仓库/Skill 库

用于授权 Stellar Sentinel flags、可配置阈值与最新 flag 记录的 Soroban 合约。Soroban contract for authorized Stellar Sentinel flags, configurable thresholds, and latest-flag records.

基于 FastAPI 的服务，用于 Stellar 账户筛查、Soroban 事件监控与网络健康监测。FastAPI service for Stellar account screening, Soroban event monitoring, and network health.

Stellar Sentinel 仪表盘，用于 Stellar 账户筛查、网络健康监测与 Soroban 合约 flag 事件。Stellar Sentinel dashboard for Stellar account screening, network health, and Soroban contract flag events.

ChatGPT iOS 订阅 / 权益流程的安全分析（内部草稿，协调披露进行中）。Security analysis of the ChatGPT iOS subscription / entitlement flow (internal draft, coordinated disclosure WIP)

具备结构化记忆、安全钩子与循环管理的自主 Agent 框架，由运行在其上的 Agent 自身构建。Autonomous agent framework with structured memory, safety hooks, and loop management. Built by the agent that runs on it.

一个面向终端的快速、键盘驱动的 HTTP 拦截代理及渗透测试工具包。A fast, keyboard-driven HTTP intercepting proxy and hacking & pentesting toolkit for the terminal.

Apeireth —— 一个纯 Safe Rust 的 AGI 操作系统与认知微内核。包含 16 个 crate：连续拓扑记忆、因果世界模型、认知调度器、Ember HUD、三层 onion 安全机制以及可移植 USB Agent。Apeireth — A Pure Safe Rust AGI Operating System & Cognitive Microkernel. 16 crates: continuous topological memory, causal world model, cognitive scheduler, Ember HUD, triple-onion security & portable USB agent.

Apeireth——AGI 操作系统 / LLM 基础（Rust）。85 个 crate：companion organ、world model、好奇心、假设检验、双层洋葱安全。Apeireth — An AGI Operating System / LLM Base (Rust). 85 crates: companion organ, world model, curiosity, hypothesis testing, double-onion security.

PKG Sender——通过局域网安装 PS4/PS5 软件包。在 PC 上选择游戏，自动查找主机，排队并安装。无需 USB，无需手动输入 IP。PKG Sender — install PS4/PS5 packages over LAN. Pick games on PC, auto-find the console, queue and install. No USB, no manual IP.

面向 AI Agent 的任务范围授权。通过加密凭证约束工具与参数，在每次委托跳转中阻止权限提升，并生成关于允许或拒绝操作的有签名证据。Task-scoped authorization for AI agents. Cryptographic warrants constrain tools and arguments, prevent privilege escalation at every delegation hop, and produce signed evidence of what was allowed or denied.

AI 编码 Agent 的资深开发者纪律：未勾选即视为失败的提交门禁、拒绝将未完成工作标记为完成的质量控制器，以及闭环每类逃逸缺陷的经验循环。单一 Go 二进制，无运行时依赖，兼容 20+ AgentSenior-developer discipline for AI coding agents. A commit gate that counts unchecked as failing, quality controllers that refuse to call unfinished work done, and a lessons loop that closes each escaped bug's class. One Go binary, no runtime deps, works with 20+ agents.

AI 生成 Agent 能力变更的确定性合并闸门——针对 MCP、OpenAPI 与 SDK 工具面的本地优先、静态 Tool-Use Readiness 审查。开源 CLI + GitHub Action。The deterministic merge gate for AI-generated agent capability changes — a local-first, static Tool-Use Readiness review for MCP, OpenAPI, and SDK tool surfaces. Open-source CLI + GitHub Action.

精心策划、持续更新的 LLM Agent 论文阅读清单，收录 500+ 篇论文，涵盖规划、记忆、工具使用、多智能体、评估与安全。配套综述论文《LLM Agents: A Survey》。A curated, continuously updated reading list of 500+ papers on LLM agents: planning, memory, tool use, multi-agent, evaluation & safety. Companion to the survey 'LLM Agents: A Survey'.

