DEDUPED Hot AI repos, turned into use cases Get 5 a day

How to build a source-backed knowledge base from your documents with Knowledge Base Kit

Set up a separate Markdown workspace and file documents with the Codex backend after review.

  • Top pick
  • Research
  • Intermediate
  • 30 minutes
  • From the README
  • Codex

Who it is forA researcher or analyst with a folder of PDFs, DOCX files, or notes who wants a searchable, source-backed knowledge base that an agent can read.

The problemRaw documents are hard to reuse. Summaries get lost, and agents cannot tell what came from which source.

The outcomeA workspace with inbox/, catalog.md, categories, and per-document full.md, summary.md, and the original attachment, checked before filing.

What you need first

  • Python 3.10+
  • Node.js 20+
  • Pandoc 3+
  • An authenticated Claude Code or Codex CLI for model-assisted processing
  • A downloaded or cloned copy of the knowledge-base-kit repository

Steps

  1. git clone https://github.com/Sixian-Li/knowledge-base-kit.git && cd Knowledge Base Kit (inferred, check the README)
  2. python3 -m venv .venv
  3. source .venv/bin/activate
  4. python -m pip install -r requirements.txt
  5. python scripts/init_workspace.py ../my-kb --backend codex --with-example
  6. cd ../my-kb then python kb.py check --backend codex

Prompt for your agent

In the knowledge-base-kit repo, initialize a Codex workspace at <workspace-path>. Then open that workspace in Codex and use the local process_docs skill with the Codex backend on <document-path>, and show the proposed category and changed files before filing. Verify that the workspace passes `python kb.py check --backend codex`.

Caveat. Validators cannot prove factual accuracy or perfect coverage, so you still need to review the full text and summary the agent writes.

Share: X LinkedIn Hacker News Email Copy link

Disclaimer

Deduped lists open-source repositories that belong to other people. We do not own, maintain, audit, or vouch for any of them, and a repo appearing here is not an endorsement or a safety check. The use cases, steps, and prompts are written by AI and may be incomplete, outdated, or just wrong. Where a use case is marked "Seen in the wild", we link to public posts where someone described something similar, but we have not verified those posts and the use case itself is still our AI's own write-up. Use all of this at your own risk. Only run code, commands, or agents on systems and accounts you are authorized to use, and read the code and every command before you run it, especially anything that touches credentials, files, or the network. Nothing here is professional, security, legal, or financial advice. All trademarks and project names belong to their respective owners, and their use here does not imply affiliation. Content is provided as is, without warranties of any kind. Found a mistake, a safety problem, or something you want removed? Email [email protected] and we will look at it promptly. Full disclaimer page