Cloud gateways route your traffic through their servers. Eval tools score answers after the fact. Local runtimes each manage only their own models. Plot the field on two axes — hosted↔local and cost-routing↔trust — and one quadrant sits empty. That is where Hydra lives. Hover any star.
Routing isn't vibes. Hydra rides the cost/quality Pareto frontier, stops sampling the instant confidence clears the bar, and reads the code graph to know when a change is dangerous. Here is the actual math.
Single models are dots. For any one of them, Hydra's routed curve reaches equal or better quality at lower cost — it picks the best head per task .
Haiku Flash GPT-class all-Claude Hydra routes here Same quality, lower cost — the RouteLLM result, applied per dispatch. b · optimal stopping Confidence, then stop Hydra polls heads until the sequential test (SPRT) crosses your target confidence — then it stops early and banks the unspent heads.
accept ✔ stopped early Fewer heads, cleared bar — the calibrated number the field lacks. c · percolation-κ Blast radius (Molloy–Reed) κ = ⟨k²⟩/⟨k⟩. A hub file with many transitive dependents is cascade-capable — so it demands more confidence. Hover a node.
A task is classified, then falls down the ten-tier ladder (red = expensive, green = free/local) to the cheapest head that fits. If that head rate-limits, the fallback fires — terminating at local Qwen, which never runs out .
tier cost ramp active route fallback fired local terminal floor By the numbers every number has a mechanism Loud numbers. Real levers. No tokens-processed arms race. Each of these is something you can reproduce on your own machine with hyctl stats and hyctl probe .
Cost routing and fallback are table stakes — most tools have them. The differentiators are the rows nobody else can check: local-first, confidence/trust routing, and an on-device accountability ledger.
The interactive agent-tree cockpit is the one roadmap item here — every row checked above ships today in the CLI ( hyctl dispatch --confidence , hyctl graph blast , hyctl mcp ).
One Go binary. No daemon, no account, no cloud.
Finds every head: CLI agents, API keys, local servers.
Classify → tier → cheapest head that clears confidence.
One cortex, many heads. Route each task to the cheapest head that clears your bar — on your own hardware, with your spend and policy staying home.
Hacker News
news.ycombinator.com