
sandbox-agent
A durable process per agent, with memory that survives restarts

A durable process per agent, with memory that survives restarts

Capability-based WASM runtime for executing untrusted AI-generated code with enforced CPU, memory, time, I/O, and filesystem limits. Provides…

Runtime security gateway for AI agents: cryptographically attests tool calls, enforces policies, sandboxes execution, and logs tamper-evident audit…

Ephemeral microVM sandbox for AI agents with network allowlisting, secret injection via MITM proxy, and VM-level isolation. Boots in under a second,…

Securekit is a protocol-agnostic security kernel that enforces zero-trust, sandboxed execution for AI tool use. It sits between any LLM or agent…

Async API security scanner in Rust for CORS, CSP, GraphQL, JWT, OpenAPI, and active API posture checks.

A script that automatically submits files to Hybrid Analysis (API)

Run untrusted AI code safely, fast