Skip to content
View Coekjan's full-sized avatar
🤔
Thinking
🤔
Thinking
  • Home
  • Beijing / Guangdong / Sheffield
  • 10:07 (UTC +08:00)

Highlights

  • Pro

Organizations

@buaa-os @Jrinx @raids-lab

Block or report Coekjan

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Content in all repositories owned by your account will be closed.
Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. Markdown is supported. This note will only be visible to you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
Showing results

Codex-native Academic Research Skills suite for human-in-the-loop academic research workflows

Python 12,131 522 Updated Oct 3, 2026

Structured deep research skill for Claude Code/Open Code/Codex with human-in-the-loop control

Python 2,303 188 Updated Aug 23, 2026

An open toolkit and public dataset hub for collecting, sanitizing, analyzing, and visualizing coding agent traces.

Python 138 22 Updated Aug 22, 2026

A high-performance communication library for machine learning training and inference on Huawei Ascend NPUs.

C++ 222 23 Updated Sep 30, 2026

DeepGEMM-Ascend: clean and efficient matrix multiplication kernel library for Huawei Ascend NPUs

C++ 512 39 Updated Sep 30, 2026

DeepEP: an efficient expert-parallel communication library

Cuda 10,245 1,458 Updated Sep 30, 2026

A scalable, agentic-first, and HuggingFace-native RL framework for research (9k lines).

Python 1,167 112 Updated Oct 5, 2026

RLinf: Reinforcement Learning Infrastructure for Embodied and Agentic AI

Python 5,441 764 Updated Oct 2, 2026

Agent skill that removes signs of AI-generated writing from text

Python 54,207 4,306 Updated Sep 28, 2026
Python 383 22 Updated Sep 21, 2026

An Asynchronous Reinforcement Learning Engine for Omni-Modal Post-Training at Scale

Python 636 174 Updated Oct 5, 2026

verl/HybridFlow: A Flexible and Efficient RL Post-Training Framework

Python 23,750 4,709 Updated Oct 5, 2026

Cosmos Curator is a powerful video curation system that processes, analyzes, and organizes video content using advanced AI models and distributed computing.

Python 286 40 Updated Oct 5, 2026

Uni-Agent is a framework for training long-horizon agents.

Python 644 127 Updated Oct 3, 2026

slime is an LLM post-training framework for RL Scaling.

Python 8,596 1,293 Updated Oct 5, 2026

Qwen3.8-27B-NVFP4 on a Single RTX 5090 (vLLM)

Shell 92 11 Updated Aug 16, 2026

Unix like coding agent

Zig 3,296 369 Updated Oct 6, 2026

Tile-Based Runtime for Ultra-Low-Latency LLM Inference

Python 1,835 128 Updated Sep 24, 2026

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.

Python 3,001 223 Updated Sep 14, 2026

DeepSeek Harness: Everything is a Plugin.

TypeScript 244,051 29,236 Updated Oct 3, 2026

Production-ready MoE load balancing via real-time expert replication

Cuda 252 19 Updated Jul 17, 2026

Makes your AI agent think like the laziest senior dev in the room. The best code is the code you never wrote.

JavaScript 156,023 8,383 Updated Oct 5, 2026

dev tools, env vars, task runner

Rust 34,634 1,458 Updated Oct 6, 2026

Efficient GPU Memory Pooling for Multi-LLM Serving via KV Cache and Weight Disaggregation

Python 11 2 Updated Oct 5, 2026

AgentENV (AENV) is a distributed platform for running agent environments at scale.

Rust 3,591 326 Updated Oct 3, 2026

Skills for Real Engineers. Straight from my .agents directory.

Shell 277,128 23,214 Updated Oct 5, 2026

JSON for Modern C++

C++ 50,729 7,511 Updated Oct 5, 2026

Run frontier MoE models on hardware you already own — pure C, zero deps, experts streamed from disk. Tiny engine, immense model. 🐦

C 39,795 4,375 Updated Oct 5, 2026

Container runtimes on macOS (and Linux) with minimal setup

Go 31,104 624 Updated Oct 2, 2026

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…

TeX 5 Updated May 11, 2026
Next