OpenAI + KLINCH

Run the KLINCH agent and chat on OpenAI models with your own key. Paste the key once, pick a model and start working on any GitHub repository.

Connect OpenAI in a minute

Open Providers, choose the OpenAI 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://api.openai.com/v1
Protocol: OpenAI Chat Completions with streaming
Key storage: AES-256-GCM, server-side only

Why use OpenAI for coding

OpenAI models are a strong default for multi-file edits and following instructions precisely. With your own key you get new models as soon as your account has access to them.

What you can do with it

Use OpenAI 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 OpenAI usage?

You do, directly to OpenAI, 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 OpenAI as part of the prompt. KLINCH itself stores chats and settings, not your repository.