My own open source implementation of OpenAI's new Deep Research agent. Get the same capability without paying $200. You can even tweak the behavior of the agent with adjustable breadth and depth. Run it for 5 min or 5 hours, it'll auto adjust.

YuE: Open Full-song Music Generation Foundation Model, something similar to Suno.ai but open

Witness the aha moment of VLM with less than $3.

Keep searching, reading webpages, reasoning until it finds the answer (or exceeding the token budget)

Solve Visual Understanding with Reinforced VLMs

This repo contains the dataset and code for the paper "SWE-Lancer: Can Frontier LLMs Earn $1 Million from Real-World Freelance Software Engineering?"

An AI chat bot for small and medium-sized teams, supporting models such as Deepseek, Open AI, Claude, and Gemini. 专为中小团队设计的 AI 聊天应用，支持 Deepseek、Open AI、Claude、Gemini 等模型。

推荐使用DeepSeekV3。可以接入微信、QQBot。基于LLM的更逼真的情感陪伴程序。内置了 Atri-My dear moments 的 prompt。Built-in prompt for Atri My dear moments.Support WeChat& QQBot. More realistic emotional companionship program based LLM, meet the characters in your dream.

(Supports DeepSeek R1) An AI-powered research assistant that performs iterative, deep research on any topic by combining search engines, web scraping, and large language models.

Reliable Automation Agents at Scale

AI Pair Programming in Emacs

基于DeepseekR1/Gemini2/GoogleVison2/GoogleSearch API实现的深度思考联网多模态大模型。

Extend OpenRLHF to support LMM RL training for reproduction of DeepSeek-R1 on multimodal tasks.

Local LLM Powered Recursive Search & Smart Knowledge Explorer

Dive is an open-source AI Agent desktop application that seamlessly integrates any Tools Call-supported LLM with frontend MCP Server—part of the Open Agent Platform initiative.

Community maintained hardware plugin for vLLM on Ascend

My own open source implementation of OpenAI's new Deep Research agent. Get the same capability without paying $200. You can even tweak the behavior of the agent with adjustable breadth and depth. Run it for 5 min or 5 hours, it'll auto adjust.

Witness the aha moment of VLM with less than $3.

Solve Visual Understanding with Reinforced VLMs

This repo contains the dataset and code for the paper "SWE-Lancer: Can Frontier LLMs Earn $1 Million from Real-World Freelance Software Engineering?"

An AI chat bot for small and medium-sized teams, supporting models such as Deepseek, Open AI, Claude, and Gemini. 专为中小团队设计的 AI 聊天应用，支持 Deepseek、Open AI、Claude、Gemini 等模型。

推荐使用DeepSeekV3。可以接入微信、QQBot。基于LLM的更逼真的情感陪伴程序。内置了 Atri-My dear moments 的 prompt。Built-in prompt for Atri My dear moments.Support WeChat& QQBot. More realistic emotional companionship program based LLM, meet the characters in your dream.

(Supports DeepSeek R1) An AI-powered research assistant that performs iterative, deep research on any topic by combining search engines, web scraping, and large language models.

Reliable Automation Agents at Scale

AI Pair Programming in Emacs

基于DeepseekR1/Gemini2/GoogleVison2/GoogleSearch API实现的深度思考联网多模态大模型。

Extend OpenRLHF to support LMM RL training for reproduction of DeepSeek-R1 on multimodal tasks.

Local LLM Powered Recursive Search & Smart Knowledge Explorer

[arXiv] On-device Sora: Enabling Diffusion-Based Text-to-Video Generation for Mobile Devices

🔬 Visualize attention layers from Stable Diffusion

SOTA RL fine-tuning solution for advanced math reasoning of LLM

fine-tune deepseek r1

YuE: Open Full-song Music Generation Foundation Model, something similar to Suno.ai but open

A GUI Agent application based on UI-TARS(Vision-Lanuage Model) that allows you to control your computer using natural language.

Keep searching, reading webpages, reasoning until it finds the answer (or exceeding the token budget)

A fast Rust based tool to serialize text-based files in a repository or directory for LLM consumption

Run local LLMs like llama, deepseek-distill, kokoro and more inside your browser

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

Dive is an open-source AI Agent desktop application that seamlessly integrates any Tools Call-supported LLM with frontend MCP Server—part of the Open Agent Platform initiative.

