embedded-ai
Let your coding agent develop firmware on the real board, with the hardware as the gate.
600 KB WASM runtime for Cactus Compute's Needle AI tool-calling models, Needle 3, 2 and 1 from one build. Browser, Cloudflare Workers, Node.js, Python, C FFI and no_std. Token-exact with the JAX reference. No backend, no API key.
A Lightweight OCR model and Engine for low computation devices, edge applications and embedded system
A real engineering language model running fully offline on an $8-class ESP32-S3 — open weights, native C, real-silicon benchmarks.
The simple way to build and embed AI agents into any software stack. Code-native, modular, and LLM-agnostic.
