Composio powers 1000+ toolkits, tool search, context management, authentication, and a sandboxed workbench to help you build AI agents that turn intent into action.
Repository Index
47,133 repositories indexed
1–19 of 19 · Most stars
The most comprehensive authentication framework
- authentication
- oauth
- oauth2
- typescript
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 line and CI/CD integration. Used by OpenAI and Anthropic.
🔒 A compiled checklist of 300+ tips for protecting digital security and privacy in 2026
- privacy
- security
- censorship
- cybersecurity
The all-in-one, open-source backend platform for agentic coding. InsForge gives your coding agent database, auth, storage, compute, hosting, and AI gateway to ship full-stack apps end-to-end.
Sandbox for developing and testing UI components in isolation
Open Source Cloud Native Application Protection Platform (CNAPP)
- cloud-native
- vulnerability-management
- threat-analysis
- devsecops
Android Reverse-Engineering Workbench for VS Code
- apktool
- apk-decompiler
- apk-editor
- smali
Deprecated in favour of Video.js 10; security fixes only until January 2028. UI components and hooks for building video and audio players on the web.
- player
- web-components
- html
- javascript
基于 REA 深度拆解并高保真还原 Claude 官方桌面端 UI。还原 30 个独立 React 组件与 8 项硬核交互物理算法，附带 3000+ 行逆向分析手册。
- anthropic
- audioworklet
- claude
- design-system
LunaSec - Dependency Security Scanner that automatically notifies you about vulnerabilities like Log4Shell or node-ipc in your Pull Requests and Builds. Protect yourself in 30 seconds with the LunaTrace GitHub App: https://github.com/marketplace/lunatrace-by-lunasec/
- tokenization
- web-security
- compliance
- security
Agent-first reverse engineering for macOS, Windows and Linux: any ACP agent reads, renames and patches binaries, Android apps and GPU kernels next to you.
Tool to export Juice Shop challenges and hints in data format compatible with CTFd, RootTheBox or FBCTF
- owasp
- ctf
- ctfd
- application-security
Open detection-rule standard for AI agent security threats — like Sigma, but for AI agents. Executable, testable rules for prompt injection, tool poisoning, context exfiltration and MCP attacks. Merged into open-source projects at Microsoft, Cisco, Gen Digital, MISP and FINOS. MIT-licensed.
- agent-security
- ai-security
- llm-security
- mcp-security
A production-ready SaaS template built with Next.js 15, Supabase, and Tailwind CSS. Includes authentication, user management, file storage, task management demos, and secure RLS policies. Now with a complete React Native + Expo mobile app template! Easily customizable with pre-built themes, i18n support (EN/PL/ZH), and legal documents.
Access control for AI agents. Set what Claude Code, Codex, Gemini, Cursor and any MCP server are allowed to do, review risky actions before they run, and keep every action on the record.
- ai-safety
- ai-security
- claude-code
- llm-agent
Security training for the apps you actually ship. Open your browser and start hacking.
Privacy-first Chrome extension for real-time website security analysis using on-device AI. Trust scores (0-100), phishing detection, SSL verification, cookie compliance & AI chatbot powered by WebLLM with zero external data transmission.
- browser-extension
- chrome-extension
- cybersecurity
- on-device-ai
Offers a collection of GraphQL directives for easy validation, authorization, and sanitation, simplifying the implementation of complex functionality in GraphQL APIs. It ensures secure and efficient GraphQL APIs with pre-built solutions.
- graphql
- validation
- authorization
- directive