Quick Start

Get up and running with ATLAS

Overview

ATLAS can be experienced in three ways:

1. Public Dashboard — Explore the live demo

2. Beta Access — Full features with your own data

3. Self-Hosted — Complete control on your infrastructure

---

1. Explore the Public Dashboard

The fastest way to understand ATLAS:

Visit: dashboard.atlas-ai.org

What you can do:

• Browse the knowledge graph visualization

• Search across indexed concepts

• See how extraction works

• Understand the data structure

Limitations:

• Read-only access

• Public knowledge only

• No personal data upload

---

2. Join the Beta

For full ATLAS functionality with your own knowledge:

Step 1: Request Access

Visit atlas-ai.org and join the waitlist.

We're onboarding users in batches to ensure quality support.

Step 2: Initial Setup

Once approved, you'll receive:

• Access credentials

• Setup instructions

• Onboarding support

Step 3: Connect Your Data

Start with your highest-value sources:

Source	Setup Time	Value
Twitter Bookmarks	5 min	High (years of curation)
Apple Notes	10 min	Medium-High
GitHub Stars	5 min	Medium

Step 4: Run Extraction

ATLAS processes your content:

Content → LLM Analysis → Concepts + Insights + Actions

Initial extraction takes 10-30 minutes depending on volume.

Step 5: Explore Your Graph

• Search across everything you've saved

• Discover connections between ideas

• See your knowledge visualized

---

3. Self-Hosted (Advanced)

For complete control:

Requirements

Component	Minimum
Python	3.11+
Node.js	18+ (for dashboard)
Storage	1GB+ (scales with data)
RAM	4GB+

Installation

# Clone repository (when available)
git clone https://github.com/atlas-ai/atlas.git
cd atlas

# Install Python package
pip install -e .

# Install dashboard dependencies
cd dashboard
pnpm install

Configuration

# Create config
cp config.example.yaml config.yaml

# Edit with your settings
# - API keys for LLM (Claude/OpenAI)
# - Data source credentials
# - Storage paths

Running

# Start API server
uvicorn atlas.api.main:app --port 8888

# Start dashboard (separate terminal)
cd dashboard && pnpm dev --port 3333

# Or use CLI
atlas dashboard  # Terminal dashboard
atlas search "query"  # Direct search

---

First Steps After Setup

1. Import Your First Source

Start with Twitter bookmarks (highest signal-to-noise):

atlas module import x_alpha --file bookmarks.json

2. Run Extraction

Process imported content:

atlas index

3. Explore

Search your knowledge:

atlas search "topic you care about"

4. Review Concepts

See what was extracted:

atlas concepts --limit 20

5. Check Actions

View extracted action items:

atlas actions --status pending

---

Next Steps

Once you're comfortable with basics:

Goal	Next Step
Add more sources	Connect Apple Notes, GitHub, etc.
Explore graph	Use web dashboard visualization
Monetize knowledge	Configure x402 protocol
Automate	Set up agent workflows

---

Getting Help

Documentation

You're reading it! Browse the sidebar for specific topics.

Support

• Beta users: Direct support channel

• General: [email protected]

Community

• Twitter: @atlas_ai

• Discord: Coming soon

---

Common First Questions

Q: How long does initial processing take? A: 10-30 minutes for typical bookmark collections (1-5K items)

Q: Can I export my data? A: Yes, always. SQLite database is portable.

Q: Is my data private? A: Yes. Local-first. Cloud features are opt-in.

Q: What LLM does extraction use? A: Claude by default. OpenAI supported.