Transforms complex documents like PDFs into LLM-ready markdown/JSON for your Agentic workflows.

AI 驱动的 SVG 演示文稿生成系统，支持 PPT、小红书、朋友圈等多格式 | 15 个示例 | 229 页 | 生成可编辑的 ppt 格式

Automate your mobile devices with natural language commands - an LLM agnostic mobile Agent 🤖

Android Automation Tool Based on Vision-Language Models

An Open Phone Agent Model & Framework. Unlocking the AI Phone for Everyone

Adaptive Program Repair with Bug Localization and Preference Learning

Large language model review prompts

Training teachers with reinforcement learning able to make LLMs learn how to reason for test time scaling.

Adaptive Gradient Clipping

Knowledge Graph Enhanced Software Repair Framework

Bug dataset provided for ChinaSoft 2025 APR Competition

A fast, parallel, syntax-aware test case reducer based on tree-sitter grammars

C-Reduce, a C and C++ program reducer

Multi-SWE-bench: A Multilingual Benchmark for Issue Resolving

[SIGGRAPH Asia 2024, Journal Track] ToonCrafter: Generative Cartoon Interpolation

A refactoring benchmark for software engineering agents. [ICLR 2025]

Debug, evaluate, and monitor your LLM applications, RAG systems, and agentic workflows with comprehensive tracing, automated evaluations, and production-ready dashboards.

Cracking encrypted wechat message history from android

Crack the password of EnMicroMsg.db with brute-force attack.

Claude Code is an agentic coding tool that lives in your terminal, understands your codebase, and helps you code faster by executing routine tasks, explaining complex code, and handling git workflo…

API client to develop tools for competitive programming

A Flexible Framework for Experiencing Heterogeneous LLM Inference/Fine-tune Optimizations