用于全栈 LLM 驱动渗透测试的 cybersecurity harness，可自主发现并修复漏洞，7×24 小时不间断。[RESEARCH PREVIEW]A cybersecurity harness for full-stack LLM-driven penetration testing. Find and fix vulnerabilities autonomously, 24/7. [RESEARCH PREVIEW]

FactCircuit：具备不可篡改来源、分阶段检查、有界检索与可复现评估的可审计主张-证据验证回路。FactCircuit: an auditable claim-and-evidence verification loop with immutable provenance, staged checks, bounded retrieval, and reproducible evaluation.

隐私优先、自托管的加密资产记账应用，零云端数据共享。聚合交易所、钱包及多链历史，计算 FIFO/LIFO/HIFO 成本基础、已实现/未实现盈亏与资本利得，跟踪质押/空投收入，并导出可报税的 CSV/PDF/JSON 报告。加密 SQLite。Python，跨平台。Privacy-first, self-hosted crypto accounting app with zero cloud data sharing. Aggregates exchange, wallet and multi-chain history, calculates FIFO/LIFO/HIFO cost basis, realized/unrealized PnL and capital gains, tracks staking/airdrop income, and exports tax-ready CSV/PDF/JSON reports. Encrypted SQLite. Python, cross-platform.

面向安全关键型控制系统的 Agent 接口与安全防护框架。An agentic interface and safety harness for safety-critical control systems

Promptfoo 的 GitHub Action。可用于测试 prompt、Agent 与 RAG；支持 LLM 的 AI 红队对抗、渗透测试与漏洞扫描；对比 GPT、Claude、Gemini、Llama 等模型的性能；通过简洁的声明式配置集成命令行与 CI/CD。The GitHub Action for Promptfoo. Test your prompts, agents, and RAGs. AI Red teaming, pentesting, and vulnerability scanning for LLMs. Compare performance of GPT, Claude, Gemini, Llama, and more. Simple declarative configs with command line and CI/CD integration.

AI-ML Companion：一个通过"看 AI 运作"来学习 AI 与 ML 的交互式平台 — 28 条学习路径、400+ 模块、实时可视化 — 另有 20+ 端到端真实项目，覆盖经典 ML、深度学习、计算机视觉到生产级 LLM 与多 Agent 系统。AI-ML Companion: an interactive platform to learn AI & ML by watching it work - 28 tracks, 400+ modules, live visualizations - plus 20+ end-to-end real world projects from classical ML, DL, Computer Vision to production LLM & multi-agent systems.

面向 Polymarket 预测市场的交易机器人——可在终端浏览 CLOB 市场、查看订单簿，并执行 edge detection、流动性提供与跨市场套利策略，支持 paper trading 与风险限额。开源教育工具——不构成投资建议。非官方社区项目，与 Polymarket 无关。Polymarket trading bot for prediction markets — browse CLOB markets, watch the order book in the terminal, run edge detection, liquidity provision and cross-market arbitrage strategies with paper trading and risk limits. Educational open-source toolkit — not financial advice. Unofficial community project, not affiliated with Polymarket.

真实 AI Agent 安全事件、入侵和漏洞的精选时间线（2024-2026）。每条记录均标注来源和日期。A curated timeline of real AI agent security incidents, breaches, and vulnerabilities (2024-2026). Every entry sourced and dated.

基于公开 Hyperliquid API 独立分析 ROI、胜率和 PnL，检测 martingale/网格恢复策略，评估最大回撤与风险调整后收益。只读终端检查工具——不交易、不需要 API key。非官方社区项目，与 Hyperliquid 无关联。Independently analyze ROI, win rate, and PnL using the public Hyperliquid API, detect martingale/grid recovery strategies, and assess maximum drawdown and risk-adjusted returns. Read-only terminal checker — no trading, no API keys. Unofficial community project, not affiliated with Hyperliquid.

Apeireth——一款基于 Rust 的 AGI 操作系统 / LLM 基座。85 个 crate：陪伴器官、世界模型、好奇心、假设检验、双层洋葱式安全Apeireth — An AGI Operating System / LLM Base (Rust). 85 crates: companion organ, world model, curiosity, hypothesis testing, double-onion security.

Spotify iOS App 的 Liquid Glass 界面效果，无需越狱。Liquid Glass UI for the Spotify iOS app, no jailbreak

离线 Ed25519 签名工具包 —— 签署文件、验证签名、通过二维码交换密钥。纯 Python 实现 RFC 8032，支持 scrypt 密码短语与 ASCII armor。面向气隙环境的签名实验场Offline Ed25519 signing toolkit - sign files, verify signatures, exchange keys via QR. Pure-Python RFC 8032, scrypt passphrases, ASCII armor. Air-gapped signing playground.

