An open-source AI agent that brings the power of Gemini directly into your terminal.

Get started with building Fullstack Agents using Gemini 2.5 and LangGraph

An open-source, code-first Python toolkit for building, evaluating, and deploying sophisticated AI agents with flexibility and control.

Open Source DeepWiki: AI-Powered Wiki Generator for GitHub/Gitlab/Bitbucket Repositories. Join the discord: https://discord.gg/gMwThUMeme

The simplest, fastest repository for training/finetuning small-sized VLMs.

PandaWiki 是一款 AI 大模型驱动的开源知识库搭建系统，帮助你快速构建智能化的 产品文档、技术文档、FAQ、博客系统，借助大模型的力量为你提供 AI 创作、AI 问答、AI 搜索等能力。

Klavis AI (YC X25): Open Source MCP integration for AI applications

Open Source TypeScript AI Agent Framework

The power of Claude Code + [Gemini Pro / Flash / O3 / Grok / OpenRouter / Ollama / Custom Model / All Of The Above] working as one.

A model-driven approach to building AI agents in just a few lines of code.

A SOTA open-source image editing model, which aims to provide comparable performance against the closed-source models like GPT-4o and Gemini 2 Flash.

Nexent is a zero-code platform for developing intelligent agents — no orchestration, no complex drag-and-drop required. Built on the MCP tool ecosystem, Nexent also offers powerful capabilities for model integration, data processing, and knowledge base management.

A Model Context Protocol (MCP) Gateway & Registry. Serves as a central management point for tools, resources, and prompts that can be accessed by MCP-compatible LLM applications. Converts REST API endpoints to MCP, composes virtual MCP servers with added security and observability, and converts between protocols (stdio, SSE, Streamable HTTP).

Open-source platform for AI-driven storytelling, worldbuilding, and immersive roleplay

Atropos is a Language Model Reinforcement Learning Environments framework for collecting and evaluating LLM trajectories through diverse environments

The world's first Full-Stack Open-Source General AI Agent

Implementing DeepSeek R1's GRPO algorithm from scratch

Live speech translation application built with Electron 34 and React, using OpenAI's Realtime API.

VLM-3R: Vision-Language Models Augmented with Instruction-Aligned 3D Reconstruction

An example agent demonstrating streaming, tool use, and interactivity from your terminal. This agent builder can help you to build your own agents and tools.

Local LLM Server with GPU and NPU Acceleration

A set of tools that gives agents powerful capabilities.

Pixel-Level Reasoning Model trained with RL

Adapting VLMs to Bench2Drive.

Most intuitive Stable Diffusion WebUI for AI artists, developers & researchers

Agent samples built using the Strands Agents SDK.

CHATS: Combining Human-Aligned Optimization and Test-Time Sampling for Text-to-Image Generation (ICML2025)

Code for the paper "VTool-R1: VLMs Learn to Think with Images via Reinforcement Learning on Multimodal Tool Use"

Voice AI agent starter kit with Groq, Llama 4, and (optionally) Twilio

This MCP server provides documentation about Strands Agents to your GenAI tools, so you can use your favorite AI coding assistant to vibe-code Strands Agents.

Machine Mental Imagery: Empower Multimodal Reasoning with Latent Visual Tokens (arXiv 2025)

Create high-quality visual content with Sora and GPT-Image-1 on Azure OpenAI

eShopLite is a set of reference .NET applications implementing an eCommerce site with features like Semantic Search, MCP, Reasoning models and more.

Documentation for the Strands Agents SDK. A model-driven approach to building AI agents in just a few lines of code.

Herobot is your 24/7 customer service assistant that helps you manage multi-channel customer conversations effortlessly.

Helm charts for llm-d

The Operating System for Agents

Take your LLM to the optometrist.

A Model Context Protocol (MCP) server that enables AI assistants to generate images, text, and audio through the Pollinations APIs. Supports customizable parameters, image saving, and multiple model options.

Professional Load Testing for Any OpenAI-Compatible LLM API

A RAG (Retrieval-Augmented Generation) solution Based on Pre-generated QA Pairs. 基于预生成 QA 对的 RAG 知识库解决方案

First-of-its-kind benchmark for evaluating the protection capabilities of large language model (LLM) guard systems

An external provider for Llama Stack allowing for the use of RamaLama for inference.

system prompts of LLMs, AI Tools, AI Products, DeepSeek,ChatGPT, Gemini, Grok, Qwen

🤖 A composable framework for building AI applications.

