AI · Agents · Blockchain · Crypto

Submit a project Sign in

Menu

Directory category

Agent Security & Sandboxing

Compare isolation, permissions and sandboxing tools for agent execution. Compare official resources, requirements and limitations.

38 projects

Directory results

Agent Security & Sandboxing projects

A Agentic Radar Agentic Radar is a Python command-line security scanner for agentic workflows.

M MCP Scanner MCP Scanner is an open-source Python developer tool for scanning Model Context Protocol servers and tools for potential security findings.

N Numbat Numbat is an open-source Go tool for endpoint visibility into AI-agent activity.

e2b.dev E2B is infrastructure that provisions an isolated microVM for each AI-agent session, giving agents a place to run code and use tools. Sandboxes can be hosted on E2B’s cloud or in a customer’s cloud account.

L Luan1Aoagent Luan1Aoagent is an open-source TypeScript AI agent for autonomous, authorized penetration testing and security research, using the Pi SDK and graph-based reasoning to coordinate tasks and preserve evidence.

A Agent Safehouse Agent Safehouse is a macOS command-line tool that uses `sandbox-exec` and composable, deny-first policy profiles to restrict local LLM coding agents’ access to files and integrations.

A Adr Adr is an open-source enterprise AI agent security system comprising tools for endpoint discovery, agent telemetry collection, security benchmarking, and suspicious-session detection.

A Agent Scan Agent Scan is a Python command-line security scanner that discovers AI agent components and scans agents, MCP servers and skills for prompt injections and other vulnerabilities.