← Back to directory

sharkcage

Trust layer and sandboxing for OpenClaw — per-skill kernel sandboxing, capability model, tool interceptors

Setup / get started

Start from the GitHub repository: source code and README for sharkcage.

Alternatives to sharkcage

Similar projects in this directory:

  • ironlink — IronLink is a distributed AI agent orchestration framework secured by a zero-trust Rust kernel. It transforms hardware…
  • OpenClaw-Host — OpenClaw Host is a Dockerised AI agent for automating code changes, Git workflows, and system tasks. It works in a…
  • skills — Provide AI agents with modular skills to use open-source security tools for labs, browser simulation, and code…
  • Safe OpenClaw Setup Guide — A guide on the safest way to run OpenClaw — covering security best practices, sandboxing, and safe deployment…
  • meridian-intelligence — Track governed competitor intelligence on Meridian’s constitutional kernel with truthfully bounded public intelligence…
By wan0netAdded 3/31/2026