Community maintained hardware plugin for vLLM on Ascend

Run Stable Diffusion on Android Devices with Snapdragon NPU acceleration. Also supports CPU inference.

Are VLMs Ready for Autonomous Driving? An Empirical Study from the Reliability, Data, and Metric Perspectives

Multi-Agent Step Race Benchmark: Assessing LLM Collaboration and Deception Under Pressure. A multi-player “step-race” that challenges LLMs to engage in public conversation before secretly picking a move (1, 3, or 5 steps). Whenever two or more players choose the same number, all colliding players fail to advance.

AIN - The First Arabic Inclusive Large Multimodal Model. It is a versatile bilingual LMM excelling in visual and contextual understanding across diverse domains.

Demonstrates how to build a streaming enterprise agent using Azure AI Agent Service. This sample integrates local HR and company policy documents, Bing for external context, and GPT-4o (though the service is model-agnostic) to deliver real-time Q&A and automated workflows.

高质量的思科模拟器汉化 CiscoPacketTracerChinese 通过使用智谱清言的 glm-4-plus 大模型 进行翻译，并结合后期人工矫正，达到了前所未有的汉化质量。

PageRank for LLMs

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

🐵 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.

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

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

Turn any app into agent knowledge

The agentic internet

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

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

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

English pronunciation correction teacher built with gemini

An iOS and macOS modular web scraping app

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

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

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

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

Unifying 3D Mesh Generation with Language Models

We present StableAnimator, the first end-to-end ID-preserving video diffusion framework, which synthesizes high-quality videos without any post-processing, conditioned on a reference image and a sequence of poses.

[768 Resolution] [Any "SDXL" Model] [Various Conditions] [Arbitrary Views] Official impl. of "MV-Adapter: Multi-view Consistent Image Generation Made Easy"

A hub for various industry-specific schemas to be used with VLMs.

CodeGate: CodeGen Privacy and Security

A Survey of Spoken Dialogue Models (60 pages)

$10/month GPT-4o and Claude-3.5-Sonnet APIs for coding and beyond.

LLM4AD: A Platform for Algorithm Design with Large Language Model

GLM Series Edge Models

一个轻量级、支持全链路且易于二次开发的大模型应用项目 支持DeepSeek/Qwen2等大模模型 基于 Dify 、Ollama&Vllm、Sanic 和 Text2SQL 📊 等技术构建的一站式大模型应用开发项目，采用 Vue3、TypeScript 和 Vite 5 打造现代UI。它支持通过 ECharts 📈 实现基于大模型的数据图形化问答，具备处理 CSV 文件 📂 表格问答的能力。同时，能方便对接第三方开源 RAG 系统 检索系统 🌐等，以支持广泛的通用知识问答。

Benchmarking Agentic LLM and VLM Reasoning On Games

Implementation of the board game Codenames, re-imagined as a collaborative game between LLM agents

The PyVisionAI Official Repo

Enhance and modify high-quality compositions using real-time rendering and generative AI output without affecting a hero product asset.

SDXL Training Improvements

A most Frontend Collection and survey of vision-language model papers, and models GitHub repository

Make websites accessible for AI agents

"LightRAG: Simple and Fast Retrieval-Augmented Generation"

📃 A better UX for chat, writing content, and coding with LLMs.

veRL: Volcano Engine Reinforcement Learning for LLM

GLM-4-Voice | 端到端中英语音对话模型

Document (PDF, Word, PPTX ...) extraction and parse API using state of the art modern OCRs + Ollama supported models. Anonymize documents. Remove PII. Convert any document or picture to structured JSON or Markdown

Towards Open-source GPT-4o with Vision, Speech and Duplex Capabilities。

The world's smartest system-wide grammar assistant; a better version of the Apple Intelligence Writing Tools. Works on Windows, Linux, & macOS, with the free Gemini API, local LLMs, & more.

Vim plugin for LLM-assisted code/text completion

Use ChatGpt 4o forFree - No API Key Need. also ChatGpt 3 and ChatGpt 3.5 Experience the power of ChatGPT with a user-friendly interface, enhanced jailbreaks, and completely free.

An Open Source implementation of Notebook LM with more flexibility and features

Large Reasoning Models

Azure OpenAI code resources for using gpt-4o-realtime capabilities.

