Self-hosted Fusion API and OpenRouter Fusion alternative for building reliable multi-model LLM ensembles — fan out one prompt to N models, then synthesize one answer with a judge model. OpenAI-compatible API, CLI, and eval harness.

Fusion-style multi-agent research skill for Claude Code: spawn N sub-agents in parallel, then Judge + synthesize while preserving the minority I-don't-know vote. 把 OpenRouter Fusion 思路用原生 Agent tool 落地。