Lists (5)
Starred repositories
Instant, Concurrent, Secure & Lightweight Sandbox for AI Agents.
Modular open-source sEMG hardware (2ch/8ch/16ch KiCad & EasyEDA Pro), firmware, and studio
DeepSelect: TopK kernels for DeepSeek Sparse Attention (DSA) and Samplers
EAT: Evolving Agent Teams (NeurIPS'26). A supervisor agent evolves teams of coding agents for long-running optimization tasks.
Accurate, fast FP4 KV-cache decoding through algorithm-system co-design.
Fast, exact fused top-k selection for learned sparse attention training and inference, from HyScale (Tencent Hy & University of Edinburgh).
A scalable, agentic-first, and HuggingFace-native RL framework for research (9k lines).
Infrastructure for continually self‑improving agents
Reverse Engineering / Authorized Penetration Testing / Security Research Skill Router Pack AI-powered routing + On-demand toolchain bootstrapping + Self-evolving knowledge base Supports Claude Code…
DeepSeek Harness: Everything is a Plugin.
AI agent toolkit: unified LLM API, agent loop, TUI, coding agent CLI
Mixture-of-experts (MoE) training megakernel for NVL72s
Infinite Worlds with Versatile Interactions
KernelBenchX: A Comprehensive Benchmark for Evaluating LLM-Generated GPU Kernels
Paper list of multi-agent reinforcement learning (MARL)
MoonEP: A Perfectly Balanced Expert Parallelism Library via Dynamic Redundant Experts
Reference implementation and examples of the CuTe Layout representation and algebra.
AgentENV (AENV) is a distributed platform for running agent environments at scale.
Companion code for the global workspace interpretability paper
FlashMLA: Efficient Multi-head Latent Attention Kernels
TokenSpeed is a speed-of-light LLM inference engine.
A high-performance, universal serving framework for any-to-any models.
A copy of the Cursor AI editor theme from cursor.sh, repackaged for use in Visual Studio Code without needing the Cursor editor.
Homepage for ProLong (Princeton long-context language models) and paper "How to Train Long-Context Language Models (Effectively)"
ElasticMM: Elastic and Efficient MLLM Serving System