Starred repositories
[RSS 2026] Interactive World Simulator for Robot Policy Training and Evaluation
Build compute kernels and load them from the Hub.
ClawSweeper scans all issues and PRs and suggest what we can close, and why. It runs every PR / Issue once a week.
Unofficial fork from https://openprop.engineering.dartmouth.edu/
Apache Nutch is an extensible and scalable web crawler
Holistic Evaluation of Language Models (HELM) is an open source Python framework created by the Center for Research on Foundation Models (CRFM) at Stanford for holistic, reproducible and transparen…
Use Codex from Claude Code to review code or delegate tasks.
A format specification for describing a visual identity to coding agents. DESIGN.md gives agents a persistent, structured understanding of a design system.
Qwen3.6 is the large language model series developed by Qwen team, Alibaba Group.
Annotate satellite imagery with LabelMe and convert the annotations to GeoJSON for use in GIS tools like QGIS.
Information and files for my mineral epoxy CNC build
A Curated List of Vision-Language-Action (VLA) and World Action Models (WAM) Research and Beyond
Multi-backend code-first parametric CAD in JavaScript/TypeScript with live params, constraints, assemblies, and exact STEP/BREP export.
[ICLR 2026] ParoQuant: Pairwise Rotation Quantization for Efficient Reasoning LLM Inference
DFlash: Block Diffusion for Flash Speculative Decoding
A theoretical reconstruction of the Claude Mythos architecture, built from first principles using the available research literature.
Browser Harness | Self-healing harness that enables LLMs to complete any task.
A feed-forward 3D foundation model for reconstructing scenes from streaming data
One brain, many harnesses. Portable .agent/ folder (memory + skills + protocols) that plugs into Claude Code, Cursor, Windsurf, OpenCode, OpenClaw, Hermes, or DIY Python — and keeps its knowledge w…
LiteRT, successor to TensorFlow Lite. is Google's On-device framework for high-performance ML & GenAI deployment on edge platforms, via efficient conversion, runtime, and optimization
Sim2Reason: Solving Physics Olympiad via Reinforcement Learning on Physics Simulators. We present a method for turning physics simulators into scalable generators of question–answer pairs for impro…