CalibratedDecisions.

Repo · Routing & model choice

A3m Router

Self-hosted OpenAI-compatible router on port 8787 that sends each prompt to the cheapest capable model across free, budget, mid and premium tiers,…

Open github.com ↗

From the repository

⚡ Adaptive multi-model LLM router — 80+ providers, Jev System One single-pass routing (model=jev-auto), pheromone-trail failover, parallel ensemble merge. npm: adaptive-memory-multi-model-router

ai-gatewayapi-gatewayartificial-intelligencebenchmarkcircuit-breakercli-toolcost-optimizationdevtoolsensemblellmllm-gatewayllm-routingmemorynodejsnvidiaopenai-proxyparallel-llmrouterarenasemantic-cachetypescript

How builders describe it

Self-hosted OpenAI-compatible router on port 8787 that sends each prompt to the cheapest capable model across free, budget, mid and premium tiers, with heuristic auto and Jev-backed routing modes.

The decision Jev makes

Pick an agent, a model, a skill from a catalog, or a function and its arguments.

Where it fits

Deciding which agent, model, skill or function should handle a request. Jev is a natural router: the options are fixed and the confidence tells you when to fall back. All 348 routing & model choice projects →

Related projects