docs: add MindsHub connection guide - #5608
Open
torrmal wants to merge 1 commit into
Open
Conversation
MindsHub (https://mindshub.ai) is an OpenAI-compatible inference gateway covering Claude, GPT, Kimi, DeepSeek and other models behind one API key. Aider already talks to it via the existing OPENAI_API_BASE / openai/ prefix mechanism used for any OpenAI-compatible endpoint, so this adds a docs page under docs/llms/ (matching openrouter.md/deepseek.md style) with the exact env vars, model aliases, and a ready-to-use config snippet. No code changes.
|
|
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Summary
Adds a docs page for connecting aider to MindsHub, an OpenAI-compatible inference gateway that fronts Claude, GPT, Kimi, DeepSeek and other models behind one API key and bill.
This is a documentation-only change. Aider's existing generic OpenAI-compatible-API support (
OPENAI_API_BASE+OPENAI_API_KEY+ theopenai/<model>prefix, as already documented indocs/llms/openai-compat.md) already covers MindsHub with zero code changes — I verified this against aider's ownopenai-compat.mdrecipe andaider/main.py's handling of--openai-api-base/OPENAI_API_BASE, and against MindsHub's own API docs (https://docs.mindshub.ai/inference/). No new provider abstraction, litellm provider, or model-metadata entry is needed or added.New file:
aider/website/docs/llms/mindshub.md, following the same structure/front-matter as the neighboringopenrouter.mdanddeepseek.mdpages (parent: Connecting to LLMs,nav_order: 500, so it's picked up automatically in the sidebar). It covers:OPENAI_API_KEY/OPENAI_API_BASEfor MindsHubaider --model openai/<alias>with MindsHub's model aliases (sonnet,opus,kimi,deepseek,gpt-codex, etc.).aider.model.settings.ymlsnippetDisclosure
I'm Jorge Torres, affiliated with MindsHub/mindsdb.com (I work there). This PR documents/promotes my own company's product, so flagging that affiliation explicitly here rather than leaving it unstated.
Test plan
--openai-api-basehandling inaider/main.pyand the existingopenai-compat.mdrecipe)chat-completions.mdx,models.mdx) rather than paraphrasingdocs/llms/*.mdfront-matter and structure conventions so it appears correctly in the "Connecting to LLMs" nav🤖 Generated with Claude Code