local-ai

synto: Local AI Wiki

Name: synto: Local AI Wiki
Author: kytmanov

Automate your wiki with synto. For founders seeking local AI knowledge management.

From the repo · “More than just Karpathy’s LLM Wiki, 100% local with Ollama. Drop Markdown notes → AI extracts concepts → your Obsidian wiki auto-links and grows. Zero sharing. Your notes stay yours.”

263 stars+1★ this week27 forksPythonGuide quality 8/10 · reviewed Jul 18Updated 10/8/2026100% free · open source

What it does

Synto automates your local wiki by extracting concepts from Markdown notes and auto-linking them in your Obsidian wiki, all while keeping your notes private and local.

When to use it

•When you have a large number of Markdown notes and want to create a wiki without manually linking concepts
•When you want to keep your knowledge management system completely local and private
•When you're using Obsidian for note-taking and want to leverage AI to enhance your wiki

Ready-to-paste prompt

python synto/extract.py path/to/your/note.md --output path/to/your/wiki

Heads up: Make sure you have Python installed and the 'ollama' library is compatible with your system, as synto relies on it for local AI knowledge management

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/synto && curl -fsSL https://workflowstacks.com/api/skills/synto/claude-skill -o ~/.claude/skills/synto/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 synto: Local AI Wiki works

Codeflow

Free to inspect

Synto: Local AI Wiki is a large Python project (~33k lines across 62 code files, plus 119 test files). It is a full software project: use it through its install path rather than reading it end to end. Last commit a month ago, MIT license, has a test suite.

Size

Large codebase

~33k lines · 62 code files · ~5 h to skim

Setup

Developer setup

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

Runs on

Python

No API keys detected

Python 93%Shell 7%

Where to start reading

1
README.md
Start here — what it does and how to install it
2
CLAUDE.md
The instructions the AI actually follows
3
pyproject.toml
Dependencies and the commands it exposes
4
src/synto/__init__.py
Inside src/ — the main logic begins here

What's in each folder

src/Core code — the actual logic57 files

docs/Documentation2 files

scripts/Helper scripts12 files

tests/Tests — proof it works136 files

.github/CI / automation (GitHub Actions)4 files

READMEHas testsDocumentedCI checksMIT 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/synto && curl -fsSL https://workflowstacks.com/api/skills/synto/claude-skill -o ~/.claude/skills/synto/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

kytmanov

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.

Outcome guide

Automate your meeting summaries

A private form takes any transcript (from Zoom, Meet, Otter, Fireflies) and emails you back a structured summary: a TL;DR, the decisions made, and action items with owners.

MCP config