ai-agent

ai-shifu: AI Teaching Helper

Name: ai-shifu: AI Teaching Helper
Author: ai-shifu

Get AI to teach and answer questions. For founders in education and AI.

324 stars+6★ this week125 forksPythonGuide quality 8/10 · reviewed Jul 9Updated 10/9/2026100% free · open source

What it does

Ai-shifu is an AI-powered tool that allows users to interact with it through text-based conversations, enabling it to teach and answer questions on various topics.

When to use it

•You need to create interactive educational content for students
•You want to develop an AI-powered chatbot for customer support
•You need to generate automated responses for frequently asked questions

Ready-to-paste prompt

python chat.py --model-path=models/my_model --question='What is the capital of France?'

Heads up: You need to have Python 3.8 or later installed, as well as the necessary dependencies specified in the `requirements.txt` file, to run ai-shifu successfully

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/ai-shifu && curl -fsSL https://workflowstacks.com/api/skills/ai-shifu/claude-skill -o ~/.claude/skills/ai-shifu/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 ai-shifu: AI Teaching Helper works

Codeflow

Free to inspect

Ai-shifu: AI Teaching Helper is a very large Python project (~431k lines across 1498 code files, plus 716 test files). It is a full software project: use it through its install path rather than reading it end to end. Last commit this month, Apache-2.0 license, has a test suite.

Size

Very large codebase

~431k lines · 1498 code files · days to read — use, don't read

Setup

Developer setup

A real software project. Use it via its install path; don't expect to read it all.

Runs on

Docker

No API keys detected

Python 68%TypeScript 31%

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
src/api/app.py
Inside src/ — the main logic begins here

What's in each folder

src/Core code — the actual logic2815 files

docs/Documentation277 files

scripts/Helper scripts85 files

docker/Deployment / infrastructure15 files

.github/CI / automation (GitHub Actions)26 files

.cursor/Editor / agent settings8 files

assets/Images & static assets3 files

.codex/Tool / agent settings1 files

READMEHas testsDocumentedCI checksDocker readyApache-2.0 licenseUpdated this month

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/ai-shifu && curl -fsSL https://workflowstacks.com/api/skills/ai-shifu/claude-skill -o ~/.claude/skills/ai-shifu/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.

Quick Actions

Details

Creator

ai-shifu

Language

Python

Do this with a working workflow

Pages we wrote and tested that put a skill like this to work — importable n8n templates, outcome guides and Claude Desktop configs.

Free n8n template

AI Support Agent (Chat)

A chat agent that answers customer questions from YOUR business info — with conversation memory. It never invents policies; anything it doesn't know, it hands to a human.