Running on CPU Upgrade Agents 2.48k Omni Image Editor 🖼 2.48k Image edit, text to image, image upscale, remove watermark
StateM: Reaching 95.3% Raw Accuracy, or a \$15 Frontier Run, on Terminal-Bench 2.1 via Harness Scaling Paper • 2608.15089 • Published 16 days ago • 445
Running on Zero Agents Featured 68 My Pi Agent 🦀 68 Chat with a coding assistant powered by a hosted AI model
Running on Zero Agents Featured 47 Follow the Mean (FLUX.2) 🪷 47 Training-free reference-guided generation with FLUX.2-klein
Running 230 The ultimate guide to RL environments: building and scaling them in the LLM era 📝 230 Building and scaling RL environments for LLM training
MolmoAct2: Action Reasoning Models for Real-world Deployment Paper • 2605.02881 • Published May 4 • 356
GUI-G^2: Gaussian Reward Modeling for GUI Grounding Paper • 2507.15846 • Published Jul 21, 2025 • 135