Features
Everything between your agents and your models.
AutoJev runs one local gateway on 127.0.0.1:9527. It connects your agents, routes every request, converts protocols, fails over and keeps a local record of every call.
Route every request to the right model.
AutoJev
autojev/qualityProviders
4
Models
12
Routes
5
Agents
3
Requests today
1,284
Tokens today
18.6M
Smart model routingExpose routes like autojev/fast to every agent. Load-balance models or let Jev pick by cost, quality, speed or balance.One-click agent setupConnect Codex, Claude Code, Gemini CLI, OpenCode and more. AutoJev edits each native config, backs it up and restores it.Protocol conversionConvert between Chat Completions, Responses and Anthropic Messages in all six directions, with streaming and tool calls.Model speed testsMeasure first-content latency and output tokens per second on your own network, on a schedule, and route by the results.Failover & load balancingWeighted pools, priority groups and sticky sessions, with automatic failover on 429s and 5xx errors and Retry-After cooldowns.Usage & request logsTokens, latency and estimated cost for every request, broken down by agent, model and provider. Metadata only, stored locally.Debug consoleTest models and routes in conversation or cURL mode and inspect the selected model, timing, tokens, cost and raw JSON.Provider managementAdd OpenAI, DeepSeek, OpenRouter, Ollama or any compatible endpoint once, or import from CC Switch and Termany.
Give every agent the right model.
Install AutoJev, add the providers you already pay for, and connect your agents in one click. Everything stays on your machine.
Free & open source · macOS · Windows · Linux