Top Open Source AI Dev Influencers in July 2024

PDF to Markdown with vision models

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

📦 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, and Gemini.

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

「大模型」3小时完全从0训练26M的小参数GPT，个人显卡即可推理训练！

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

In-browser Postgres sandbox with AI assistance

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！💪

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.

A simple, easy-to-hack GraphRAG implementation

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

An AI personal tutor built with Llama 3.1

A Multimodal Native Agent Framework for Smart Hardware and More

A system for agentic LLM-powered data processing and ETL

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

Minimal LLM inference in Rust

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

Captcha Bypass using GPT4-o

Arch is an intelligent prompt gateway. Engineered with (fast) LLMs for the secure handling, robust observability, and seamless integration of prompts with your APIs - outside business logic. Built by the core contributors of Envoy proxy, on Envoy.

A list of free LLM inference resources accessible via API.

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

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

An AI-powered automation SDK can control the page, perform assertions, and extract data in JSON format using natural language.

LOTUS: A semantic query engine - process data with LLMs as easily as writing pandas code

A command-line interface for LLMs written in Bash.

Stable-Hair: Real-World Hair Transfer via Diffusion Model

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

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.

Prompt chains maximize intelligence and results when using LLMs

Implementation of Stable Diffusion with PyTorch

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

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

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

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

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

A React-based web app project that enables running Claude AI’s Artifacts either locally or on your own server.

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

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

Connect Data Silos with Explainable AI⚡🚀

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

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

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。

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.

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

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

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

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

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

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

💃 Dance with Intelligence in Your Code. Minuet AI integrates with nvim-cmp, offering AI completion from popular LLMs including OpenAI, Gemini, Claude, and more.

Finetune Llama-3-8b on the MathInstruct dataset

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

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

LLaVA-MORE: Enhancing Visual Instruction Tuning with LLaMA 3.1

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）。

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

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

LLM-powered AI guide that leads and drives intelligent conversations

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

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,

Providing Duckduckgo AI Chat API, which can use gpt-4o-mini for free.

Share your claude artifacts❤️

💭 一个可二次开发 Chat Bot 对话 Web 端 MVP 原型模板, 基于 Vue3、Vite 5、TypeScript、Naive UI 、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)

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

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.

用 LLM 和 jina reader 生成的总结

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

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

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，后续支持stable-diffusion，充值消费等

Large Model Proxy is designed to make it easy to run multiple resource-heavy Large Models (LM) on the same machine with limited amount of VRAM/other resources. It listens on a dedicated port for each proxied LM, making them always available to the clients connecting to these ports.

Happy experimenting with MLLM and LLM models!

Dabarqus is a stand alone application that implements a complete RAG solution.

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

AUTOSAR MCAL Embedded Upskilling Bootcamp by Modular MX.

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。

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.

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

ROS2 nodes for LLM, VLM, VLA

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

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

The Library for LLM-based web-agent applications

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.

This is the official repository for all the code of TheoremLlama

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.

[ACMMM'2024] Generative Expressive Conversational Speech Synthesis

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

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: A multilingual audio-augmented large language model for research and education

Use Codestral Mamba with Visual Studio Code and the Continue extension. A local LLM alternative to GitHub Copilot.

A simple chat bot to play with Llama 3.1

Let's RAG it RAW without fancy frameworks