Skip to content
View luyaxi's full-sized avatar
  • Tsinghua University

Highlights

  • Pro

Block or report luyaxi

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. 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

Starred repositories

Showing results

Towards a More Autonomous Agent System

TypeScript 23,935 2,968 Updated Nov 3, 2026

A Benchmark for Evaluating Agent Self-Evolution on Real Business Tasks

Python 122 6 Updated Oct 29, 2026

DeepSeek Harness: Everything is a Plugin.

TypeScript 284,058 35,275 Updated Nov 18, 2026

Scale computer-use 2.0 with open-source drivers, cross-OS sandboxes, and benchmarks for training, evaluation, and data generation.

Rust 32,658 2,463 Updated Nov 19, 2026

The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.

JavaScript 306,975 45,191 Updated Nov 17, 2026

LLM Wiki is a cross-platform desktop application that turns your documents into an organized, interlinked knowledge base — automatically. Instead of traditional RAG (retrieve-and-answer from scratc…

TypeScript 21,770 2,465 Updated Oct 21, 2026
Python 14 Updated May 26, 2026

Delicately-TUICed 0-RTT proxy protocol

3,294 515 Updated May 15, 2025

An agent-managed museum exhibit, built in Rust with Gajae-Code / LazyCodex — developed and maintained with no human intervention.

Rust 194,756 107,213 Updated Nov 10, 2026

AI agent toolkit: unified LLM API, agent loop, TUI, coding agent CLI

TypeScript 122,882 15,854 Updated Nov 19, 2026

The AI that really does things. Any OS. Any Platform. The lobster way. 🦞

TypeScript 394,802 82,928 Updated Nov 19, 2026

Production ready toolkit to run AI locally

C++ 10,351 419 Updated Nov 10, 2026

🙌 OpenHands: AI-Driven Development

TypeScript 93,827 12,560 Updated Nov 19, 2026

An End-to-End Infrastructure for Training and Evaluating Various LLM Agents

Python 835 69 Updated Oct 22, 2026

USP: Unified (a.k.a. Hybrid, 2D) Sequence Parallel Attention for Long Context Transformers Model Training and Inference

Python 697 86 Updated Sep 16, 2026

[FSE'2026] SWE-Factory: Your Automated Factory for Issue Resolution Training Data and Evaluation Benchmarks

Python 203 19 Updated May 12, 2026

All-in-One Sandbox for AI Agents that combines Browser, Shell, File, MCP and VSCode Server in a single Docker container.

Python 6,364 575 Updated Sep 14, 2026

A simple yet powerful agent framework that delivers with open-source models

Python 4,637 494 Updated Nov 9, 2026

清华主题PPT模板

Python 1,752 108 Updated Nov 16, 2025

[NeurIPS 2025 Spotlight] OpenCUA: Open Foundations for Computer-Use Agents

Python 877 111 Updated May 25, 2026

Renderer for the harmony response format to be used with gpt-oss

Rust 4,546 320 Updated Apr 8, 2026

Official repo of Toucan: Synthesizing 1.5M Tool-Agentic Data from Real-World MCP Environments

Python 271 19 Updated Dec 16, 2025

A General, Accurate, Long-Horizon, and Efficient Mobile Agent driven by Multimodal Foundation Models

Python 246 13 Updated Nov 18, 2025

Meta Agents Research Environments is a comprehensive platform designed to evaluate AI agents in dynamic, realistic scenarios. Unlike static benchmarks, this platform introduces evolving environment…

Python 581 89 Updated Sep 30, 2026

AgentCPM-GUI: An on-device GUI agent for operating Android apps, enhancing reasoning ability with reinforcement fine-tuning for efficient task execution.

Python 1,431 138 Updated Jan 11, 2026

A PyTorch native platform for training generative AI models

Python 5,926 1,091 Updated Nov 19, 2026

PyTorch native quantization for training and inference

Python 3,030 692 Updated Nov 19, 2026

slime is an LLM training framework for RL Scaling.

Python 8,849 1,369 Updated Nov 5, 2026

[NeurIPS 2024] OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments

Python 3,268 564 Updated Nov 14, 2026

A curated list of papers related to constrained decoding of LLM, along with their relevant code and resources.

378 19 Updated Jul 27, 2026
Next