开源 FDE Agent 与企业 AI 约束层：24 条规则的 git-diff 审计、自动快照回滚、规则注入、自我进化。以 9 个 DeepSeek Harness 插件 + MCP server（66 个工具）形式交付。MIT 许可。Open-source FDE Agent & constraint layer for enterprise AI: 24-rule git-diff audit, auto snapshot rollback, rule injection, self-evolution. Ships as 9 DeepSeek Harness plugins + MCP server (66 tools). MIT.

面向创意工具的 Skill 优先控制平面：共享 MCP/REST runtime、gateway、CLI、marketplace、安全与可观测性，覆盖工作室流水线。Skill-first control plane for creative tools: shared MCP/REST runtime, gateway, CLI, marketplace, safety, and observability across studio pipelines.

面向 coding agent 的本地护栏机制：策略、审批、86 个安全策略包、操作系统级沙箱、审计追踪，无需 Docker。Local guardrails for coding agents. Policy, approvals, 86 safety packs, OS sandbox, audit trail — no Docker.

面向 AI Agent 的 Metasploit：扫描、攻击并修复 AI Agent 与 MCP 服务器。开源安全工具包Metasploit for AI agents: scan, attack, and fix AI agents and MCP servers. Open source security toolkit.

SPY put-credit 验证与真金白银的 control plane，具备券商账本支持、确定性 risk gates、hybrid RAG、对账及每月 $1k 税后收益证据追踪。SPY put-credit validation and real-money control plane with broker-backed ledgers, deterministic risk gates, hybrid RAG, reconciliation, and $1k/mo after-tax evidence tracking.

grantex 是面向 AI Agent 的身份、授权与审计基础设施，堪称 Agentic 互联网的"OAuth 时刻"。提供通用 SDK 与云服务，让任意 AI Agent 可代表人类在限定、可撤销权限下执行操作，并具备加密身份与不可篡改的审计追踪。开发者可在数分钟内完成集成。grantex is the identity, authorization, and audit infrastructure for AI agents — the "OAuth moment" for the agentic internet. We provide a universal SDK and cloud service that lets any AI agent act on behalf of a human with scoped, revocable permissions, cryptographic identity, and an immutable audit trail. Developers integrate in minutes.

ThumbGate 预动作检查通过排序后的教训和反复失败进行自我改进，硬性阻断检测到的密钥泄露，并在严格模式下阻断匹配项。ThumbGate Pre-Action Checks self-improve from ranked lessons and repeated failures, hard-block detected secret leaks, and block matches in strict mode.

基于 Rust 的 SIP 与 RTP 抓包、分析与安全工具，单二进制，仅依赖 libpcap。SIP & RTP capture, analysis, and security tool. One binary, one dependency (libpcap), built in Rust.

一个以证据为引领的六语种 LLM 实战手册：包含可迁移的核心、Codex 旗舰路线，以及 ChatGPT、Claude Code、Gemini、DeepSeek 和 Grok 的适配器。An evidence-led, six-language LLM playbook: the transferable core, the Codex flagship track, and adapters for ChatGPT, Claude Code, Gemini, DeepSeek, and Grok.

用于评估 Agentic AI 应用的 AI 红队工具与 LLM 安全框架，测试 prompt injection，支持漏洞评估、SBOM 生成与静态分析。AI red-teaming tool and LLM security framework to evaluate agentic AI applications. Tests prompt injections, handles vulnerability assessment, SBOM generation, and static analysis.

🔐 Replayable RAG —— 本地优先、可审计的知识推理平台。Graph-RAG + 仅追加审计日志 + 确定性矛盾仲裁 + 人类把关的自演化。可逐字节回放任意历史知识状态。100% 本地（Ollama）。MIT 许可。🔐 Replayable RAG — a local-first, auditable knowledge-reasoning platform. Graph-RAG + append-only audit log + deterministic contradiction arbitration + human-gated self-evolution. Replay any past knowledge state byte-for-byte. 100% local (Ollama). MIT.