Agent-built research knowledge bases
OpenClaw learned to use a YouTube summariser, a paper extraction tool, and QMD, then built searchable Markdown knowledge bases for videos and research papers.
The author now has two dense, searchable knowledge bases, one from YouTube videos and one from research papers, which they say speeds up understanding.
Overview
How it was set up
OpenClaw agent on a dedicated Mac mini. Author installed youtube-summariser via pip and Tobi's QMD via bun, plus their own paper-fluff-cutter tool. The agent learned each tool.
Worth knowing
No numbers on size or time saved; the benefit is the author's own impression.
A prompt to start from
Learn how to use [summariser tool] and [QMD], then use both to build your own knowledge base from [source type]. Save outputs as Markdown so they can be indexed and searched.
Written by Agentic Feats from the source. Not the author's exact prompt.
Sources 1
History
- Source published
- 2026-02-05
- Added to Agentic Feats
- 2026-10-13
- Pick
- No
- Markdown copy
- /c/agent-built-research-knowledge-bases-openclaw.md
More in research
36 featsResultIt created the text file as asked, but after clicking a result it took a screenshot too early and hallucinated the answer.
ResultOperator handled tour search and lesson plan but was slow; adding three grocery items took 15 minutes and an Uber price check took five.
ResultThe draft was usable but weaker than accepted NSF summaries; thinking mode helped, though it began hallucinating and misreading the sources.