C-based eUICC LPA

An open-sourced end-to-end VLM-based GUI Agent

🔥🔥🔥AI-driven database tool and SQL client, The hottest GUI client, supporting MySQL, Oracle, PostgreSQL, DB2, SQL Server, DB2, SQLite, H2, ClickHouse, and more.

Accept by CVPR 2025 (highlight)

AI agents running research on single-GPU nanochat training automatically

A cross-platform desktop All-in-One assistant for Claude Code, Codex, OpenCode, OpenClaw, Gemini CLI & Hermes Agent. Only official website: ccswitch.io

AI API中转站推荐与评测

An enhanced tool for CodexApp, striving to make Codex better to use and more comfortable 一个CodexApp的增强工具，努力让Codex变得更好用更舒服

🚀 Run Codex Mobile Anywhere: Linux, Windows, or Termux on Android 🚀

这是一个手机远程控制电脑 Codex 的私有网页面板与桌面控制工具

代理,快捷切换codex 账号, 监控codex用量的工具,以及对codex进行api反代 , 支持多语言

A CLI tool to switch and manage Codex accounts

Open Cowork - Opensource Claude Cowork for Windows & macOS & Linux.

Official implementation of the WASP web agent security benchmark

[ACL 2026] PIArena: A Platform for Prompt Injection Evaluation

All-in-one New-API/Sub2API account hub: balance/usage dashboard, auto check-in, one-click keys, price comparison, health checks, plus advanced channel management | 一站式 New-API/Sub2API 等中转站账号管理：余额/用…

Fully autonomous & self-evolving research from idea to paper. Chat an Idea. Get a Paper. 🦞

ARIS ⚔️ (Auto-Research-In-Sleep) — Lightweight Markdown-only skills for autonomous ML research: cross-model review loops, idea discovery, and experiment automation. No framework, no lock-in — works…

Security scanner for MCP servers

CVPR2026

Benchmarking Behavioral Jailbreaks of LLM Agents in Real OS Environments.

[ICML 2026] Official implementation for paper "Unsafer in Many Turns: Benchmarking and Defending Multi-Turn Safety Risks in Tool-Using Agents"

[NeurIPS 2025] The official implementation of the paper "DRIFT: Dynamic Rule-Based Defense with Injection Isolation for Securing LLM Agents".

The official implementation of the paper "AgentDyn: A Dynamic Open-Ended Benchmark for Evaluating Prompt Injection Attacks of Real-World Agent Security System".

The official implementation of the paper "AgentDyn: Are Your Agent Security Defenses Deployable in Real-World Dynamic Environments?"

Parsing-free RAG supported by VLMs

A Dynamic Environment to Evaluate Attacks and Defenses for LLM Agents.

🚀 Automated & lossless LaTeX paper migration tool. Instantly convert your Overleaf source between top-tier AI conference templates (NeurIPS, ICLR, ACL等). 一键无损转换顶会论文格式！解决转投时的排版折磨，完美保留公式、图表与引用，让科研人员专…