Top Open Source AI Dev Influencers in December 2024

An automated document analyzer for Paperless-ngx using OpenAI API, Ollama, Deepseek-r1, Azure and all OpenAI API compatible Services to automatically analyze and tag your documents.

Taming Stable Diffusion for Lip Sync!

Open source alternative to Gemini Deep Research. Generate reports with AI based on search results.

All Cursor AI's official download links for both the latest and older versions, making it easy for you to update, downgrade, and choose any version. 🚀

🐵 Preswald is a full-stack platform for building, deploying, and managing interactive data applications. It brings ingestion, storage, transformation, and visualization into a simple SDK, minimizing complexity while maintaining flexibility for both prototyping and production-grade use cases.

This series will take you on a journey from the fundamentals of NLP and Computer Vision to the cutting edge of Vision-Language Models.

English pronunciation correction teacher built with gemini

A free and open source, self hosted Ai based live meeting note taker and minutes summary generator that can completely run in your Local device (Mac OS support is added. Will add windows and linux support soon)

A highly optimized LLM inference acceleration engine for Llama and its variants.

Google AI Studio Starter Apps

Project showcasing Llama 3.3 70B HTML codegen abilities

Minimalist LLM Framework in 100 Lines. Enable LLMs to Program Themselves.

OmniThink: Expanding Knowledge Boundaries in Machine Writing through Thinking

✨ AI interface for tinkerers (Ollama, Haystack RAG, Python)

A framework to enable autonomous android and computer use using any LLM (local or remote)

Vanilla JS web interface for Gemini 2.0 flash-exp Multimodal API with text, audio, camera, screen inputs and audio responses and function calling

Friends of OLMo and their links.

Turn any app into agent knowledge

Codec for paper: LLaSA: Scaling Train-time and Inference-time Compute for LLaMA-based Speech Synthesis

The agentic internet

A lightweight, functional, and composable framework for building AI agents. No PhD required.

Googles NotebookLM but local

Official repo of VLABench, a large scale benchmark designed for fairly evaluating VLA, Embodied Agent, and VLMs.

Code for FreeScale, a tuning-free method for higher-resolution visual generation

Launch monitor using low-cost raspberry pi and camera hardware to determine ball launch speed, angles and spin

uses gpt-4o and gpt-4-mini to write books on topics while researching with perplexity API

[RSS 2024] NaVid: Video-based VLM Plans the Next Step for Vision-and-Language Navigation

VLM-RL: A Unified Vision Language Models and Reinforcement Learning Framework for Safe Autonomous Driving

An iOS and macOS modular web scraping app

MLX Model Manager unifies loading and inferencing with LLMs and VLMs.

TrustEval: A modular and extensible toolkit for comprehensive trust evaluation of generative foundation models (GenFMs)

It's an automatic sign-up for a Windsurf account, so you only need an email address to get unlimited access to windsurf's premium features..这是一个自动注册 Windsurf 账号的工具，你只需要一个邮箱即可无限使用windsurf高级功能。

Remote Sensing Temporal Vision-Language Models: A Comprehensive Survey

A Model Context Protocol (MCP) server providing path-based task management with dependency tracking & more for Large Language Models (LLM) Agents

Dingo: A Comprehensive Data Quality Evaluation Tool

A document analysis tool built with Streamlit and Microsoft MarkItDown. Extract and analyze content from multiple document formats with optional GPT-4o enhancement.

[CVPR'25] SeeGround: See and Ground for Zero-Shot Open-Vocabulary 3D Visual Grounding

A MCP server connecting to a managed index on LlamaCloud

A CLI tool to provide LLM context for coding projects by combining project files into a single text file (or clipboard text) with directory tree structure.

智谱AI 2024年金融行业大模型挑战赛仓库

ChatGPT 中文版：国内免费使用指南及镜像网站推荐（支持 GPT-4o 和 o1）【2025年2月更新】

Emma-X: An Embodied Multimodal Action Model with Grounded Chain of Thought and Look-ahead Spatial Reasoning

AI tools collection for students and researchers. 学生和研究人员的AI工具合集。

LLM Divergent Thinking Creativity Benchmark. LLMs generate 25 unique words that start with a given letter with no connections to each other or to 50 initial random words.

Hacker News Companion - Browser extension

WorkflowAI is an open-source platform where product and engineering teams 
collaborate to build and iterate on AI features.

📊 Research-focused SDXL training framework exploring novel optimization approaches. Goals include enhanced image quality, training stability & comprehensive monitoring. ⭐ Performance-focused research framework.

READ THE README

An experimental project using LLM technology to generate security documentation for Open Source Software (OSS) projects

一些最新逆向demo，目前有爱奇艺、QQ音乐（sign、cookie获取及刷新）、网易云（param、encSecKey及cookie获取)、酷狗(signature)、优酷、剧看看、抖音（a_bogus 192)、小红书（x-s、x-s-common），自备cookie，大模型kimi、deepseek（自备Bearer Token，支持菜单、（是否开启R1深度思考）k1.5\kimi、流式输出、是否开启联网搜索）、讯飞星火（自备cookie，流式输出联网搜索）

The official landing page for Sora Labs.

Roblox Electron Executor is one of the most favorite Roblox Executors at the moment. Before I tell you how to download Electron Executor, let me tell you that it is currently available safely for Windows. But it is not officially available for Android users as of now but the update is coming and will be launched soon.

