AI tools, scored for your job
Get paid to train AI
🤝 You're in the Free & Open Source library — community-built tools you can use without paying. A different concept from our scored AI directory.
Home › Free & Open Source › Productivity › second-brain-os
✦ Free & open sourceProductivity

second-brain-os

An AI second brain that maintains itself inside your own Obsidian vault.

AI second brain that maintains itself

Self-organizing knowledge base in Claude Code and Obsidian.

Free forever · open source · MIT
✓ Light setup✓ Browser-based✓ Real-time collaboration
7
ZEKAI
Self-maintaining Obsidian wiki
Free & open source · Productivity
Ease of setup4
Usefulness8
Maintenance9.5
Community6.5
★ 683
GITHUB
Sep 2026
UPDATED
MIT
LICENSE
🛠 Don't want to self-host? We can set it up →
⚡ Quick answer

Second-brain-os is an open-source guide and toolkit for running a self-maintaining personal knowledge base using Claude Code and Obsidian. It suits professionals and researchers who save vast amounts of information but struggle to manually link and file it.

Runs on
Cross-platform
Hosting
Desktop
Languages
HTML
License
MIT

What it is

It provides a starter vault template, agent skills, slash commands, and scripts to turn raw ingested articles, PDFs, and chat transcripts into a densely linked markdown wiki. The AI handles extraction, linking, and linting while keeping your notes in plain markdown files you own.

Who it's for

It suits heavy readers, engineers, and researchers willing to learn Claude Code and manage local markdown files. It does not suit users looking for a point-and-click graphical web app or those who expect an out-of-the-box hosted cloud experience.

Key features

Automated Vault Ingestion

Turns raw clips, articles, and transcripts into linked wiki pages instead of leaving them in unread queues.

Two-Layer Architecture

Separates your permanent knowledge wiki from active project pipelines with individual inputs and outputs.

Contradiction Preservation

Records new conflicting sources alongside old ones with dates and attributions rather than overwriting past beliefs.

Zero Vector Database

Relies entirely on structured markdown pages and typed links for retrieval without external database infrastructure.

How to start

Up and running in 3 steps

1
Clone the repository and copy the starter vault template into your local machine directory.
2
Open the folder as an Obsidian vault and configure your Claude Code environment.
3
Clip an article into your raw folder and run the ingest command to let the agent build your wiki.
Real talk

Our honest verdict

What's great

  • Keeps all data in plain, portable markdown files you own entirely
  • Includes 18 agent skills and 72 slash commands for automated maintenance
  • Maintains historical positions when sources contradict each other
  • Includes five compact tracks on graphs, harnesses, loops, and evals

Where it falls short

  • Requires manual setup of local git repositories, Python scripts, and Claude Code
  • The graph and agent workflows take time to ingest enough sources to become useful
  • Relies heavily on your willingness to adopt terminal-based agent workflows
Cost

Pricing & license

Free under its license. The only cost is running it yourself on your local machine using your own agent API credits.

Paid work

Open remote AI-training roles

880 open remote AI-training roles, updated November 15, 2026; most pay $20–$175 an hour. Zekai lists them free; the application goes to the employer’s platform.

See all open roles →
Compare

Alternatives

🎁 Free & open-source alternatives

These reviewed AI tools do the same job instantly — from our scored directory.

Get more

Use it, or have us set it up

📄 Free PDF: second-brain-os for Productivity
A plain-language guide to getting your first result. Sent to your inbox.
🔔 64 people want a full video tutorial — add your vote
🛠 Don't want to set it up yourself?
We'll install, host & configure second-brain-os for you — and train your team.
Get it done for you ↗
Questions

FAQ

Do I need a vector database to run this?

No, the system relies on structured markdown pages and direct links to handle retrieval without extra database overhead.

How does it handle conflicting information?

When a new source disagrees with an existing page, both positions are kept with dates and sources to preserve your belief history.

What software do I need installed beforehand?

You need Obsidian, Claude Code, and Python for running the built-in vault stats and link-checking scripts.

Radar

Latest AI news

✉️ The weekly free toolkit
The best new free & open-source tools for Productivity — one short email a week, in your language.
Free · 1 email/week · unsubscribe anytime
Get paid to train AI →

See Zekai first in Google