## Summary
umerkay/mike
A focused Mike fork that gives the assistant a practical web-research arm for live online investigation.
umerkay is steering Mike toward research that reaches beyond uploaded material. The fork proposes a single, authenticated research surface for reading supplied web pages, asking questions against them, exploring sites, and understanding their structure.
For someone trying it, the appeal is straightforward: bring live web material into the assistant's research process rather than treating the web as outside the workspace. MikeWatch has no further identity signal for umerkay, but the direction is clear and narrowly focused; GitHub is the place to explore the detail.
What's in it
- Web page research Pull content from supplied public URLs into a research workflow.
- Question answering Ask questions about web material and receive sourced answers.
- Site crawling Explore a website more broadly instead of limiting research to one page.
- Site mapping Map a site's structure to help orient further investigation.
Direction
searchintegration
Activity
Four new endpoints let the assistant pull live content off the open web - scrape a page, ask a question and get a sourced answer, or map and crawl a whole site.
Threads of work (detailed view)
umerkay gives Mike a web-research arm
Four new endpoints let the assistant pull live content off the open web - scrape a page, ask a question and get a sourced answer, or map and crawl a whole site.
umerkay adds Olostep web research endpoints behind optional dependency
Four backend POST endpoints at `/api/research` - scrape a URL to Markdown, run an AI Q&A against a page, start a multi-page crawl, or discover site URLs - all gated behind an optional `olostep` SDK install and `OLOSTEP_API_KEY` env var. Absent the key, every call returns an error string; nothing breaks on boot.
Pull requests (detailed view)
⛔ Closed without merge (1)
by
umerkay · opened 6mo ago · closed 6mo ago