Secure, local and programmable sandboxes for AI agents — launch hardware-isolated microVMs in sub-100ms to execute untrusted code

Model Context ProtocolAI AgentsDocker

VIEW DETAILS →

An autonomous security research framework built on Claude Code, chaining static analysis, binary fuzzing, LLM-driven vulnerability validation, and exploit generation

Model & Inference FrameworkLarge Language ModelsMulti-Agent System

VIEW DETAILS →

An agent-powered vulnerability scanner for large codebases, featuring multi-stage pipelines, incremental recovery, and distributed execution.

AI AgentsNode.jsTypeScript

VIEW DETAILS →

An open-source, end-to-end platform for evaluating, observing, and improving LLM & AI Agent applications, unifying Tracing, Evals, Simulations, Guardrails, Gateway, and Prompt Optimization.

Model & Inference FrameworkLarge Language ModelsModel Context Protocol

VIEW DETAILS →

An architect-centric agentic swarm plugin for OpenCode featuring hub-and-spoke orchestration, gated QA pipelines, and multi-agent collaboration for trustworthy AI coding.

Multi-Agent SystemAI AgentsBun

VIEW DETAILS →

A lightweight CLI tool for managing and running single-responsibility LLM agents via declarative TOML configuration, featuring sub-agent delegation, stdin piping, persistent memory, and MCP tool support.

Model & Inference FrameworkMulti-Agent SystemModel Context Protocol

VIEW DETAILS →

A terminal command safety guardrail that intercepts and verifies dangerous shell commands before execution, supporting 8 shells, 100+ risk patterns, and AI agent integration.

Model Context ProtocolAI AgentsRust

VIEW DETAILS →

Self-hosted cloud orchestrator for running and managing AI coding agents within isolated Linux workspaces, with multi-agent runtime support, task scheduling, and Git-versioned configuration.

Multi-Agent SystemAI AgentsDocker

VIEW DETAILS →

Context-aware safety guard for coding agents and terminals that performs millisecond-level deterministic tri-classification (allowed/paused/blocked) via structured classifiers, providing fine-grained permission control for Claude Code, Codex, and user shells.

AI AgentsPythonCLI

VIEW DETAILS →

An open-source dependency manager by Microsoft for AI coding agents, enabling portable, secure, and governed distribution of skills, plugins, and MCP servers via apm.yml.

Model Context ProtocolAI AgentsPython

VIEW DETAILS →