Search

LangGraph Multi-Agent Automated Testing Suite for Node.js/TypeScript — 8 AI agents that analyze, test, review, secure & document your project. OWASP Top 10, Zero-Day scanning, 100+ vulnerability patterns.

An open framework for a persistent, self-regulating AI operations system on a coding-agent CLI: tiered memory + SSOT, security-first gates, a knowledge pipeline, multi-agent protocols, session survival, and a zero-dependency cockpit.

An opinionated development framework for building production-ready AI agents with LangGraph. It grounds AI coding assistants (Cursor, Windsurf, Cline) and guides them to use local, official documentation, ensuring reliable, secure, and observable agentic workflows.

Production-grade PostgreSQL MCP Server. Empowers LLMs with 40+ tools for deep database interaction, including schema inspection, secure query execution, performance analysis, and administrative tasks. Built for reliable AI-driven development.

The local firewall for AI agents: route and repair them, and keep your secrets off the model, the API relay, and the supply chain. Local credential masking, per-route model routing, and security detectors on the wire. Free and fully open source.

An open-source secure data access gateway for AI agents. It provides database safety access services to AI agents through the MCP protocol. 一个面向 AI Agent 的开源安全数据访问网关，通过 MCP 协议为 AI Agent 提供数据库安全访问服务。

Opinionated, security-first AI workflow for Salesforce DX projects in Claude Code. 11 specialist subagents + 56 skills, Headless-360 native (MCP, Agentforce, Trust Layer), prod orgs hard-blocked by default.

Secure infrastructure for AI agents operating Linux hosts — persistent terminal sessions powered by rmux, full-chain audit logging, MCP-native interface for all major AI clients, with file transfer and multi-host orchestration.

Call 1,680+ AI agent tools via x402 USDC micropayments on Base. Bring your own wallet — pay per call, no API keys, no credits. Gas, captcha, web scraping, token security, DeFi data, and more.

The SmythOS Runtime Environment (SRE) is an open-source, cloud-native runtime for agentic AI. Secure, modular, and production-ready, it lets developers build, run, and manage intelligent agents across local, cloud, and edge environments.

Masterless, terminal-native coding agent (Claude Code-style: reads, edits, runs code) for Claude, Gemini, Cerebras, Groq, and Ollama. Provider-agnostic with evals, memory, security hardening, 200+ plugins, and MCP. MIT.

🔥 CogitoAgent — An autonomous AI agent, cloud-driven but locally executed. It continuously thinks, automatically analyzes, and integrates practical tools like file management, code execution, web search, and database operations — secure and efficient.

Turn Android Termux into an autonomous AI agent and security orchestrator. Powered by a local ReAct framework with 50 system tools and MCP support, a background task │ scheduler, on-device ADB controls, and a unified Web UI & Telegram Bot.

AI security analyst that investigates suspicious emails, logins and call transcripts with tools, backs every verdict with evidence, and waits for human approval before risky actions. Spring Boot gateway built; Python agent and React dashboard in progress.

CodeGlide Agents that transforms API specifications and source code into fully functional, production-ready MCP (Model Context Protocol) servers. It automates the entire generation process while ensuring security best practices and providing comprehensive deployment configurations.

AI-Agent is an AI-powered assistant that uses natural language prompts to send emails and create Google Calendar events. Built with React, it features Google OAuth for secure login and uses MCP for seamless client-server communication.

DeepSeek Harness (dsh) plugin: run work as a small crew of role agents (product manager, researcher, architect, engineer, QA, code reviewer, security reviewer, doc reviewer) that talk through files on disk, with the PM as the only voice to the user.

An open-source AI agent framework skeleton. Built by a Chinese lawyer who cannot code. Needs your genius ideas to solve: Fully Intrinsic AI, Auto-Evolution, Anti-Hallucination, Security. A true intelligent agent robot completed by the community.

A complete FastAPI application for creating a WhatsApp -> LLM chat agent. Features per-user memory, OpenAI tool-calling, secure n8n integration for proactive messaging, and full setup guides for Cloudflare Tunnels and permanent Meta tokens.

Jebat Agent — 30-second setup for AI agent workspace with 8 local LLM models (Gemma 4, Qwen2.5, Hermes3, Phi-3), IDE integration, multi-agent orchestration, markdown rendering, and enterprise security.