Sec-Gemini v1 is a cutting-edge AI model designed to enhance cybersecurity capabilities and empower defenders in the ongoing battle against cyber threats.

A framework for training diffusion models with stable, self-consistent scores near the data distribution.

This repository hosts the instructions and workshop materials for Lab 331 (Deep Research with Langchain and DeepSeek R1) for Microsoft Build

Synthetic Dialog Generation and Analysis with LLMs

Library for text-to-text regression, applicable to any input string representation and allows pretraining and fine-tuning over multiple regression tasks.

Everything you need to build, deploy, and collaborate with agents. Ride the llama, avoid the drama.

versatile AI platform that lets users create custom AI models via API, enabling chatbots, image generation, coding assistance, and video creation all in one integrated interface.

[ATC'25] Katz is a high-performance serving system designed specifically for diffusion model workflows with multiple adapters.

Run Llama 3.3, DeepSeek-R1, Phi-4, Gemma 3, Mistral Small 3.1, and other state-of-the-art language models locally with scorching-fast performance. Inferno provides an intuitive CLI and an OpenAI/Ollama-compatible API, putting the inferno of AI innovation directly in your hands.

This is a repository for the AgentX project "Improving LLM Agents With Reinforcement Learning on Cryptographic CTF Challenges"

This sample shows how to implement a deep researcher with DeepSeek R1

Official implementation of VLMLight

unsloth vlm grpo

OneSDK: A unified AI access SDK for edge devices, providing LLM capabilities (text/voice chat, image generation) and IoT device management with MQTT support, compatible with ESP32, Linux, macOS, and Windows platforms.

⽊ ongoing list of curated resources for decentralized AI and LLMs, with a focus on agents, blockchains, and privacy 🏴‍☠️

An AI development platform that allows users to build custom AI models through an API, supporting chatbots, music generation, and coding tools to streamline creative and technical workflows.

a lua runtime for vibecoding

​​LibRAG​​: A next-gen intelligent content retrieval engine that redefines traditional RAG architecture. Leveraging ​​full-chain LLM inference​​ to streamline document processing and paragraph recall, it eliminates embedding models/vector databases while achieving precise end-to-end semantic retrieval through deep language understanding .

Un Asistente de IA basado en Google Gemini para Android Antiguo 4.2-8.1 / An AI Assistant based on Google Gemini for Old Android 4.2-8.1

Simplified "how to run" Llama 4

Code for the experiments and websites of the paper "Same Task, Different Circuits"

Go bindings to llama.cpp

Track brand visibility across different LLMs

This is a repository of scripts for reproducing benchmarking genomic language model on Nullsettes.

3D-Aware Vision-Language Models Fine-Tuning with Geometric Distillation

Moxin-VLM: Designed for advanced Vision-Language understanding and interaction, built upon the Moxin-LLM backbone

A comprehensive list of state-of-the-art papers in autonomous driving and robotics, covering end-to-end (e2e) learning, vision-language models (VLM), vision-language-action models (VLA), world models, and reinforcement learning (RL), with links to papers, code repositories, and relevant websites.

An open-source, production-ready AI chat application featuring Claude Sonnet 4, GPT-4o, real-time messaging, and modern UI. Built with Next.js 15, Convex, and TypeScript.

A package to house the main github repo for the hackathon

LlamaIndex integration with the ASIMOV Platform.

New Landing page for all documentation around CISA's Logging Made Easy project

Stream-Omni is an end-to-end language-vision-speech chatbot that simultaneously supports interaction across various modality combinations.

The fastest, lightest, and most powerful AI gateway on the market. Fully open-sourced.

A featured, easy-to-use, multimodal WhatsApp AI GPT-4o Chatbot in PHP for your Business. A fully functional, easy to customize WhatsApp ChatGPT AI Chatbot in Python. Supports GPT-4o with text + audio + image input, audio responses, and improved RAG + MCP Tools 🤩

A fully functional, easy to customize WhatsApp ChatGPT AI Chatbot in Python. Supports GPT-4o with text + audio + image input, audio responses, and improved RAG + MCP Tools 🤩

Fork of lm/navigation-stack-backport

Web de practica para lenguaje de marcas y CSS

TrustyAI's LMEval provider for Llama Stack