The fork wires up OpenAI alongside the Claude and Gemini engines already powering Mike, giving users a third model family to pick from.
fabiotaroc/mike
fabiotaroc's fork of Mike adds OpenAI as a third LLM backend, giving operators a choice beyond Claude and Gemini.
This is a lightly diverged fork of Mike from fabiotaroc. The headline change is straightforward: where upstream Mike speaks to Claude and Gemini, this version also speaks to OpenAI - including streaming, tool-calling, and the option to surface reasoning summaries from newer OpenAI models.
That's effectively the whole story so far. There's no rebrand, no niche-specific reshaping, no visible deployment angle. It reads like a focused contribution by someone who wanted a third backend on the menu and built it.
If you're evaluating Mike and your shop is standardized on OpenAI - or you just want backend optionality - this fork is worth a click through to GitHub.
What's in it
- OpenAI backend Adds OpenAI as a third LLM provider alongside Mike's existing Claude and Gemini support, so GPT-family models can drive the assistant.
- Streaming responses OpenAI replies stream in token-by-token, matching the responsiveness users already get from the other two backends.
- Tool-calling support The OpenAI integration wires up tool use, so Mike's agentic features keep working when GPT is the model behind them.
- Reasoning summaries Optionally surfaces reasoning summaries from OpenAI's newer reasoning models, giving users a peek at the model's thinking.
Direction
integrationinfrastructure
Activity
Threads of work (detailed view)
fabiotaroc adds OpenAI as a third brain
The fork wires up OpenAI alongside the Claude and Gemini engines already powering Mike, giving users a third model family to pick from.