Persistent Context Across Sessions for Every Agent – Captures everything your agent does during sessions, compresses it with AI, and injects relevant context back into future sessions. Works with C…

AI generates a real, editable PowerPoint from any document — native shapes & animations, speaker notes voiced as audio narration, and the option to follow your own .pptx template, not slide images …

📡 Your own AI-powered news radar. Generates daily briefings in English & Chinese. | 用 AI 构建你专属的新闻雷达

One Forge, All Skills: A curated skill collection for academic writing and research. 点开即用，按需配置的一站式学术研究skills平台。

The agent that grows with you

The Netzgrafik-Editor is a powerful software that enables the creation, modification, and analysis of regular-interval timetable.

Backend for the Netzgrafik-Editor

An open source web application for railway infrastructure design, capacity analysis, timetabling and simulation

通用的列车运行图绘图、编辑、分析软件，适用于客货运铁路、城市轨道交通等。原pyETRC项目的Qt (C++) 重构版本。

Branch-and-Price-and-Cut in Julia

GLM-5: From Vibe Coding to Agentic Engineering

AI agents running research on single-GPU nanochat training automatically

企业微信自动打卡 远程指令打卡(支持企业定制打卡页)(可免root)(永远不可能被检测)（2026.4.13持续有效）(上千人在使用的稳定)

Sends virtual input commands

A cross-platform GUI automation Python module for human beings. Used to programmatically control the mouse & keyboard.

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

npx ccusage

Official, Anthropic-managed directory of high quality Claude Code Plugins.

Gemma open-weight LLM library, from Google DeepMind

VS Code extension for monitoring Google Antigravity AI quotas. Features Webview dashboard, QuickPick mode, and quota grouping.

Public repository for Agent Skills

Specification and documentation for Agent Skills

Claude Code skill that removes signs of AI-generated writing from text

CL-bench: A Benchmark for Context Learning

The best ChatGPT that $100 can buy.

Transformers-compatible library for applying various compression algorithms to LLMs for optimized deployment with vLLM

ModelScope: bring the notion of Model-as-a-Service to life.

A high-throughput and memory-efficient inference and serving engine for LLMs

gpt-oss-120b and gpt-oss-20b are two open-weight language models by OpenAI

Open Source AI Platform - AI Chat with advanced features that works with every LLM