thegrif/mike

A fork of Mike that broadens the AI model lineup, giving users a third provider option alongside the existing two.

Early days - one distinct thread of work landed in early May 2026, with no follow-up activity yet.

This is thegrif/mike, a fork of Mike maintained by Tom Griffin (handle: thegrif). At a glance, the fork stays close to upstream Mike in shape and purpose - what's changed is what's under the hood when Mike reaches for a language model.

The headline move so far: where Mike historically routed work to two AI providers, this fork adds a third into the mix. For a user trying it, the experience would feel familiar, but the answers, costs, and characteristics behind the scenes now have another source feeding them.

It's early days for the divergence - a single thread of work, recently landed. Whether thegrif takes this further into provider-choice territory, cost optimisation, or something else isn't yet visible. Readers curious about the implementation can click through to GitHub.

What's in it

Third AI provider option Expands Mike's model lineup beyond its original two providers by wiring in a third, with both a flagship and a lighter-weight tier from that provider available to the system.
Tiered model routing preserved Keeps Mike's existing pattern of using different model tiers for different jobs - heavier work goes to a top-tier model, lighter tasks to a cheaper one.
Pattern-faithful integration The new provider slots into Mike's existing abstraction rather than replacing it, so the rest of the product behaves the way upstream users would expect.

Direction

infrastructureintegration

Activity

Themed changes and pull requests touching this fork, newest first. Themed changes that haven't been turned into a public post yet still appear — they're real work even without a published writeup.

⛔ #16 Add OpenAI as third LLM provider (GPT-5.5, GPT-5.4 Nano) +331 -166 16d ago by thegrif ↗ analysis ↗ GitHub

Adds full OpenAI support across backend and frontend, following the existing Claude/Gemini provider pattern: streaming chat with tool use, text completion, model selection UI, API key management, and DB schema.

📝 thegrif adds OpenAI as a third engine option 1 commit 25d ago integrationinfrastructure draft

Mike already let users pick between Anthropic's Claude and Google's Gemini. Tom Griffin's fork makes OpenAI a peer.

Threads of work (detailed view)

1 thread have been distilled into posts.

thegrif adds OpenAI as a third engine option

Mike already let users pick between Anthropic's Claude and Google's Gemini. Tom Griffin's fork makes OpenAI a peer.

integrationinfrastructure

1 commit · latest 25d ago

Pull requests (detailed view)

1 PR touch this fork — inbound (filed against it) or outbound (filed from it). State icons match the editorial dashboard.

⛔ Closed without merge (1)

⛔ closed · #16 Add OpenAI as third LLM provider (GPT-5.5, GPT-5.4 Nano)

by thegrif · opened 25d ago · closed 16d ago

willchen96/mike ← thegrif/mike · +331 -166 · ↗ analysis · ↗ GitHub