Top Open Source AI Dev Influencers in July 2024

PDF to Markdown with vision models

📦 Repomix (formerly Repopack) 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.

🚀🚀 「大模型」2小时完全从0训练26M的小参数GPT！🌏 Train a 26M-parameter GPT from scratch in just 2h!

Let AI be your browser operator.

🔍 An LLM-based Multi-agent Framework of Web Search Engine (like Perplexity.ai Pro and SearchGPT)

Open-source Next.js template for building apps that are fully generated by AI. By E2B.

Distributed LLM and StableDiffusion inference for mobile, desktop and server.

In-browser Postgres sandbox with AI assistance (formerly postgres.new)

TensorZero creates a feedback loop for optimizing LLM applications — turning production data into smarter, faster, and cheaper models.

Conquer Any Code in VSCode: One-Click Comments, Conversions, UI-to-Code, and AI Batch Processing of Files! 在 VSCode 中征服任何代码：一键注释、转换、UI 图生成代码、AI 批量处理文件！💪

A simple, easy-to-hack GraphRAG implementation

Local realtime voice AI

GraphRAG using Local LLMs - Features robust API and multiple apps for Indexing/Prompt Tuning/Query/Chat/Visualizing/Etc. This is meant to be the ultimate GraphRAG/KG local LLM app.

Build multimodal language agents for fast prototype and production

An AI personal tutor built with Llama 3.1

A Node.js CLI that uses Ollama and LM Studio models (Llava, Gemma, Llama etc.) to intelligently rename files by their contents

A list of free LLM inference resources accessible via API.

A system for agentic LLM-powered data processing and ETL

AI-native (edge and LLM) proxy for agents. Engineered with fast ⚡️ LLMs for task (query) routing, rich observability, and the seamless integration of prompts with your APIs for agentic tasks. Built by the contributors of Envoy proxy.

MobileLLM Optimizing Sub-billion Parameter Language Models for On-Device Use Cases. In ICML 2024.

Effortlessly run LLM backends, APIs, frontends, and services with one command.

LOTUS: A semantic query engine for fast and easy LLM-powered data processing

Streamlines and simplifies prompt design for both developers and non-technical users with a low code approach.

Minimal LLM inference in Rust

Captcha Bypass using GPT4-o

Prompt chains maximize intelligence and results when using LLMs

This is a project that unifies the management of LLM APIs. It can call multiple backend services through a unified API interface, convert them to the OpenAI format uniformly, and support load balancing. Currently supported backend services include: OpenAI, Anthropic, DeepBricks, OpenRouter, Gemini, Vertex, etc.

A command-line interface for LLMs written in Bash.

Stable-Hair: Real-World Hair Transfer via Diffusion Model (AAAI 2025)

Official JAX implementation of Learning to (Learn at Test Time): RNNs with Expressive Hidden States

The fastest way to bring multi-agent workflows to production.

Implementation of Stable Diffusion with PyTorch

An awesome repository & A comprehensive survey on interpretability of LLM attention heads.

💃 Dance with Intelligence in Your Code. Minuet offers code completion as-you-type from popular LLMs including OpenAI, Gemini, Claude, Ollama, Codestral, and more.

Deploy agentic reasoning in a scalable and reliable platform in minutes. Become an on demand subject matter expert by loading portable cognitive cores for the most complex knowledge work. 🧠

A template project for easily converting Claude AI’s Artifacts into React applications, ready to run out of the box or extend as needed.

End-to-End Local-First Text-to-SQL Pipelines

A package for parsing PDFs and analyzing their content using LLMs.

开箱即用的基于企业私有知识库的LLM大语言模型的智能客服机器人问答系统，支持私有化部署，代码免费开源且可商用，由芝麻小客服官方推出。

A minimal codebase for finetuning large multimodal models, supporting llava-1.5/1.6, llava-interleave, llava-next-video, llava-onevision, llama-3.2-vision, qwen-vl, qwen2-vl, phi3-v etc.

The code for "TokenPacker: Efficient Visual Projector for Multimodal LLM".

LlamaVoice is a llama-based large voice generation model, providing inference and training ability.

Awesome-LLM-KV-Cache: A curated list of 📙Awesome LLM KV Cache Papers with Codes.

参考GraphRag使用 Semantic Kernel 来实现的dotnet版本，可以使用NuGet开箱即用集成到项目中

[NeurIPS 2024] Official Repository of The Mamba in the Llama: Distilling and Accelerating Hybrid Models

AUITestAgent is the first automatic, natural language-driven GUI testing tool for mobile apps, capable of fully automating the entire process of GUI interaction and function verification.

Context-aware structured outputs. Search your documents or the web for specific data and get it back in JSON or Markdown.

💭 一个可二次开发 Chat Bot 单轮对话 Web 端 MVP 原型模板, 基于 Vue 3, Vite 6, TypeScript, Naive UI, Pinia(v3), UnoCSS 等主流技术构建, 🧤简单集成大模型 API, 采用单轮 AI 问答对话模式, 每次提问独立响应, 无需上下文, 支持打字机效果流式输出, 集成 markdown-it 预览, 💼 易于定制和快速搭建 Chat 类大语言模型产品 (附示例截图)

A LLM RAG system runs on your laptop. 大模型检索增强生成系统，可以轻松部署在笔记本电脑上，实现本地知识库智能问答。

List of Stable Diffusion style prompts, optimized for RobMix Zenith.

