Stars
Experimental GLM-5.2 v17 TP4/DCP4 image with RAM LMCache and CKV-gather prefill optimization
Agent Reinforcement Trainer: train multi-step agents for real-world tasks using GRPO. Give your agents on-the-job training. Reinforcement learning for Qwen3.6, GPT-OSS, Llama, and more!
NVIDIA Linux open GPU with P2P support
Skills for Real Engineers. Straight from my .agents directory.
The context API to search, scrape, and interact with the web at scale. 🔥