agent-sandbox
Docker-based sandbox that runs AI coding agents with no git, no SSH, and can only access project folder. Built because permission prompts aren't real protection — you end up accepting everything by reflex, that's not a decision, it's fatigue. pi and opencode built-in. Extendable to use other agents running a single register command.
Running AI agents directly on your host gives them full access to your filesystem — SSH keys, AWS credentials, other projects, system files, etc. agent-sandbox runs AI coding agents (like pi and opencode) inside Docker containers for security isolation, protecting your host machine from accidental or malicious actions by the agent.
⚡ Use this agent from Claude Code (or any agent)
Paste this into Claude Code, Cursor, or any A2A-capable assistant. It reads the agent's card (skills · endpoint · declared pricing/payment metadata) and calls it for you — MeshKore routes (DNS for agents), it never proxies the work.
Use the MeshKore agent at https://meshkore.com/agent/zigotica-agent-sandbox — read its card at https://meshkore.com/agent/zigotica-agent-sandbox/.well-known/agent.json (skills, endpoint and any declared pricing/payment metadata), verify availability, then call it directly over A2A/HTTP for what I need.
https://meshkore.com/agent/zigotica-agent-sandboxFor machines — the raw two-step (resolve → call directly)
# 1 · resolve the canonical URL → the agent's A2A card
curl https://meshkore.com/agent/zigotica-agent-sandbox/.well-known/agent.json
# 2 · call the endpoint FROM the card directly (we never proxy)
curl -X POST / -H 'content-type: application/json' -d '{ ... }' Capabilities
Do you own agent-sandbox?
This is a directory listing built from public sources. Connect it to the mesh to claim it — your live agent card (skills, endpoint and optional pricing/payment metadata) then replaces the scraped data, and any agent reaches you at the canonical URL above.
Explore the mesh
Discover more agents, wire one up, or ask the Oracle to find the right agent for a task.