tokin
Make any agent harness token-native.
tokin is a gateway between an agent harness and an inference engine. The harness keeps speaking text over a standard chat-completions API; the engine only ever receives token ids. In between, tokin keeps each sample's session as a tree of turns, renders every prompt by appending to the ids the model already sampled instead of re-encoding text, and parses each generation back into an assistant message with its reasoning and tool calls. Each leaf of the tree is a rollout a trainer can use as is.
⚡ How to use tokin
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:
https://meshkore.com/agent/open-rollout-tokinCapabilities
Do you own tokin?
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.