Search

A free, open-source LLM security proxy. Drop it between your app and any LLM provider to get rate limiting, audit logging, token tracking, and Prometheus metrics with no code changes to your app.

🤖 AI-powered Digital Marketing Assistant — content creation, strategy, research & analytics via Telegram. Bilingual EN/ID, Notion integration, pluggable LLM, security-hardened.

A free, open-source LLM security proxy. Drop it between your app and any LLM provider to get rate limiting, audit logging, token tracking, and Prometheus metrics with no code changes to your app.

Open-source Symfony bundle for Fakturownia API with built-in MCP tools, enabling AI agents (Codex, Claude, Cursor) to securely list clients/invoices and automate invoicing workflows.

Drop-in preflight guard for AI agents — one call to the x402 Trust Layer (guard + security grade + attestation) before any paid x402_fetch. Works with any agent framework (LangChain, CrewAI, Coinbase AgentKit).

OpenEnv-compliant RL environment for autonomous vulnerability patch management. Trains AI agents to balance security patching with uptime in complex dependency graphs. Meta PyTorch OpenEnv Hackathon 2026.

"An advanced AI-powered framework for automated bug bounty hunting and security research. Featuring autonomous reconnaissance, multi-model LLM integration, and real-time reporting via Telegram and CLI."

Elevate your AI assistants (like Claude & Cursor) into autonomous cybersecurity experts. Pentester-MCP integrates 200+ pentesting tools via the Model Context Protocol (MCP) using a secure Docker sandbox.

Production-ready Agent Client Protocol (ACP) adapter for Cursor CLI with comprehensive tool system, security framework, and seamless AI-powered coding assistance in ACP-compliant editors like Zed

AI-powered personal assistant framework built on AgentOS, forked from OpenClaw channels/integrations/bridges - adaptive agents with HEXACO personality, multi-channel communication, hierarchical inference, and human-in-the-loop security

Unified web search extension for pi with 9 backend providers — DuckDuckGo, Marginalia, Serper, Brave, Tavily, Exa, Firecrawl, LangSearch, and WebSearchAPI.ai. Auto-fallback, rate limiting, and secure key storage.

Agent Skills for AI coding assistants (Claude Code, Cursor, Copilot) — teaches MapQuest API best practices: geocoding, directions, static maps, search-ahead, store locators, traffic, and key security.

Production-Ready MCP Server Framework • Build, deploy & scale secure AI agent infrastructure • Includes Auth, Observability, Debugger, Telemetry & Runtime • Run real-world MCPs powering AI Agents

tinyAgent uniquely treats functions as first-class citizens, easily transforming them into powerful AI tools. Inspired by human organizational structures, it dynamically orchestrates specialized agents, balancing security and capability for complex tasks.

skelm — open-source TypeScript framework for secure, agentic, long-running workflows. Authoring, scheduling, and operating typed pipelines that mix deterministic code, LLM inference, and agent loops under default-deny permissions.

APIMesh — 23 pay-per-call web analysis APIs + 16-tool MCP server with autonomous API generation. Security audits, SEO, tech stack detection. x402 + Stripe MPP payments.

Klava is a cli for dead-simple usage cli code agents with any providers. Use claude code with your OpenAI-like provider. Make any code agents more secure - filter out any leaking secret keys and crypto keys from your filesystem.

Allwright — the AI teammate that runs on YOUR machine. Polls your Jira, runs jailed agents in your local checkouts, opens PRs, executes approved deploys, and audits security/testing/architecture. Credentials and code never leave your host.

Chartbrew + AI agents. MCP server exposing Chartbrew's documented API: teams, connections, datasets, dashboards, charts, live queries, and secure embedding. TypeScript · stdio · restricted/unrestricted tool modes.

An autonomous, AI-driven Security Operations Center (SOC). Uses FastAPI, PyTorch, local LLMs (Ollama), and the OpenClaw agent framework to detect anomalies and autonomously deploy firewall defenses via a Human-in-the-Loop dashboard.