autonomous-agents

用于构建、执行与改进 AI 代理、工作流程及自主目标的本地优先操作系统。

LockKnife：终极 Android 安全研究工具。专为研究人员与黑客打造，提供统一的 TUI 工作区与无头 CLI，支持 AI 代理驱动的黑客攻击、凭证恢复/破解、APK 分析、情报收集与运行时检查，核心由 Python 编排并以 Rust 加速。

Self-hosted AI Agents Platform supporting Claude Code, Codex, Gemini agents. Apache 2.0.

专为渴望通过简洁、高效且符合 Go 惯用语的方式探索大型语言模型 (LLM) 与其他生成式 AI 潜力的开发者所设计的函数库

🌍 AppWorld: A Controllable World of Apps and People for Benchmarking Function Calling and Interactive Coding Agent, ACL'24 Best Resource Paper.

Safe runtime for autonomous on-chain AI agents: isolated sandboxes, Library skills, encrypted secrets.

自主式 AI 开发团队机器人

Autonomous white-hat security auditor for AI-driven code review, bug bounty research, exploit construction, and execution-grounded verification.

The action firewall for AI agents. Enforce policy and human approval before risky tool calls, shell commands, workflows, and production changes, with auditable evidence.