open-source fugu
MAESTROone endpoint · every model · cheap-first · full cost shown
request lifecycle
▤
REQUEST
any client
→◉
CLASSIFY
task · difficulty
→▦
ROUTE
cheap → strong
→✓
VERIFY
accept / escalate
→■
ANSWER
+ route + cost
cheap model first → VERIFY → escalate to frontier only if needed
the point
Same quality. A fraction of the cost.
97%
cheaper · 92% of best quality
26×
answers per $
+4pt
quality vs random
2
APIs: OpenAI + Anthropic
0
GPUs required
the loop
It climbs only as high as it must.
CHEAP
MID
FRONTIER
the pool
Any model. Open and closed. Yours.
One OpenRouter key, or your own local models. Swap them in a JSON file. No retraining.
GLM-4.7 cheapQWEN3.5 cheapDEEPSEEK-V4 midKIMI-K2.7 midOPUS 4.8 frontierGPT-5.5 frontierGEMINI 3.1 frontier+ LOCAL ollama / vllmGLM-4.7 cheapQWEN3.5 cheapDEEPSEEK-V4 midKIMI-K2.7 midOPUS 4.8 frontierGPT-5.5 frontierGEMINI 3.1 frontier+ LOCAL ollama / vllm
no black box
Every answer ships its receipt.
{
"route": [
{ "deepseek/deepseek-v4-pro", "verdict": "REVISE" },
{ "anthropic/claude-opus-4.8", "verdict": "ACCEPT" }
],
"classify": { "task": "code", "difficulty": 0.78 },
"cost_usd": 0.0182,
"cost_vs_frontier_only_usd": 0.0241,
"savings_pct": 24
}vs the rest
Open. Honest. Runs anywhere.
| MAESTRO | Sakana Fugu | OpenFugu | |
|---|---|---|---|
| open source / self-host | YES | no | yes |
| any model (open + closed) | YES | 3 closed | research |
| OpenAI + Anthropic API | YES | no | partial |
| per-request cost shown | YES | no | no |
| no GPU required | YES | n/a | needs GPU |
| honest benchmark | YES | partial | mock |
🔌
DROP-IN
Change one base URL. Works in Claude Code, opencode, Cursor, the OpenAI & Vercel AI SDKs.
🛠
YOUR TOOL LOOP
Tools pass straight through. tool_calls returned verbatim. Maestro never runs your tools.
🏠
SELF-HOST
No GPU, no model hosting. Bring one key, or go fully local with Ollama / vLLM.
The open-source Fugu you can run.
Early build. Tested live on real models. MIT.