⚖MikeWatch Forks of the Mike legal-AI codebase, distilled for legal-tech readers
Home · jpbreda/mike

jpbreda/mike

A Mike fork exploring a path to run AI features with self-hosted models.

This appears paused or very early: MikeWatch has tracked no work ahead of Mike, and the last push was in May 2026.

View on GitHub →

jpbreda's fork is pointed at a more self-directed deployment story for Mike: alongside commercial AI services, it explores connecting the product to OpenAI-compatible models hosted locally, including vLLM.

That could suit organisations that want more control over where their AI runs while keeping commercial-provider options available. The work is associated with @jpbreda and remains an early, focused direction rather than a broad product rework.

What's in it

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.

Threads of work (detailed view)

2 threads have been distilled into posts.

jpbreda adds vLLM as a third LLM provider alongside Claude and Gemini

This fork wires a self-hosted vLLM endpoint into Mike's provider system, letting operators swap the model layer to a local inference server instead of routing all requests through Anthropic or Google. The PR closed without merging upstream on May 10.

infrastructuresecurity
3 commits · latest 6mo 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)