Repo · Routing & model choice

EvolveRoute

Local-first LLM routing gateway (single Rust binary) that sits between your coding agents and LLM providers and routes each request to the most…

Open github.com ↗

From the repository

Stop burning premium model tokens on simple prompts. Save tokens. Spend them where they matter. Local-first self-evolving LLM router with a decision model + feedback flywheel. Judges each request and picks the right model on the fly. 7MB Rust, zero cloud, fully auditable. Works with OpenAI/Anthropic & agents.

agentai-gatewayanthropicclaude-codecodexdecision-modelgatewayhermes-agentjevllmlocal-routeropenaiopencalwopencodeproviderproxyrouterself-hosting

How builders describe it

Local-first LLM routing gateway (single Rust binary) that sits between your coding agents and LLM providers and routes each request to the most suitable model, judged per request by TypeSafe Jev plus a heuristic second opinion, with a feedback flywheel and an auditable JSONL decision log.

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