实时语音交互数字人，支持端到端语音方案（GLM-4-Voice - THG）和级联方案（ASR-LLM-TTS-THG）。可自定义形象与音色，无须训练，支持音色克隆，首包延迟低至3s。Real-time voice interactive digital human, supporting end-to-end voice solutions (GLM-4-Voice - THG) and cascaded solutions (ASR-LLM-TTS-THG). Customizable appearance and voice, supporting voice cloning, with initial package delay as low as 3s.

Parsing-free RAG supported by VLMs

Chat with your documents using Vision Language Models. This repo implements an End to End RAG pipeline with both local and proprietary VLMs

A collection of LLM papers, blogs, and projects, with a focus on OpenAI o1 🍓 and reasoning techniques.

g1: Using Llama-3.1 70b on Groq to create o1-like reasoning chains

LLaMA-Omni is a low-latency and high-quality end-to-end speech interaction model built upon Llama-3.1-8B-Instruct, aiming to achieve speech capabilities at the GPT-4o level.

An Open Source Python alternative to NotebookLM's podcast feature: Transforming Multimodal Content into Captivating Multilingual Audio Conversations with GenAI

An AI-powered file management tool that ensures privacy by organizing local texts, images. Using Llama3.2 3B and Llava v1.6 models with the Nexa SDK, it intuitively scans, restructures, and organizes files for quick, seamless access and easy retrieval.

Graph UI for visualizing AI agent trajectories in Python

Kodu is an autonomous coding agent that lives in your IDE. It is a VSCode extension that can help you build your dream project step by step by leveraging the latest technologies in automated coding agents

🚀 「大模型」1小时从0训练26M参数的视觉多模态VLM！🌏 Train a 26M-parameter VLM from scratch in just 1 hours!

BaseAI — The Web AI Framework. The easiest way to build serverless autonomous AI agents with memory. Start building local-first, agentic pipes, tools, and memory. Deploy serverless with one command.

这是一份入门AI/LLM大模型的逐步指南，包含教程和演示代码，带你从API走进本地大模型部署和微调，代码文件会提供Kaggle或Colab在线版本，即便没有显卡也可以进行学习。项目中还开设了一个小型的代码游乐场🎡，你可以尝试在里面实验一些有意思的AI脚本。同时，包含李宏毅 (HUNG-YI LEE）2024生成式人工智能导论课程的完整中文镜像作业。

Browser automation system that uses AI-driven planning to navigate web pages and perform goals.

Dynamiq is an orchestration framework for agentic AI and LLM applications

Hexabot is an open-source AI chatbot / agent builder. It allows you to create and manage multi-channel and multilingual chatbots / agents with ease.

Use LLMs and LLM Vision (OCR) to handle paperless-ngx - Document Digitalization powered by AI

LLM notes, including model inference, transformer model structure, and llm framework code analysis notes.

Jobs_Applier_AI_Agent_AIHawk aims to easy job hunt process by automating the job application process. Utilizing artificial intelligence, it enables users to apply for multiple jobs in a tailored way.

Official inference framework for 1-bit LLMs

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

an open source, extensible AI agent that goes beyond code suggestions - install, execute, edit, and test with any LLM

Scira (Formerly MiniPerplx) is a minimalistic AI-powered search engine that helps you find information on the internet. Powered by Vercel AI SDK! Search with models like Grok 2.0.

Efficient Triton Kernels for LLM Training

利用AI大模型，一键解说并剪辑视频； Using AI models to automatically provide commentary and edit videos with a single click.

Optimizing inference proxy for LLMs

Laminar - open-source all-in-one platform for engineering AI products. Crate data flywheel for you AI app. Traces, Evals, Datasets, Labels. YC S24.

A Powerful web scraper powered by LLM | OpenAI, Gemini & Ollama

The TypeScript AI framework.

nanoGPT style version of Llama 3.1

Chat with any codebase in under two minutes | Fully local or via third-party APIs

Lightweight library for scraping web-sites with LLMs

ROSA 🤖 is an AI Agent designed to interact with ROS1- and ROS2-based robotics systems using natural language queries. ROSA helps robot developers inspect, diagnose, understand, and operate robots.

