How does Hydra determine which model to use for a task?

It uses Sequential Probability Ratio Testing (SPRT) to stop querying once a configurable confidence threshold is met, routing tasks to the cheapest model that clears this bar. It also uses a blast-radius analyzer to raise confidence requirements for changes affecting widely-used code.

Is Hydra free to use?

Yes, Hydra is free and open-source under the MIT license. However, users still pay the underlying providers for the tokens Hydra dispatches to them.

What types of AI models does Hydra support?

Hydra discovers and routes to installed CLI agents like Claude Code and Codex, API keys for providers like OpenAI and Anthropic, local servers like Ollama and LM Studio, and OpenRouter-backed providers.

Does Hydra require a hosted service or dashboard?

No, Hydra is a local-first CLI tool. It does not have a hosted UI, dashboard, or HTTP API, and it keeps routing decisions and audit logs on your machine.

Who is Hydra designed for?

It is best for individual developers and small teams who already use multiple AI models and want a privacy-preserving, scriptable router to optimize costs and manage local fallbacks.

Hydra

Local-first trust control plane that routes AI tasks to the cheapest model that clears your confidence bar.

Free· Free and open-source under the MIT license; no hosted tier or paid plan. You still pay whatever the underlying providers (Anthropic, OpenAI, OpenRouter, etc.) charge for tokens Hydra dispatches to them.AgentsMulti-provider: routes across Claude, GPT, Gemini Flash, OpenRouter-hosted models, and local Qwen via Ollama / LM Studio

Visit website →

In short

Hydra is an open-source orchestration layer that dispatches AI tasks to the most cost-effective available model based on confidence scores. It is best for developers who want to minimize API costs by keeping routine work on local or cheaper models while escalating complex tasks to frontier models.

Best for

Individual developers and small engineering teams who already juggle Claude, GPT, Gemini, and local Ollama/LM Studio models and want a scriptable, privacy-preserving router that keeps routine work off frontier APIs.

Skip if

Non-developers, teams that need a hosted control plane with SSO and org-wide dashboards, or single-provider shops that just want one model — Hydra's payoff comes from routing across many heads.

Hydra (CLI: hyctl) is an open-source, local-first orchestration layer for multi-model AI workflows. Instead of forcing every request through a single hosted router like OpenRouter, LiteLLM, or Portkey, Hydra discovers every 'head' already available on your machine — installed CLI agents (Claude Code, Codex, Gemini CLI), API keys in your environment, local Ollama or LM Studio servers, and OpenRouter-backed providers — and then dispatches each task to the cheapest head that can clear a configurable confidence threshold (default 0.95). It categorizes work across a ten-tier cost ladder and uses Sequential Probability Ratio Testing (SPRT) to stop querying as soon as the target confidence is met, so boilerplate rewrites don't burn frontier-model tokens and only genuinely hard tasks escalate to Opus- or GPT-class models. A 'blast radius' analyzer inspects your dependency graph and raises the confidence bar for changes that touch widely-used code, while a bundled local Qwen model acts as an offline failsafe so routing keeps working with zero network calls. An on-device 'accountability ledger' records which head handled what, giving teams an audit trail without shipping prompts or code to a hosted control plane. Typical workflows: point hyctl at your repo, run `hyctl probe` to enumerate heads, then use `hyctl dispatch` in place of your usual model CLI so refactors, tests, and doc-writing get routed locally while architecture questions escalate. Reported outcomes on the landing page include 58% of tasks staying fully local, ~73% median cost reduction versus always-frontier routing, and roughly a dozen heads discovered on a typical dev machine.

Editor's take

Hydra is the rare meta-router that respects your keys and your machine — decisions happen locally, the ledger stays local, and it slots into an existing multi-CLI setup instead of demanding you re-pipe everything through a hosted proxy. The SPRT + blast-radius framing is smart, but the headline savings numbers are self-reported and the project is still early, so treat it as a promising power-user tool rather than a settled default.

— The AI Tool Bible editorial team

Pros

✅ Genuinely local-first — routing decisions and the accountability ledger stay on your machine, unlike hosted meta-routers.
✅ Discovers heads you already have (Claude Code, Codex, Ollama, LM Studio, OpenRouter keys) instead of re-plumbing you through one vendor.
✅ SPRT-based confidence stopping avoids burning frontier tokens on tasks a cheaper model already answered well.
✅ Blast-radius heuristic ties confidence requirements to code impact, so trivial edits go cheap and load-bearing changes escalate.
✅ Ships with a local Qwen failsafe so dispatch keeps working offline or when an API is down.
✅ MIT-licensed and installable via brew, npm, pip, or a shell script — easy to adopt or fork.
✅ Provider-neutral by design; no lock-in and no need to hand a third party your API keys.

Cons

⚠️ CLI-only — no hosted UI, dashboard, or documented HTTP API for non-terminal workflows.
⚠️ Reported cost-savings numbers (73% median, 58% local) come from the vendor's own landing page and aren't independently benchmarked.
⚠️ Confidence scoring and blast-radius weighting are heuristics; miscalibration can silently route hard tasks to weak models.
⚠️ Value depends on already having multiple model backends installed and configured — thin benefit for single-provider users.
⚠️ Young project on a personal-namespace domain (uvansa.com / github.com/ankit373) with limited community track record versus LiteLLM or OpenRouter.
⚠️ No team/org features documented — the on-device ledger doesn't obviously roll up across multiple developers.

Use cases

multi-model CLI routingcost-optimized code generationoffline AI coding with local fallbackconfidence-gated task dispatchblast-radius-aware refactorson-device audit ledger for AI usageboilerplate work on cheap/local modelsescalation of hard tasks to frontier modelsvendor-neutral agent orchestration

Frequently asked

How does Hydra determine which model to use for a task?: It uses Sequential Probability Ratio Testing (SPRT) to stop querying once a configurable confidence threshold is met, routing tasks to the cheapest model that clears this bar. It also uses a blast-radius analyzer to raise confidence requirements for changes affecting widely-used code.
Is Hydra free to use?: Yes, Hydra is free and open-source under the MIT license. However, users still pay the underlying providers for the tokens Hydra dispatches to them.
What types of AI models does Hydra support?: Hydra discovers and routes to installed CLI agents like Claude Code and Codex, API keys for providers like OpenAI and Anthropic, local servers like Ollama and LM Studio, and OpenRouter-backed providers.
Does Hydra require a hosted service or dashboard?: No, Hydra is a local-first CLI tool. It does not have a hosted UI, dashboard, or HTTP API, and it keeps routing decisions and audit logs on your machine.
Who is Hydra designed for?: It is best for individual developers and small teams who already use multiple AI models and want a privacy-preserving, scriptable router to optimize costs and manage local fallbacks.