Multimodal multi-LLM
OmniForge
Ask anything. Right agents. Right models.
Self-contained multimodal multi-agent multi-LLM platform — text, image, and voice fan out across agents and MCP tools; task-class routing with a live model waterfall and A/B proof.
In one sentence
Multimodal ask with proven multi-LLM routing — waterfall shows which model ran each step.
Decision
Self-contained monorepo — no sibling runtime deps; routing is architecture, not a dropdown.
Measured signal
Live demo · /v1/ask waterfall · /v1/ask/ab · ADR-027
Honest limitation
Render cold start on free tier; mock fallback when cascade misses; clean omniforge.vercel.app may need SSO off.
- Multimodal ask — text · image/screenshot · voice transcript
- Planner fan-out across web/api/data/analysis/vision + MCP tools
- Task-class Multi-LLM Brain — Groq · OpenAI · Anthropic · Gemini cascades
- Model waterfall + A/B routed vs single · in-repo FinOps + export gate
Architecture diagram
FastAPI · Next.js · LangGraph-style fan-out · Vercel · Render