automation

llm-wiki-agent: Auto Knowledge Base

Name: llm-wiki-agent: Auto Knowledge Base
Author: SamurAIGPT

Get a self-building knowledge base with llm-wiki-agent.

3,270 stars382 forksPythonGuide quality 8/10Updated 7/27/2026100% free · open source

What it does

Llm-wiki-agent is a personal knowledge base that automates reading sources, extracting knowledge, and maintaining a persistent interlinked wiki using Claude, Codex, or Gemini

When to use it

•When you need to organize and link large amounts of information from various sources
•To automate knowledge extraction and wiki maintenance for your startup's documentation
•When you want to leverage AI-powered tools like Claude, Codex, or Gemini for knowledge management

Ready-to-paste prompt

python llm_wiki_agent.py --gemini --source ../my_document.pdf --output ../my_knowledge_base

Heads up: Make sure you have Python and the required AI tool (Claude, Codex, or Gemini) installed and configured on your system, as llm-wiki-agent relies on these dependencies to function

Saves to your device

Use with Claude

New

Skip the builder — one click puts this in Claude, Cursor, Antigravity and more.

🛠️ Technical setup

Expect 20–40 minutes in a terminal — or let your AI agent drive it.

Try it instantly — no install

Claude Code

mkdir -p ~/.claude/skills/llm-wiki-agent && curl -fsSL https://workflowstacks.com/api/skills/llm-wiki-agent/claude-skill -o ~/.claude/skills/llm-wiki-agent/SKILL.md

Open in another AI app

Opens the app with this repo with the prompt ready to go — no copy-paste needed.

Connect the whole catalog (MCP)

claude mcp add --transport http workflowstacks https://workflowstacks.com/api/mcp

Adds a WorkflowStacks connector to Claude Code: search and load any skill here by chatting.

How llm-wiki-agent: Auto Knowledge Base works

Codeflow

Free to inspect

Llm-wiki-agent: Auto Knowledge Base is a medium Python project (~3.2k lines across 11 code files). Expect some technical setup — comfortable with a terminal, or ask a developer. Last commit this month, MIT license, no tests found.

Size

Medium codebase

~3.2k lines · 11 code files · 26 min skim

Setup

Some technical setup

Comfortable with a terminal? 20–40 min. Otherwise ask a dev.

Runs on

Python

No API keys detected

Python 100%

Where to start reading

1
README.md
Start here — what it does and how to install it
2
AGENTS.md
The instructions the AI actually follows
3
pyproject.toml
Dependencies and the commands it exposes
4
examples/cjk-showcase/README.md
A worked example — copy this to get going

What's in each folder

wiki/Documentation3 files

examples/Examples you can copy2 files

docs/Documentation1 files

tools/Helper scripts11 files

graph/Folder1 files

raw/Folder1 files

.claude/Editor / agent settings4 files

.github/CI / automation (GitHub Actions)1 files

READMENo tests foundDocumentedCI checksExamples includedMIT licenseUpdated this month