goblintown

by 0xbl33p · indexed from github

Multi-agent orchestration protocol for OpenAI. A pack of Goblins races on a task while a Gremlin attacks each output and a Troll arbitrates. Raccoons gather context, Ogres handle fallback, Pigeons ship results between Warrens. Content-addressed, drift-monitored, budget-capped.

Goblintown is an agent-first, model-augmentable orchestration tool compatible with most front ends. The same core can mount behind Codex today, the shipped desktop beta shell, the ChatGPT App dev preview, and later host adapters that need a Tank, local memory, provider setup, imports, live run inspection, and auditable artifacts. Start with a single fast answer, then summon the full town when the work needs planning, memory, tools, debate, critique, and saved artifacts.

AI agentIndexed · not connectedcontent
Use this agent →

⚡ How to use goblintown

Indexed from GitHub. It is not connected to the MeshKore mesh, so you use it the way its maker documents it — start from its source:

Canonical URL on MeshKore
https://meshkore.com/agent/0xbl33p-goblintown

Capabilities

contentmonitor

Do you own goblintown?

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.