📝 sean-a-ward opens Mike up to OpenRouter and friends 3 commits 7d ago infrastructureintegration draft
This fork lets you point Mike's AI brain at almost any model provider, not just OpenAI.
sean-a-ward/mike
sean-a-ward's fork loosens Mike's leash on model providers, letting you swap in OpenRouter, LiteLLM, LM Studio, and friends.
This is a fork of Mike maintained by sean-a-ward, aimed at people who don't want to be locked into a single AI provider. The headline change: Mike's AI brain can now be pointed at almost any OpenAI-compatible endpoint, which opens the door to OpenRouter's model marketplace, self-hosted setups via LiteLLM, and fully local models running through LM Studio.
Alongside that, sean-a-ward has wired up automation to keep the fork tracking upstream Mike on a daily cadence, so the provider flexibility doesn't come at the cost of falling behind on the parent project's improvements.
The direction so far is narrow but coherent: keep Mike's product surface intact, but give operators a real choice about where the inference runs and who they pay for it. If that flexibility matters to you, the GitHub repo is worth a look.
What's in it
- Bring-your-own model provider Point Mike at OpenRouter, LiteLLM, LM Studio, or anything else that speaks the OpenAI API - not just OpenAI itself.
- Local and self-hosted inference With LM Studio support in the mix, you can run Mike against models on your own hardware instead of sending prompts to a third party.
- Daily upstream sync Automation pulls in changes from the original Mike project every day, so the fork doesn't drift away from the parent.
Direction
integrationinfrastructure
Activity
📝 Fork-sync GitHub Actions workflow (no public page) 1 commit 7d ago not yet rewritten
Threads of work (detailed view)
sean-a-ward opens Mike up to OpenRouter and friends
This fork lets you point Mike's AI brain at almost any model provider, not just OpenAI.