Skip to content

Ailerix

Model router that never names a model: Jev classifies the task family, then a cost-per-task Pareto walk picks the cheapest frontier point clearing its quality floor.

Stars
2
Language
TypeScript
Published by
Community
Author
tylerjharden
Last verified
Oct 2026

tylerjharden/ailerix

User repository on GitHub

View on GitHub

Type-safe model router. Jev (System One) banks each request to a typed catalog route.

Forks
0
Last pushed
Updated Sep 2026

Repo stats from the GitHub API, cached Oct 2026.Homepage

About this project

Type-safe model router. An OpenRouter competitor that uses TypeSafe Jev (System One) to classify every request, then walks an Artificial Analysis cost-per-task Pareto chain to bank a provider. You never name a model. The only public slug is ailerix/auto. An aileron banks an aircraft. Ailerix banks a request.

Quoted from the project's README. Read the full README.

Highlights

  • Jev classifies task families only, seven of them, and never puts model ids into the routing questions.
  • POST /api/v1/route returns aa_id, cost-per-task, the floor and reasons; ailerix/auto is the only slug completions accepts.
  • Development runs on a checked-in Artificial Analysis fixture with no live scrape, and a local engine keeps the playground up without credentials.
  • A Jev-compatible /api/v1/systemone endpoint exposes Choice, Score and Noul alongside an OpenAI-shaped chat completions route.

Watch out

This repo is a working slice of the product contract rather than the product: the dashboard is a mock, completions stay mocked until you add provider keys, and routing only reaches hosted Jev when TYPESAFE_API_KEY is set. Live Artificial Analysis ingest needs a commercial licence, so every frontier figure in development comes from a checked-in fixture. The domain notes, the isitagentready.com score and the OpenRouter feature-parity matrix are the author's own claims, not measurements. Copy reviewed against the repository README on 2026-10-04, not from running it.

Questions about this entry

Short answers drawn from the linked project or page.

More Jev resources like this

13GitHub stars
Pi extension that classifies each task with Jev over OpenRouter and routes it to a Pareto-optimal model balancing measured quality, cost, and latency under a role policy.
Jev Agents & MCP#community#jevbest#catalog-import
10GitHub stars
Node router that sends each query to the cheapest capable LLM tier by asking Jev to classify demand against your tier descriptions, with no LLM call spent on routing.
Jev Agents & MCP#community#jevbest#catalog-import
5GitHub stars
A Claude Code function hook that sends AskUserQuestion dialogs to Jev and draws a probability per option above the dialog, so you still choose while seeing how confident the model is.
Jev Agents & MCP#community#jevbest#catalog-import
3GitHub stars
Model router that asks Jev eleven questions in one call and lets a YAML policy turn the answers into a tier. Every request starts on the fast tier and only escalates on evidence such as multi-step reasoning, hard difficulty, high stakes or safety, and every decision is logged without the message text.
Jev Agents & MCP#community#jevbest#catalog-import
6GitHub stars
A per-prompt capability router for coding agents: a local BM25 shortlist of installed skills, MCP servers, subagents and commands, then one Jev request injects at most one suggestion plus two runner-ups.
Jev Agents & MCP#community#jevbest#catalog-import
10GitHub stars
Two pi extensions driven by Jev judgments: one replaces summary-based context compaction with keep, drop and shorten calls, the other scores each prompt for difficulty and switches pi's model before the turn runs.
Jev Agents & MCP#community#jevbest#catalog-import
Back to all resources

From the Jev community

Posts from builders shipping with Jev right now.

Follow @typesafeai