No-code, local-first studio for building and running production ready AI agents. Inference runs on your machine — llama.cpp, MLX, or vLLM — or any OpenAI-compatible API you register

🌐 Make websites accessible for AI agents. Automate tasks online with ease.

opentelemetry instrumented fastapi service with a running grafana stack

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

Model Context Protocol Servers

An AI Hedge Fund Team

Sampling profiler for Python programs

An Elasticsearch Python ORM based on Pydantic.

Solidity library unifying ERC20, ERC721 & ERC1155 transfers by wrapping them into MultiToken Asset struct.