manueljpconde/mikept

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.

📝 manueljpconde teaches Mike to run on your own hardware 2 commits 2mo ago infrastructuresecurity draft

A fourth AI option lets the fork point at a self-hosted or local model instead of the big cloud providers.

📝 Gitignore local agent/AI tool configs 2 commits 2mo ago minor change

Threads of work (detailed view)

2 threads have been distilled into posts.

manueljpconde teaches Mike to run on your own hardware

A fourth AI option lets the fork point at a self-hosted or local model instead of the big cloud providers.

infrastructuresecurity

2 commits · latest 2mo ago

Add `local` provider for any OpenAI-compatible self-hosted LLM

manueljpconde adds a fourth LLM provider to the abstraction layer, letting self-hosters point the backend at Ollama, LM Studio, or any `/v1/chat/completions`-compatible endpoint. The integration is entirely backend-configured; the browser never learns the URL, model ID, or API key.

infrastructuresecurity

2 commits · latest 2mo ago