AI-powered browsing assistant for Chrome. Built for the Google Chrome Built-in AI Challenge 2025.

Upload your data → Get a fine-tuned SLM. Free.

A simple, performant and scalable Jax LLM!

Fast ML inference & training for ONNX models in Rust

Easily fine-tune, evaluate and deploy gpt-oss, Qwen3, DeepSeek-R1, or any open source LLM / VLM!

Low-code framework for building custom LLMs, neural networks, and other AI models

Turn any PDF or image document into structured data for your AI. A powerful, lightweight OCR toolkit that bridges the gap between images/PDFs and LLMs. Supports 100+ languages.

POC about using Leann to create a local RAG getting data from Wikipedia.

RAG chatbot and document indexer, based on Next.js chatbot template from Vercel

Semantica 🧠 — A framework for building semantic layers, context graphs, and decision intelligence systems with explainability and provenance.

Integrate cutting-edge LLM technology quickly and easily into your apps

Open Accelerated Discovery Toolkit

SaaS Starter con AI, Auth, Supabase & Next.js

Continuous Thought Machines, because thought takes time and reasoning is a process.

CLI-Anything: Making ALL Software Agent-Native

A general-purpose tool for dynamic report generation in R

simple web-based, free and open-source visual novel editor that can be used in a web browser. It is written in JavaScript without using any third party libraries and thus does not require additiona…

A Next.js application demonstrating Mastra AI agent observability with real-time weather information. Showcases how to integrate Mastra's observability for production deployments to Vercel

The AI Scientist: Towards Fully Automated Open-Ended Scientific Discovery 🧑‍🔬

A set of ready to use Agent Skills for research, science, engineering, analysis, finance and writing.

An autonomous agent that conducts deep research on any data using any LLM providers

Implementation of Google Deepmind's AI co-scientist with LangGraph and GPT Researcher

Lightpanda: the headless browser designed for AI and automation

OpenRAG is a comprehensive, single package Retrieval-Augmented Generation platform built on Langflow, Docling, and Opensearch.

React Starter Kit built using React Router v7, Clerk, Convex & Polar

Open chat interface for all your models.

✨ Reverse-engineered Python API for Google Gemini web app

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