Highlights
- Pro
Stars
🧠 两小时从 0 训出你的 64M 大模型。Train your own 64M LLM from scratch in 2 hours.
Play your own Switch games on iPhone/iPad — one-click macOS app, no terminal. | 把 Switch 游戏装进 iPhone:图形界面一键构建,不用命令行。Bring your own game.
A compatibility layer for porting Switch games to Android, one game at a time
Free, two-way Figma MCP server. Turn designs into framework-aware code, and push code back to the canvas. Works with Claude Code, Cursor, Codex, and any MCP client.
sdmj76 / Mousecape-swiftUI
Forked from alexzielenski/MousecapeCursor Manager Rewritten from Mousecape with Swift
MxIris-LyricsX-Project / LyricsX
Forked from ddddxxx/LyricsX🎶 Ultimate lyrics app for macOS.
任意门 · 基于 Xposed 的安卓全局虚拟定位工具,反检测、地图选点/摇杆/路线模拟| System-wide GPS spoofer for Android (Xposed/LSPosed): hooks system_server, no mock flag, map picker, joystick & route simulation
Free and open-source macOS menu bar toolkit.
A unified web console for Codex, Claude Code, OpenCode, and ACP agents. Manage sessions, approvals, and tasks from desktop or mobile, with deck-api for agent collaboration.
Artifact for "From Seed to Scope: Reasoning to Identify Change Impact Sets"
Master's Thesis: Test-Driven AI Development - Minimizing code regressions in AI agents using TDD and GraphRAG
Recommend new arxiv papers of your interest daily according to your Zotero libarary.
Training neural networks on Apple Neural Engine via reverse-engineered private APIs
a C\C++ library and command-line tools for Diff & Patch between binary files or directories(folder); cross-platform; runs fast; create small delta/differential; support large files and limit memory…
Edit Banana: A framework for converting statistical formats into editable.
邦邦手游星石挖掘机 / bangdream girls band party (semi) auto player
1 min voice data can also be used to train a good TTS model! (few shot voice cloning)
[NAACL 2025] Benchmark for Repository-Level Code Generation, focus on Executability, Correctness from Test Cases and Usage of Contexts from Cross-file Dependencies
Awesome autocompletion, static analysis and refactoring library for python
⚡A CLI tool for code structural search, lint and rewriting. Written in Rust
CrossCodeEval: A Diverse and Multilingual Benchmark for Cross-File Code Completion (NeurIPS 2023)
DependEval: a hierarchical benchmark for evaluating LLMs on repository-level code understanding across 8 programming languages.
Official repository for the paper "LiveCodeBench: Holistic and Contamination Free Evaluation of Large Language Models for Code"