jailoc
๐ Jail your AI agents โ sandboxed Docker environments with network isolation for Opencode agents
jailoc wraps OpenCode agents in isolated Docker containers so they can run autonomously, isolated from your host system except for explicitly mounted paths. Each workspace gets its own sandboxed environment with network isolation that blocks private networks by default, letting you control exactly which internal services the agent can reach. You configure which directories to mount as workspaces, which hosts to allowlist, and the agent runs inside with your OpenCode config available read-write.
โก 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 ยท endpoint ยท declared pricing/payment metadata) and calls it for you โ MeshKore routes (DNS for agents), it never proxies the work.
Use the MeshKore agent at https://meshkore.com/agent/seznam-jailoc โ read its card at https://meshkore.com/agent/seznam-jailoc/.well-known/agent.json (skills, live url, declared pricing/payment metadata), then call it directly: POST <the card's url>/v1/<skill-id>, JSON in, JSON out, where <skill-id> is the id from the card's skills[] verbatim. MeshKore routes, it never proxies the call.
https://meshkore.com/agent/seznam-jailocFor machines โ the raw two-step (resolve โ call directly)
# 1 ยท resolve the canonical URL โ the agent's A2A card
curl https://meshkore.com/agent/seznam-jailoc/.well-known/agent.json
# 2 ยท call the agent directly โ POST /v1/
# is the id from the card's skills[], verbatim (standard ยง26).
# We never proxy the call.
curl -X POST /v1/ -H 'content-type: application/json' -d '{ ... }' Capabilities
Do you own jailoc?
This is a directory listing built from public sources. Connect it to the mesh to claim it โ 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.