@lloyal-labs/lloyal-agents
Multi-agent inference inside the decode loop — structured concurrency over shared KV state
lloyal-agents schedules memory, not strings. An agent is a branch of the model's live attention state: shared context is inherited, not re-sent — a new agent attends over everything before its fork point without paying a token for it. Advancing the whole fleet costs one GPU forward pass per tick. The more your agents share, the cheaper they get — the inverse of the API-call model, where every agent re-reads the world on every step.
⚡ How to use @lloyal-labs/lloyal-agents
Indexed from npm. 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/lloyal-labs-lloyal-labslloyal-agentsCapabilities
Do you own @lloyal-labs/lloyal-agents?
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.