Molt
An agentic-first RL framework for research. Ray · vLLM · NVIDIA AutoModel — the smallest PyTorch-native stack for 1T-class fully-async, multimodal, multi-turn agentic RL.

Build continually improving models on your agent traces by distilling frontier open models
An agentic-first RL framework for research. Ray · vLLM · NVIDIA AutoModel — the smallest PyTorch-native stack for 1T-class fully-async, multimodal, multi-turn agentic RL.
PorTAL generates portable task specific LoRA adapters that can efficiently transfer across language models.
Tinker is a training API for researchers and developers.
An occasional email when notable AI dev tools and models land in the directory. No spam, unsubscribe anytime.