Search

A self-hosted, secure code execution sandbox for LLM agents deployed on your cloud infrastructure using SkyPilot. Built on llm-sandbox for multi-language code execution.

🤖 Build an AI chat app with multi-model support, secure user data isolation, and advanced features like model integration and persistent conversation management.

Open-source tool to package your AI agent's capabilities into secure, multi-protocol service interfaces — REST API, MCP Server, WebSocket, Webhook, and Bot adapters.

Burtson Icons: an open-source stroke icon set for AI agents, security, provenance, infrastructure and evidence work. 24px grid, 2px stroke, zero dependencies.

PrivAgents is a privacy-first framework where intelligent agents interact with a secure MCP (Model Computation & Processing) server to perform encrypted data analysis using homomorphic encryption.

Standardized AI agent environment profiles, quality gates, security policies, and memory contracts for Cursor, Claude Code, Codex, Gemini / Antigravity, OpenCode, and GitHub Copilot.

An enterprise framework implementing the Agent Operation Authorization protocol with cryptographic identity binding, fine-grained authorization, and semantic audit trails for secure AI agent operations.

MAPLE - Production-ready multi agent communication protocol with integrated resource management, type-safe error handling, secure link identification, and distributed state synchronization.

Ory Agent Security for the Cloudflare Agents SDK — per-tool authorization, tracing, and identity propagation by wrapping the AI SDK tools passed to streamText. Built on @ory/argus.

User interface for AI agent assistants that run Python code safely on your device through an intuitive chat interface. Supports local and cloud LLM models with built-in security features.

A CLI tool for AI Agents to handle file operations and cloud storage with JSON output. Support for S3, R2, MinIO, and more. Token-aware, secure, and agent-first design.

A comprehensive demonstration of Model Context Protocol (MCP) servers and clients, showcasing AI-powered tools and multi-agent systems for code analysis, security scanning, and intelligent automation.

Chaterm is an Electron-based AI-driven terminal tool that provides intelligent command completion, multi-device management, AI Agent capabilities, and enterprise-grade security features.

Standalone contrib extensions for pi — browser, codebase, diff, healthcheck, network-monitor, observatory, path-security, rate-limiter, repl, sleep, system-monitor, tool-config

Agenter — Backend-agnostic SDK for autonomous coding agents supporting Claude, Codex, Anthropic, and AWS Bedrock with streaming, budget controls, security validation, and LangGraph/PydanticAI adapters.

A small, complete, runnable environment for experimenting with agentic pipelines: LangGraph agents, MCP tool servers, a LiteLLM gateway, memory, Langfuse traces and a security boundary. Runs offline.

Architecture → Messages → Tools → Resources → Prompts → Streamable HTTP → Clients → MRTR → Tasks → Extensions → Authorization → Enterprise-Managed Auth → Security → Gateways → Agents → RAG → Testing → Observability → Deployment

High-performance Model Context Protocol (MCP) server gateway for Claude Pro. Seamlessly bridges Claude Web UI with local environments, file systems, and secure execution layers.

Universal MCP Gateway & Agent Runtime in Rust. Securely bridges frontier AI models to local coding executors across isolated workspaces. Headless Linux daemon & desktop GUI.

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.