Personal Knowledge Base (RAG)
This workflow builds a searchable knowledge base from everything you save, so you can find any saved content later with semantic search.
Requirements
- You need the knowledge-base skill from ClawdHub, or you can build a custom RAG with embeddings instead.
- The web_fetch tool is used, which is built in.
- A Telegram topic or a Slack channel for ingestion.
How to use
Dropping any URL into Telegram or Slack auto-ingests the content, including articles, tweets, YouTube transcripts and PDFs. Semantic search over everything you have saved returns ranked results with sources, for example asking what you saved about agent memory. The knowledge base also feeds other workflows, such as the video idea pipeline, which queries it for relevant saved content when building research cards.
- Install the knowledge-base skill from ClawdHub.
- Create a Telegram topic called knowledge-base, or use a Slack channel instead.
- Prompt OpenClaw with the following.
When I drop a URL in the "knowledge-base" topic:
1. Fetch the content (article, tweet, YouTube transcript, PDF)
2. Ingest it into the knowledge base with metadata (title, URL, date, type)
3. Reply with confirmation: what was ingested and chunk count
When I ask a question in this topic:
1. Search the knowledge base semantically
2. Return top results with sources and relevant excerpts
3. If no good matches, tell me
Also: when other workflows need research (e.g., video ideas, meeting prep), automatically query the knowledge base for relevant saved content.
- Test it by dropping a few URLs and asking questions like what you have about LLM memory.
Source: hesamsheikh/awesome-openclaw-usecases and its contributors. License: MIT.
Copyright (c) 2026
Translation and editorial adaptation by ClawCases.
>Resources
>Related Use Cases
Apple Notes CLI
Manage Apple Notes directly from the terminal with the memo CLI: create, view, edit, delete, search, move notes between folders, and export notes to HTML or Markdown.
Automate the macOS UI with the Peekaboo CLI
Use Peekaboo to inspect the macOS UI, act on the intended target, and verify the result. The examples use v4 syntax; check the current documentation and the installed command's help, and for older versions follow that version's help.
Open WebUI Frontend
Point Open WebUI, a self-hosted chat frontend, at Hermes's OpenAI-compatible API server to get a polished browser UI on top of your full agent, with streaming replies and file upload.