FUGU

by AI-Safeter · indexed from github

Sep-CMA-ES: the separable CMA-ES optimizer behind TRINITY's evolved LLM-coordinator router (Sakana FUGU). NumPy, no LLM required.

A PyTorch implementation of separable CMA-ES (Ros & Hansen, 2008), the gradient-free optimizer that TRINITY uses to evolve its LLM-coordinator router head. This is the method behind Sakana AI's FUGU multi-LLM orchestration service. A NumPy backend with an identical API ships alongside it for dependency-light use.

AI agentIndexed · not connectedai-infra
Use this agent →

⚡ How to use FUGU

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/ai-safeter-fugu

Capabilities

routerllm

Do you own FUGU?

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.