OpenRouter + KLINCH
Run the KLINCH agent and chat on OpenRouter models with your own key. Paste the key once, pick a model and start working on any GitHub repository.
Connect OpenRouter in a minute
Open Providers, choose the OpenRouter preset and paste your API key. The base URL is filled in for you. KLINCH loads the model list from the provider, or you can type a model id.
- Base URL: https://openrouter.ai/api/v1
- Protocol: OpenAI Chat Completions with streaming
- Key storage: AES-256-GCM, server-side only
Why use OpenRouter for coding
OpenRouter gives one key for models from many labs. It is the easiest way to compare models on the same task or fall back to another model when one is overloaded.
What you can do with it
Use OpenRouter in agent mode to edit code across files and propose a commit, or in chat mode to ask about @file, @folder or the whole @repo. Switch models between chats whenever a task needs more or less power.
FAQ
Who pays for OpenRouter usage?
You do, directly to OpenRouter, at their prices. KLINCH adds no markup and is free during the beta.
Is my code sent anywhere else?
File contents the agent reads are sent to OpenRouter as part of the prompt. KLINCH itself stores chats and settings, not your repository.