A research prototype of a human-centered web agent

Collection of evals for Inspect AI

This repository is meant for GeoRegional Africa Ideas.

Intereval: An interactive CLI tool for evaluating and comparing LLMs locally via Ollama. Features guided sessions, non-interactive modes for automation, and flexible evaluation criteria. Compare on…

Inspect: A framework for large language model evaluations

Jan is an open source alternative to ChatGPT that runs 100% offline on your computer

A gallery that showcases on-device ML/GenAI use cases and allows people to try and use models locally.

Building a new architecture for Ugandan languages in a Small Language Model

Cross-platform framework for deploying LLM/VLM/TTS models locally on smartphones.

Qiskit Global Summer School: The Past, Present and Future of Quantum Computing

The Cursor for Designers • An Open-Source Visual Vibecoding Editor • Visually build, style, and edit your React App with AI

Fully Local Manus AI. No APIs, No $200 monthly bills. Enjoy an autonomous agent that thinks, browses the web, and code for the sole cost of electricity. 🔔 Official updates only via twitter @Martin9…

A powerful AI agent for browser-based interactions powered by Fireworks AI models. Navigate the web, extract content, analyze websites, and provide intelligent feedback based on what it sees. Featu…

Finetune Qwen3, Llama 4, TTS, DeepSeek-R1 & Gemma 3 LLMs 2x faster with 70% less memory! 🦥

Waymo Open Dataset

Tool for generating high quality Synthetic datasets

The K-Scale Robot

Efficient and low latency real-time global-scale GPS trajectory modeling

Official inference framework for 1-bit LLMs

Suna - Open Source Generalist AI Agent

Lightweight coding agent that runs in your terminal

🤗 Benchmark Large Language Models Reliably On Your Data

Model Context Protocol Servers

NeMo Guardrails is an open-source toolkit for easily adding programmable guardrails to LLM-based conversational systems.

An open protocol enabling communication and interoperability between opaque agentic applications.

A collection of notebooks/recipes showcasing usecases of open-source models with Together AI.

Qwen2.5-Omni is an end-to-end multimodal model by Qwen team at Alibaba Cloud, capable of understanding text, audio, vision, video, and performing real-time speech generation.