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

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

A list of free LLM inference resources accessible via API.

library & platform to build, distribute, monetize ai apps that have the full context (like rewind, granola, etc.), open source, 100% local, developer friendly. 24/7 screen, mic, keyboard recording and control

Utilities intended for use with Llama models.

TEN Agent is a conversational AI powered by the TEN, integrating Gemini 2.0 Live, OpenAI Realtime, RTC, and more. It delivers real-time capabilities to see, hear, and speak, while being fully compatible with popular workflow platforms like Dify and Coze.

一本 GPT4 生成的单词书📚，超过 8000 个单词分析，涵盖了词义、例句、词根词缀、变形、文化背景、记忆技巧和小故事

A framework for serving and evaluating LLM routers - save LLM costs without compromising quality

Using GPT to parse PDF

ETL, Analytics, Versioning for Unstructured Data

SwarmUI (formerly StableSwarmUI), A Modular Stable Diffusion Web-User-Interface, with an emphasis on making powertools easily accessible, high performance, and extensibility.

Cambrian-1 is a family of multimodal LLMs with a vision-centric design.

Autoregressive Model Beats Diffusion: 🦙 Llama for Scalable Image Generation

Latitude is the open-source prompt engineering platform to build, evaluate, and refine your prompts with AI

The code used to train and run inference with the ColPali architecture.

Things you can do with the token embeddings of an LLM

Agentless🐱: an agentless approach to automatically solve software development problems

A toolkit to create optimal Production-readyRetrieval Augmented Generation(RAG) setup for your data

LLM101n: Let's build a Storyteller

🚀🤖 Crawl4AI: Open-source LLM Friendly Web Crawler & Scraper

🍒 Cherry Studio is a desktop client that supports for multiple LLM providers. Support deepseek-r1

llama3 implementation one matrix multiplication at a time

Task oriented AI agent framework for digital workers and vertical AI agents

GLM-4 series: Open Multilingual Multimodal Chat LMs | 开源多语言多模态对话模型

File Parser optimised for LLM Ingestion with no loss 🧠 Parse PDFs, Docx, PPTx in a format that is ideal for LLMs.

A self-organizing file system with llama 3

A suite of tools to develop RAG, semantic search, and other AI applications more easily with PostgreSQL

A fast multimodal LLM for real-time voice

AI一键批量生成各类短视频,自动批量混剪短视频,自动把视频发布到抖音,快手,小红书,视频号上,赚钱从来没有这么容易过! 支持本地语音模型chatTTS,fasterwhisper,GPTSoVITS,支持云语音：Azure,阿里云,腾讯云。支持Stable diffusion,comfyUI直接AI生图。Generate short videos with one click using AI LLM,print money together! support:chatTTS,faster-whisper,GPTSoVITS,Azure,tencent Cloud,Ali Cloud.

Deploy your agentic worfklows to production

llama3.np is a pure NumPy implementation for Llama 3 model.

Generate music based on natural language prompts using LLMs running locally

We introduced a new model designed for the Code generation task. Its test accuracy on the HumanEval base dataset surpasses that of GPT-4 Turbo (April 2024) and GPT-4o.

Practice to LLM.

LLM training in simple, raw C/CUDA

🔥 Turn entire websites into LLM-ready markdown or structured data. Scrape, crawl and extract with a single API.

Collection of awesome LLM apps with AI Agents and RAG using OpenAI, Anthropic, Gemini and opensource models.

SWE-agent takes a GitHub issue and tries to automatically fix it, using GPT-4, or your LM of choice. It can also be employed for offensive cybersecurity or competitive coding challenges. [NeurIPS 2024]

FreeAskInternet is a completely free, PRIVATE and LOCALLY running search aggregator & answer generate using MULTI LLMs, without GPU needed. The user can ask a question and the system will make a multi engine search and combine the search result to LLM and generate the answer based on search results. It's all FREE to use.

Convert any URL to an LLM-friendly input with a simple prefix https://r.jina.ai/

A new DSL and server for AI agents and multi-step tasks

《动手学大模型Dive into LLMs》系列编程实践教程

Llama3、Llama3.1 中文仓库（随书籍撰写中... 各种网友及厂商微调、魔改版本有趣权重 & 训练、推理、评测、部署教程视频 & 文档）

The easiest way to use Agentic RAG in any enterprise

🧑‍🚀 全世界最好的LLM资料总结（数据处理、模型训练、模型部署、o1 模型、小语言模型、视觉语言模型） | Summary of the world's best LLM resources.

