Open Weights Python Packages

lcode-cli

A coding agent that runs entirely on your own machine: open-weight models, up to 256K context, NVIDIA GPU or Apple Silicon Mac, via Ollama.

tacet

Typed decisions from one encoder pass. Open weights, Apache 2.0.

helm-runtime-sdk

A local launcher and platform for open-weight generative models. Install video, image and speech studios from their own repositories, run them on your Mac, and keep everything they make in one gallery.

blackdrome-noma

Noma: an open-weight decision model for AI agents. Calibrated decisions in milliseconds, self-hosted, with a Jev-compatible API.

pareta

Python client for Pareta — deploy open-weights endpoints, run metered inference, and evaluate models on your own data.

fusion-embedding

One embedding space for text, image, video, audio, thermal, motion, and touch. Open weights, self-hostable.

pbl-lm

A real engineering language model running fully offline on an $8-class ESP32-S3 — open weights, native C, real-silicon benchmarks.

h3check

Machine-readable spec sheet for MiniMax H3 / Hailuo 3, plus a validator that catches the 17n+5 duration grid, the 12-file reference cap and the 768P/2K-only resolution list before you pay for the render.