful AI Client

    

    Project mention: Open source project chatbox is under attack | news.ycombinator.com | 2026-01-07

17. AstrBot

    15 2 41,611 9.9 Python

    AI Agent Assistant & development framework that integrates lots of IM platforms, LLMs, plugins and AI feature, and can be your openclaw alternative. ✨

    

18. LightRAG

    16 14 40,041 10.0 Python

    [EMNLP2025] LightRAG: Simple and Fast Retrieval-Augmented Generation

    

    Project mention: Why Vector RAG Answers Only Half of a Legal Question: Building a GraphRAG Agent That Follows the Law's Cross-References, in 5 Steps | dev.to | 2026-10-02

    [3] Z. Guo et al., “LightRAG: Simple and Fast Retrieval-Augmented Generation,” arXiv:2410.05779, 2024. https://arxiv.org/abs/2410.05779

19. ChatTTS

    17 4 39,893 6.2 Python

    A generative speech model for daily dialogue.

    

20. Rufus

    18 557 37,855 8.7 C

    The Reliable USB Formatting Utility

    

    Project mention: Lenovo ThinkStation PGX Repair and Multi-GPU Interconnection | dev.to | 2026-09-12

    Reinstalling the OS itself is not difficult, and the Lenovo official link given above is also quite detailed. Here, to prevent some people from being unable to access it due to network issues, I will briefly go over it. Assume you have already downloaded the PGX ISO image file, then download the rufus tool from rufus's GitHub official repository, then insert a USB drive (capacity of at least 16G), open the rufus tool, select the USB drive, then select the downloaded ISO image, leave everything else unchanged at the defaults, then click Start directly

21. one-api

    19 4 37,107 6.9 JavaScript

    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.

    

    Project mention: An Inside Look at the Token Reseller Market | news.ycombinator.com | 2026-07-26

22. graphrag

    20 27 36,275 8.4 Python

    A modular graph-based Retrieval-Augmented Generation (RAG) system

    

    Project mention: From Prompt to Graph Engineering, Explained With One Bug | dev.to | 2026-09-19

    In this example, nodes represent work and edges represent allowed transitions. Microsoft GraphRAG uses a knowledge graph extracted from a corpus to support retrieval and answering. A system can use both, with GraphRAG providing information to a node in an execution workflow. GraphRAG overview

23. awesome-ai-agents

    21 19 30,319 3.4

    A list of AI autonomous agents

    

24. RAG_Techniques

    22 6 29,660 8.7 Jupyter Notebook

    This repository showcases various advanced techniques for Retrieval-Augmented Generation (RAG) systems. Each technique has a detailed notebook tutorial.

    

25. repomix

    23 53 28,740 9.9 TypeScript

    📦 Repomix is a powerful tool that packs your entire repository into a single, AI-friendly file. Perfect for when you need to feed your codebase to Large Language Models (LLMs) or other AI tools like Claude, ChatGPT, DeepSeek, Perplexity, Gemini, Gemma, Llama, Grok, and more.

    

    Project mention: One console.log disconnects your MCP server: the stdout bug every stdio server author hits | dev.to | 2026-09-27

    Real examples: esp-idf#19087, repomix#1866, keycloak-mcp#6.

26. SaaSHub

    www.saashub.com sponsored

    SaaSHub - Software Alternatives and Reviews. SaaSHub helps you find the best software and product alternatives

    

Gpt related posts

• How vLLM CUDA Kernels Write and Read the Paged KV Cache

  1 project | dev.to | 9 Oct 2026

• dify VS cubeplex - a user suggested alternative

  2 projects | 9 Oct 2026

• Running vLLM natively on Windows

  3 projects | dev.to | 8 Oct 2026

• Dify 2026: The Open-Source Platform for Production-Ready AI Workflows

  2 projects | dev.to | 8 Oct 2026

• When Offloading Stalls Inference: Queue Capacity, CUDA Event Ownership, and Misleading Health Checks

  1 project | dev.to | 5 Oct 2026

• vLLM ignores LoRA rank_pattern and alpha_pattern and serves the adapter at the wrong scale

  1 project | dev.to | 3 Oct 2026

• vLLM's weight cache can serve another checkpoint's weights when the tensor layout matches

  1 project | dev.to | 3 Oct 2026
• A note from our sponsor - AppSignal
  www.appsignal.com | 10 Oct 2026

  Stop vibe-debugging. Every exception, every backtrace, grouped so you see patterns, not noise. Learn more →

Index

Sponsored

AppSignal knows why the f*#k it crashed.

Stop vibe-debugging. Every exception, every backtrace, grouped so you see patterns, not noise.

www.appsignal.com