Stars
😼 优雅地使用基于 clash/mihomo 的代理环境
LLM API 管理 & 分发系统，支持 OpenAI、Azure、Anthropic Claude、Google Gemini、DeepSeek、字节豆包、ChatGLM、文心一言、讯飞星火、通义千问、360 智脑、腾讯混元等主流模型，统一 API 适配，可用于 key 管理与二次分发。单可执行文件，提供 Docker 镜像，一键部署，开箱即用。LLM API management & k…
[NOTE] Parent repo is migrating ownership, until the operation is done this repo is blocked. The free build of Claude Code. All telemetry removed, security-prompt guardrails stripped, all experimen…
Runtime policy enforcement for AI agents. Cryptographic audit trail, human-in-the-loop approvals, kill switch. Zero code changes.
Static security scanner for LLM agents — prompt injection, MCP config auditing, taint analysis. 49 rules mapped to OWASP Agentic Top 10 (2026). Works with LangChain, CrewAI, AutoGen.
🦞 MCP server for OpenClaw - secure bridge between Claude.ai and your self-hosted OpenClaw assistant with OAuth2 authentication
tinman watches other tinmen and keeps them in check.
🛡️ Security scanner for OpenClaw skills — detect malicious patterns before installing
Security evaluation harness for OpenClaw agents. 280+ attack payloads across prompt injection, tool exfiltration, context bleed, privilege escalation, supply chain, MCP, indirect injection, evasion…
Revolutionary security scanner for AI agent skills - LLM-powered semantic analysis, attack chains, behavioral sandbox
PinchBench is a benchmarking system for evaluating LLM models as OpenClaw coding agents. Made with 🦀 by the humans at https://kilo.ai
12 Lessons to Get Started Building AI Agents
Gemini polling proxy service （gemini轮询代理服务）
OpenAI 接口管理 & 分发系统，改自songquanpeng/one-api。支持更多模型，加入统计页面，完善非openai模型的函数调用。
Your own personal AI assistant. Any OS. Any Platform. The lobster way. 🦞
一个基于nano banana pro🍌的原生AI PPT生成应用，迈向真正的＂Vibe PPT＂; 支持上传任意模板图片；上传任意素材&智能解析；一句话/大纲/页面描述自动生成PPT；口头修改指定区域、一键导出可编辑ppt - An AI-native slides generator based on nano banana pro🍌
Security Scanner for Agent Skills
The official repository for the paper: Simple yet Effective Learning for Multi-Turn Jailbreak Attacks.
This tool helps users test prompt injections for good that help combat shadow AI. The tool allows users to generate injected documents, test against multiple AI models and evaluate results.
Agent Reinforcement Trainer: train multi-step agents for real-world tasks using GRPO. Give your agents on-the-job training. Reinforcement learning for Qwen3.5, GPT-OSS, Llama, and more!
🧠 LLMFuzzer - Fuzzing Framework for Large Language Models 🧠 LLMFuzzer is the first open-source fuzzing framework specifically designed for Large Language Models (LLMs), especially for their integra…
[ICLR'24 Spotlight] A language model (LM)-based emulation framework for identifying the risks of LM agents with tool use
开源SSL证书管理工具；全自动证书申请、更新、续期；通配符证书，泛域名证书申请；证书自动化部署到阿里云、腾讯云、主机、群晖、宝塔；https证书，pfx证书，der证书，TLS证书，nginx证书自动续签自动部署
Google Deepmind's PromptBreeder for automated prompt engineering implemented in langchain expression language.
The most advanced Nano Banana image generator and editor application. Your central hub for AI image generation and revisions. Intuitive UI features reference images, editing with image masks, versi…
Official inference repo for FLUX.1 models