Integrations
Any agent. Any model. One endpoint.
AutoJev connects the coding agents you already use to the providers you already pay for — converting protocols in between so every pairing just works.
Agents
CodexResponses
~/.codex/config.toml
Claude CodeMessages
~/.claude/settings.json
Gemini CLIGemini
~/.gemini/settings.json
OpenCodeChat
~/.config/opencode/opencode.json
Agents
One click writes the agent's own config, with a backup. Quit AutoJev and the original comes back.
CodexRun Codex on DeepSeek, OpenRouter, Ollama or any model. AutoJev speaks Responses to Codex and converts for Chat-only providers.Claude CodePoint Claude Code at AutoJev via ANTHROPIC_BASE_URL and use DeepSeek, GPT, Kimi or local models through the Messages API.Gemini CLIUse a custom model in Gemini CLI. AutoJev bridges Gemini API requests to Chat Completions and on to any provider.OpenCodeAdd AutoJev as an OpenCode provider in one click: every selected model and route appears under the autojev provider.
HermesConnect Hermes to AutoJev over Chat Completions and route it to any provider, route or local model from one place.
OpenClawAutoJev registers itself as an OpenClaw model provider and sets the primary model, so OpenClaw can use any model you route.
Kimi Code CLIUse other models in Kimi Code CLI. AutoJev adds an autojev provider and model entries to your Kimi config.toml.
Grok BuildGive Grok Build a custom model: AutoJev writes model entries to ~/.grok/config.toml and routes them to any provider.
oh-my-pi (OMP)Connect OMP to AutoJev: a provider in models.yml plus the default model role in config.yml, restored together.
Custom agents & BYOK clientsAdd any local agent executable, use templates for Kilo and more, or copy env, JSON and cURL connection parameters.Model providers
Built-in presets plus any OpenAI- or Anthropic-compatible endpoint. Bring your own keys — no markup.
OpenAIAdd your OpenAI key once and use its models in every agent, with Responses or Chat Completions set per model.
DeepSeekRun DeepSeek in Codex and Claude Code. AutoJev converts Responses and Messages to Chat Completions on localhost.
OpenRouterBring OpenRouter models to every agent. The same key can power Jev, the decision model for intelligent routing.
OllamaUse local Ollama models in any coding agent, prefer them in routing, and fail over to cloud models when needed.OpenAI-compatible APIsKimi, Qwen, SiliconFlow, MiniMax, vLLM, LM Studio — any OpenAI-compatible endpoint, available to all your agents.
Anthropic-compatible APIsAdd any Anthropic Messages endpoint. Claude Code gets native passthrough; Codex and others get automatic conversion.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