-
Cactus (YC S25)
Stars
BDH (Dragon Hatchling) – Architecture and Code
On-device models that know when they're wrong: every answer carries a confidence score for cloud handoff.
Programming language for ML on XLA with JAX-level speed; compiles for CPU, TPUs/Nvidia GPUs, AMD GPUs, Apple GPUs, etc.
Sub-50mb agentic, voice and vision intelligence for consumer devices.
Become a cracked AI/ML researcher/engineer with this unconventional textbook covering maths, computing, and ML with intuition.
Parameter-efficient transformer embeddings replace learned embeddings with hardware-aware polynomial expansions of token IDs.
Cactus React Native package: Run AI locally in your React Native apps
2bit quants, kernels and runtime for consumer devices.
Your private AI mind. In your pocket. For free.
Private, local RAGs. Supercharge LLMs with your own knowledge base.
High-performance, privacy-first on-device AI inference library for React Native, powered by PyTorch's ExecuTorch runtime
On-device AI across mobile, embedded and edge for PyTorch