-
Home
- Beijing / Guangdong / Sheffield
-
10:07
(UTC +08:00)
Highlights
- Pro
Stars
Codex-native Academic Research Skills suite for human-in-the-loop academic research workflows
Structured deep research skill for Claude Code/Open Code/Codex with human-in-the-loop control
An open toolkit and public dataset hub for collecting, sanitizing, analyzing, and visualizing coding agent traces.
A high-performance communication library for machine learning training and inference on Huawei Ascend NPUs.
DeepGEMM-Ascend: clean and efficient matrix multiplication kernel library for Huawei Ascend NPUs
DeepEP: an efficient expert-parallel communication library
A scalable, agentic-first, and HuggingFace-native RL framework for research (9k lines).
RLinf: Reinforcement Learning Infrastructure for Embodied and Agentic AI
Agent skill that removes signs of AI-generated writing from text
An Asynchronous Reinforcement Learning Engine for Omni-Modal Post-Training at Scale
verl/HybridFlow: A Flexible and Efficient RL Post-Training Framework
Cosmos Curator is a powerful video curation system that processes, analyzes, and organizes video content using advanced AI models and distributed computing.
Uni-Agent is a framework for training long-horizon agents.
slime is an LLM post-training framework for RL Scaling.
Qwen3.8-27B-NVFP4 on a Single RTX 5090 (vLLM)
Tile-Based Runtime for Ultra-Low-Latency LLM Inference
J-Space Cognition Suite — a model-agnostic inference-time control suite for deep reasoning, long-horizon work, verification, and recovery. Based on Anthropic's J-space global workspace research.
DeepSeek Harness: Everything is a Plugin.
Production-ready MoE load balancing via real-time expert replication
Makes your AI agent think like the laziest senior dev in the room. The best code is the code you never wrote.
Efficient GPU Memory Pooling for Multi-LLM Serving via KV Cache and Weight Disaggregation
AgentENV (AENV) is a distributed platform for running agent environments at scale.
Skills for Real Engineers. Straight from my .agents directory.
Run frontier MoE models on hardware you already own — pure C, zero deps, experts streamed from disk. Tiny engine, immense model. 🐦
Container runtimes on macOS (and Linux) with minimal setup
A Claude Code skill for polishing computer systems conference papers. Features multi-agent iterative review with diverse reviewer personas, story-driven coherence checking, citation verification, a…





