Top Open Source AI Organization Influencers in 2025Q2

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

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.

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

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

Implementing DeepSeek R1's GRPO algorithm from scratch

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.

A set of tools that gives agents powerful capabilities.

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.

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

Take your LLM to the optometrist.

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

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.

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

Adapting VLMs to Bench2Drive.

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 sample shows how to implement a deep researcher with DeepSeek R1

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

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 .

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.

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.

Simplified "how to run" Llama 4

Track brand visibility across different LLMs

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

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

Llama Stack Example

Fork of lm/navigation-stack-backport

Source code and data for paper "Patterns Over Principles: The Fragility of Inductive Reasoning in LLMs under Noisy Observations".

a generalist ultrasound vision-language model capable of multi-organ understanding, abnormality detection, ultrasound-based diagnostic reasoning, structured report generation, and multi-turn patient-centered dialogue.

Web de practica para lenguaje de marcas y CSS

Capacitor binding of llama.cpp

A production-ready TypeScript template for building AI agents using LlamaIndex in Blaxel.

React Native Turbo Module for llama.cpp integration, optimized for the New Architecture

An implementation of HuggingFace Snap on Android using llama.cpp and libmtmd

an introduction to language models, unplugged /lowcode

This repository contains an intelligent Customer Support Assistant that utilizes a large language model (LLM) to provide support to banking customers. It is built using python programming.

describe_photos_llama_vision

LMS 자동 출석 프로그램

LLM component of WayfindR

swa20250430011lm8zadnc3rwfutoswpicz

A demo of Gemma 3 1B Instruction-tuned Quantized q4_0. This repo uses LLaMa CPP library to inference the model in .gguf format.

The simplest way to inference llama3.2 fast

swa2025042201592hj2lmmfmu8mpvwjxfi7

This is the public advertisement website for the VLM gaze paper.

Source universe for: glmgen

LMG framework

swa2025042701fcl9gpj9b9lmyc1r1y2l9x

swa2025042701ze2h72hm4lm2ygaw936k50

Experience edge AI with free access to the DeepSeek R1 model

Funcionalidad de reservaciones para cliente

swa2025042401xmu0q34lmtzhk2puqlqu49

LLM backend

Distillation POC for Llama4

swa20250430014kmdkz292db0lmu5wqgqn6

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

A fun way to learn about git troubleshooting.

BentoML + llama.cpp

Product integrations for LiquidMetal Raindrop in Typescript

Implementation of logistic regression and basic neural network

This repository contains a collection of demonstration projects showcasing various capabilities and applications of LlamaIndex, a powerful data framework for building LLM applications with custom data. Each tutorial focuses on a specific aspect of LlamaIndex functionality, ranging from basic usage to advanced features like RAG, chatbots, etc.

[automatic-octo-robot] Llama Playground (2025-04-07)

Python app that auto categorizes your expenses

gitops resources for {{ 'chatbot-app' }}

AI-powered academic planner that syncs with Canvas and your calendar to build dynamic, personalized study schedules. Built with React Native, Supabase, and GPT-4o.

本库包含了已做好LIMR适配的LLaMA-Factory库，并在README.MD中详述了 LIMR 工作流及适配所做修改的详细报告

Minimal Helm chart for deploying llama-stack, llama-serve, safety-model