DenseFusion-1M: Merging Vision Experts for Comprehensive Multimodal Perception

[MM'24 Oral] Prior Knowledge Integration via LLM Encoding and Pseudo Event Regulation for Video Moment Retrieval

Efficiently find the best-suited language model (LM) for your NLP task

Artifacts-like chrome extension for ChatGPT, inspired by Claude 3.5 Sonnet. Requires CSP unblocker for JS to function.

LLM-powered AI guide that leads and drives intelligent conversations

A framework for standardizing evaluations of large foundation models, beyond single-score reporting and rankings.

Finetune Llama-3-8b on the MathInstruct dataset

Creates an index of images, queries a local LLM and adds tags to the image metadata

Quickly create functional plugins from simple descriptions, addressing specific needs without unnecessary bloat.

LLaVA-MORE: Enhancing Visual Instruction Tuning with LLaMA 3.1

Imagine a world where everyone can access powerful AI models—LLMs, generative image models, and speech recognition—directly in their web browser. Integrating AI into daily browsing will revolutionise online interactions, offering instant, intelligent assistance tailored to individual needs.

GPT automatically organizes your browser bookmarks

Generalized Out-of-Distribution Detection and Beyond in Vision Language Model Era: A Survey [Miyai+, arXiv2024]

Providing Duckduckgo AI Chat API, which can use o3-mini for free.

Happy experimenting with MLLM and LLM models!

LLMServingSim: A HW/SW Co-Simulation Infrastructure for LLM Inference Serving at Scale

基于lobe-chat，增加了绘图面板，支持midjourney、dall-e-3，flux，suno，luma，runway，kling(快手可灵)，用户注册登录，充值消费等

Paper collections of multi-modal LLM for Math/STEM/Code.

A LibreOffice Writer extension that adds local-inference generative AI features.

jd_scripts,https://jdc.52hym666.top脚本N100, Nas, awesome双11Nas羊毛docker自动nodejs约i茅台damai秒杀pxq抢票12306工具autojs面板qinglong神器go数据PDF程序tv入门java有趣next博客halo建站API收集python机器人AI一键admin生PT成bot部JD群晖签到WPS自用tgB站ele小白proxy云盘VPN部署lucky饿了么frp基础CDN简单push票星球TikTok纷玩岛fwd一个gpt拼多多小红书美团技术, chatgpt, go,jd, jd_scripts, jd_scripts京东脚本, nginx, php, python, rust, 京东, 代挂, 免费,

本项目展示了如何利用 GPT 自动化检索仓库内的文件（如 PDF、XLS、Word 等）并完成多模态任务。可将家庭摄像头的视频帧送入仓库，可以自动化判断家庭是否危险的事情（利用大模型对世界的理解力）。

Share your claude artifacts❤️

Emotion text classification using Llama3-8b with LoRA and FlashAttention. Based on LLaMA-Factory.

A multi-agent system designed for generating music videos with scrolling subtitles based on lyrics. This project analyzes the lyrics and creates detailed prompts based on the analysis results to generate story-like images, ultimately producing an image-to-image music video, using openai API, gpt-4o and dall-e 3 models.

Dabarqus is incredibly fast RAG that runs everywhere.

wordpress plugin to automatice creation of quality wordpress standard posts using NEWS API , GEMINI AI and Stable Diffusion API for free

用 LLM 和 jina reader 生成的总结

[ECCV 2024] - Improving Zero-shot Generalization of Learned Prompts via Unsupervised Knowledge Distillation

ControlLoRA Version 3: LoRA Is All You Need to Control the Spatial Information of Stable Diffusion.

Run multiple resource-heavy Large Models (LM) on the same machine with limited amount of VRAM/other resources by exposing them on different ports and loading/unloading them on demand

An introduction to the world of AI Agents

The Library for LLM-based web-agent applications

ROS2 nodes for LLM, VLM, VLA

AUTOSAR MCAL Embedded Upskilling Bootcamp by Modular MX.

📱 Compose Multiplatform, 100% UI shared by Compose, generates contents by Gemini

A Python-based virtual assistant using Gemini AI. Features include voice recognition, text-to-speech, weather updates, news retrieval, jokes, Wikipedia info, and music management. Comes with an interactive web interface. Easily extendable and customizable.

The official implementation of the paper "MMInstruct: A High-Quality Multi-Modal Instruction Tuning Dataset with Extensive Diversity". The MMInstruct dataset includes 973K instructions from 24 domains and four instruction types.

Demo of a RAG Question and Answering System with Llama 3.1 and Marqo

This is the official repository for all the code of TheoremLlama

Research tool leveraging LLM for answers

In this project I designed a knowledge graph focused on Napoleon's history. I built a RAG application using this data and improved the output of LLM using the relationship between nodes

PodGPT: An audio-augmented large language model for research and education

CompBench evaluates the comparative reasoning of multimodal large language models (MLLMs) with 40K image pairs and questions across 8 dimensions of relative comparison: visual attribute, existence, state, emotion, temporality, spatiality, quantity, and quality. CompBench covers diverse visual domains, including animals, fashion, sports, and scenes.