Generalist Virtual Agents: A Survey on Autonomous Agents Across Digital Platforms

A macOS tool to build long-context prompts for models like OpenAI o1 and Gemini 2.0.

Read and Listen to NeurIPS 2024 Papers

Multi-agent workflows and complex Agent interactions, both via YAML manifest and programmatic usage. Pydantic-AI and LiteLLM backends. Human-in-the-loop integration.

TradeGPT is an intelligent trading bot built with ChatGPT and AI to automate and optimize trading strategies. It analyzes market data, predicts trends, and executes trades in real-time, providing traders with tools to enhance efficiency and profitability.

🤖 AI News Slack Bot | Daily AI tech updates in Slack Channel | Uses GPT-4o, DuckDuckGo & Phidata | Dockerized & Portainer-ready

For SDXL, SD1.5, Flux. Nuke T5 and let CLIP guide Flux.1 on its own! Or let let random guide Flux.1! Or load a CLIP crazy opinion embedding about your image and let that guide the AI!

OctoPrompt is a local based prompt engineer for your codebase. Craft the perfect prompt for modern LLMs.

comfyUI+vscode，两大神器首次跨界融合。集成式AGI大模型开发+AIGC创意平台,苹果OOTB模式,解压即用。comfyUI+vscode， The first cross-border fusion of two major artifacts. Integrated AGI Large Model Development +AIGC Creative Platform, Apple OOTB mode, ready to use for decompression.

Automatically update arXiv papers about LLM Reasoning, LLM Evaluation, LLM & MLLM and Video Understanding using Github Actions.

An open source implementation of NotebookLM that runs on Union

FreeScout module for requests to ChatGPT using latest models

DuckDuckGo AI to API. Chatting with DuckDuckGo AI through API,Free to use gpt-4o-mini, claude-3-haiku, llama-3.1-70b, mixtral-8x7b, etc. Supports continuous dialogue, compatible with OpenAI API format.

AI code editor that enhances developer productivity, bundled with the AI super assistant, ChatLLM.

A tool for evaluating LLMs on the MATH and GSM8K dataset.

This repository showcases how to leverage the capabilities of LLMs to analyze and extract insights from video files or video URLs, including their audio content, offering several configurable parameters, such as the duration for splitting the video, the number of frames to extract per second, frame resizing, and prompts.

Closed-loop evaluation for end-to-end VLM autonomous driving agent

触发关键词 Newyear,把物体绒意年味化！！！一起看看怎么装扮家乡的地标迎接新年吧~

FloTorch is an open-source tool for optimizing Generative AI workloads on AWS. It automates RAG proof-of-concept development with features like hyperparameter tuning, vector database optimization, and LLM integration. FloTorch streamlines experimentation, ensures security, and accelerates production with cost-efficient, validated workflows.

Official impl. of "Promptus: Can Prompts Streaming Replace Video Streaming with Stable Diffusion". A general semantic video communication framework.

Chat offline with open-source LLMs like deepseek-r1, nemotron, qwen, llama and more all through a simple R package powered by Shiny and Ollama. 🚀

Local LLM Discord Bot

Video Generation Benchmark

Document Reader Powered by Gemini AI

Official Python SDK for VLM Run

PaperCheckAI is a cutting-edge, open-source platform-as-a-service leveraging state-of-the-art multimodal large language models (LLMs) to autonomously digitise, interpret, and evaluate handwritten long-form answer sheets in compliance with custom rubrics, ensuring scalable, secure, and explainable AI-driven assessments for educational institutions.

AI-powered code assistant for Vim. OpenAI and ChatGPT plugin for Vim and Neovim, built on top of coc.nvim's extension system, with support for DeepSeek-R1(deepseek-reasoner)

【ChatGPT 中文版】国内镜像网站免费推荐（支持 4o、o1 和 GPT-4）【2025年3月更新】

ML platform for training, versioning, and experimenting with VLM and VLA models at scale

A web interface for GraphRAG. 🚀

Language Model Board, a better way to read the LMSYS results

Mading a LLM chat compoent

dcit201-classroom-lms-LMS created by GitHub Classroom

GLM_vision 是一款适用于 chatgpt-on-wechat 的图像和视频分析插件，基于智谱GLM-4V视觉模型，支持通过URL链接分析图片和视频内容。

Experiments with reasoning models, training techniques, papers

Commify: You Should Commit Yourself. Commify is a CLI tool that generates meaningful, structured commit messages for Git repositories using AI.

Home Assistant custom integration for the Light Manager Air by jb media. Control lights, blinds and other actuators, receive radio signals , and manage scenes through HASS.

An LM forked from my transformer-train-script repo that replaces attention with a novel idea called "matrix recurrent units."

RAG-Diffusion re-implemented in sdxl

implements the methodology outlined in the paper *Cultural Evolution of Cooperation among LLM Agents*. The paper explores whether a society of large language model (LLM) agents can develop cooperative norms through cultural evolution, using the classic *Donor Game*. The goal is to evaluate multi-agent interaction dynamics

Automatically Update LLM Papers Daily using Github Actions. Ref: https://github.com/Vincentqyw/cv-arxiv-daily

LlamaIndex SDK for interacting with the Gen AI Toolbox for Databases.