Qwen3-TTS is an open-source series of TTS models developed by the Qwen team at Alibaba Cloud, supporting stable, expressive, and streaming speech generation, free-form voice design, and vivid voice…

Academic Research Skills for Claude Code: research → write → review → revise → finalize

AI 驱动的学术论文配图生成平台。上传论文 → AI 分析内容生成 Prompt → 一键生成高质量科研配图，还有配套的skill可在主流agent中使用

【Numbered musical notation tools】je 简谱 处理工具，包括转调、播放、制谱、midi提取（转换）与制作等

Apple MacOS Screen Sharing Arbitrary File read/write -> RCE

Read-only PoC for CVE-2026-65400 — macOS Screen Sharing (screensharingd) pre-auth SRP bypass giving root file read. Patched in macOS 26.6.1 / 15.7.9 / 14.8.9.

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

Collection of evals for Inspect AI

💲 🔨 Path of Exile trading app for price checking

面向 AI 的领域技能包：作词、作曲编曲、Synthesizer V 调校

VulnGym: A Real-World, Project-Level Vulnerability Benchmark for White-Box Vulnerability-Hunting Agents

利用 AI 大模型和自动化工作流，根据主题或关键词一键生成高清短视频。Generate HD short videos from a topic or keyword with an automated AI workflow.

MCP Server for FL Studio

Agent Security Bench (ASB)

A benchmark for evaluating the robustness of LLMs and defenses to indirect prompt injection attacks.

[ICLR'24 spotlight] An open platform for training, serving, and evaluating large language model for tool learning.

Test your prompts, agents, and RAGs. Red teaming/pentesting/vulnerability scanning for AI. Compare performance of GPT, Claude, Gemini, DeepSeek, and more. Simple declarative configs with command li…

AI算法岗求职攻略（涵盖准备攻略、刷题指南、内推和AI公司清单等资料）

OpenAI's Codex Security CLI and TypeScript SDK for finding, validating, and fixing security vulnerabilities. npm: https://www.npmjs.com/package/@openai/codex-security

Can Language Models Rebuild Programs From Scratch?

Own your AI. The native macOS harness for AI agents -- any model, persistent memory, autonomous execution, cryptographic identity. Built in Swift. Fully offline. Open source.

CyberGym-E2E is a large-scale benchmark built from real-world vulnerabilities in widely used open-source projects to evaluate AI agents' end-to-end cybersecurity capabilities, from discovering vuln…

Pre-indexed code knowledge graph, auto syncs on code changes, for Claude Code, Codex, Gemini, Cursor, OpenCode, AntiGravity, Kiro, CoPilot, and Hermes Agent — fewer tokens, fewer tool calls, 100% l…

From Chain-of-Thought prompting to OpenAI o1 and DeepSeek-R1 🍓

Framework for evaluating and improving agents

Qiushi-Skill: Build agents that investigate first, focus on the main contradiction, validate in practice, and keep pushing until the work is actually done. 求是Skill——从经典唯物辩证法与实践哲学中提炼出一条总原则和九大方法论工具武装…