One sprawling commit opens Mike up to more AI providers, third-party tool servers, and easier self-hosting.
wearefaces/mike
wearefaces is widening Mike's AI backbone, plugging in more model providers and tooling so the assistant isn't tied to a single vendor.
This is an early-stage fork of Mike maintained by wearefaces. So far the work is concentrated in one substantial push that broadens the range of AI providers and external tools the assistant can reach for, rather than reshaping the product surface a legal user would see.
If you tried it today, it would still feel like Mike. The interesting bet is underneath: the fork is being shaped to talk to a wider set of model providers and integrations, which suggests wearefaces wants flexibility in how (and through whom) the underlying intelligence is sourced.
There's no rebrand, no declared niche, and no deployment story yet beyond that. Click through to GitHub if you want to see how the plumbing is being laid out.
What's in it
- Broader model provider support Room for multiple AI providers behind the assistant, not just one.
- Expanded tooling surface More external tools and integrations the assistant can call on during a task.
- Provider routing A way to direct requests to the right backend depending on which model is being used.
Direction
integrationinfrastructure
Activity
Threads of work (detailed view)
wearefaces widens Mike's AI plumbing
One sprawling commit opens Mike up to more AI providers, third-party tool servers, and easier self-hosting.