Utilize the unlimited free GPT-3.5-Turbo API service provided by the login-free ChatGPT Web.

Turn any webpage into structured data using LLMs

🔍 AI search engine - self-host with local or cloud LLMs

Implementation for MatMul-free LM.

《大语言模型》作者：赵鑫，李军毅，周昆，唐天一，文继荣

🙌 OpenHands: Code Less, Make More

The official Meta Llama 3 GitHub site

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

An LLM-powered knowledge curation system that researches a topic and generates a full-length report with citations.

利用AI大模型，一键生成高清短视频 Generate short videos with one click using AI LLM.

An open-source RAG-based tool for chatting with your documents.

Examples and guides for using the Gemini API

🤖 Open-source GenBI AI Agent that empowers data-driven teams to chat with their data to generate Text-to-SQL, charts, spreadsheets, reports, and BI. 📈📊📋🧑‍💻

LLocalSearch is a completely locally running search aggregator using LLM Agents. The user can ask a question and the system will use a chain of LLMs to find the answer. The user can see the progress of the agents and the final answer. No OpenAI or Google API keys are needed.

Build a Perplexity-Inspired Answer Engine Using Next.js, Groq, Llama-3, Langchain, OpenAI, Upstash, Brave & Serper

A CLI tool to convert your codebase into a single LLM prompt with source tree, prompt templating, and token counting.

🚀 KIMI AI 长文本大模型逆向API【特长：长文本解读整理】，支持高速流式输出、智能体对话、联网搜索、探索版、K1思考模型、长文档解读、图像解析、多轮对话，零配置部署，多路token支持，自动清理会话痕迹，仅供测试，如需商用请前往官方开放平台。

🤖 𝗟𝗲𝗮𝗿𝗻 for 𝗳𝗿𝗲𝗲 how to 𝗯𝘂𝗶𝗹𝗱 an end-to-end 𝗽𝗿𝗼𝗱𝘂𝗰𝘁𝗶𝗼𝗻-𝗿𝗲𝗮𝗱𝘆 𝗟𝗟𝗠 & 𝗥𝗔𝗚 𝘀𝘆𝘀𝘁𝗲𝗺 using 𝗟𝗟𝗠𝗢𝗽𝘀 best practices: ~ 𝘴𝘰𝘶𝘳𝘤𝘦 𝘤𝘰𝘥𝘦 + 12 𝘩𝘢𝘯𝘥𝘴-𝘰𝘯 𝘭𝘦𝘴𝘴𝘰𝘯𝘴

Run PyTorch LLMs locally on servers, desktop and mobile

DeepSeek-VL: Towards Real-World Vision-Language Understanding

Devon: An open-source pair programmer

🙌 OpenHands: Code Less, Make More

1 min voice data can also be used to train a good TTS model! (few shot voice cloning)

🚀🤖 Crawl4AI: Open-source LLM Friendly Web Crawler & Scraper

The official Meta Llama 3 GitHub site

Make websites accessible for AI agents

Jobs_Applier_AI_Agent_AIHawk aims to easy job hunt process by automating the job application process. Utilizing artificial intelligence, it enables users to apply for multiple jobs in a tailored way.

LLM training in simple, raw C/CUDA

🔥 Turn entire websites into LLM-ready markdown or structured data. Scrape, crawl and extract with a single API.

An LLM-powered knowledge curation system that researches a topic and generates a full-length report with citations.

利用AI大模型，一键生成高清短视频 Generate short videos with one click using AI LLM.

An open-source RAG-based tool for chatting with your documents.

Collection of awesome LLM apps with AI Agents and RAG using OpenAI, Anthropic, Gemini and opensource models.

SWE-agent takes a GitHub issue and tries to automatically fix it, using GPT-4, or your LM of choice. It can also be employed for offensive cybersecurity or competitive coding challenges. [NeurIPS 2024]

Composio equip's your AI agents & LLMs with 100+ high-quality integrations via function calling

🍒 Cherry Studio is a desktop client that supports for multiple LLM providers. Support deepseek-r1

llama3 implementation one matrix multiplication at a time