Key Concepts
Understanding these core concepts will help you grasp how Unbrowse works and how you can benefit from it.
Abilities
Definition: Reusable patterns that define how to interact with specific websites or perform specific actions.
Think of abilities like recipes:
A recipe tells you how to make chocolate chip cookies
An ability tells an AI agent how to "post to LinkedIn" or "book a flight"
Key characteristics:
Captured from real browsing: Created when users browse websites naturally
Reusable: Once created, any agent can use them forever
Network-level: Execute via HTTP requests, not visual UI
Parameterized: Can accept inputs (dates, search terms, etc.)
Examples:
"Search for flights on United Airlines"
"Post update to LinkedIn with image and tags"
"Check account balance on Chase Bank"
"Create Jira ticket with priority and assignee"
"Pull competitor traffic data from SpyFu"
How they're created:
User browses website normally with extension installed
Extension captures network traffic (HAR files)
AI analyzes patterns and generates ability wrapper
Ability stored in searchable index
Available for all agents to use
Indexers
Definition: Users who contribute browsing patterns to the network and earn rewards.
Who can be an indexer:
Anyone with a browser
No technical skills required
Just browse normally
What indexers do:
Install Unbrowse browser extension
Browse websites as they normally would
Extension captures network patterns automatically
Earn 19% of execution fees when abilities are used
First-mover advantage:
The first person to index "Book flight on United" captures that workflow
Popular abilities can generate significant passive income
Early indexers benefit most from high-value workflows
Examples of valuable indexing:
SaaS tools (Notion, Slack, Jira, Salesforce)
Financial platforms (banking, trading, crypto exchanges)
Data sources (analytics, research, market data)
Social media (LinkedIn, Twitter, Instagram)
E-commerce (Amazon, Shopify, marketplaces)
Large Action Model (LAM)
Definition: The AI brain that analyzes captured browsing patterns and generates executable abilities.
What LAM does:
Pattern Analysis
Studies millions of captured browsing sessions
Identifies common interaction patterns
Understands authentication flows
Recognizes data structures
Ability Generation
Converts HAR files into executable API wrappers
Generates parameter schemas
Creates error handling logic
Optimizes for reliability
Workflow Composition
Chains multiple abilities together
Handles data flow between steps
Optimizes execution order
Manages dependencies
Routing & Matching
Matches natural language queries to abilities
Selects best ability variant for each request
Learns from success/failure patterns
Improves recommendations over time
Network-Level Execution
Definition: Direct HTTP communication with websites, bypassing visual UI entirely.
How it works:
When you click a button on a website:
[You click "Buy Now"]
↓
[Browser sends HTTP POST request to server]
↓
[Server processes order]
↓
[Server sends response back]
↓
[Browser displays confirmation page]Traditional automation forces agents to:
See the button visually
Figure out where to click
Simulate the click
Wait for page to load
Parse visual result
Unbrowse lets agents:
Send the HTTP request directly
Receive the response
Done
No screenshots. No clicking. No waiting.
Why this is revolutionary:
Speed
30-45 seconds
0.3 seconds
Reliability
70-85%
95%+
Cost
$0.01-$0.10
$0.001-$0.006
Maintenance
Constant (breaks often)
Minimal (stable patterns)
Technical benefits:
No browser overhead
No rendering engine needed
No visual parsing
Direct server communication
Structured data responses
Parallelizable (run 1000s simultaneously)
Ability Index
Definition: The searchable database of all available abilities.
Think of it as "Google for agent actions":
Google indexes information (web pages)
Ability Index indexes actions (how to do things)
How agents search:
Natural language queries:
"How to book flight on United"
"Post to LinkedIn with image"
"Check balance on Chase"
X402 Payment Rails
Definition: Solana-based smart contract infrastructure for atomic multi-party payment splits.
The problem it solves:
Traditional payments require:
Manual invoicing
Payment processors (2.9% fees)
Settlement delays (2-7 days)
International transfer fees
Trust between parties
X402 eliminates all of this:
When an agent executes an ability:
executeAbility(abilityId, fee) {
// Atomic split in single transaction
websiteOwner.transfer(fee * 0.50) // 50%
treasury.transfer(fee * 0.46) // 46%
indexer.transfer(fee * 0.03) // 3%
infrastructure.transfer(fee * 0.01) // 1%
// Treasury auto-buys FDRY
fdryBought = buyFDRY(fee * 0.46)
burn(fdryBought * 0.50) // Permanent burn
treasury.hold(fdryBought * 0.50) // Development
}All of this happens in milliseconds.
Key features:
Instant settlement (no delays)
On-chain transparency (auditable)
Immutable fee structure (can't be changed)
Program Derived Addresses (correct routing)
Low transaction costs (Solana)
Two transaction types:
Search Fee: $0.0001 (0.01¢)
97% → Treasury buyback
3% → Infrastructure
Execution Fee: $0.001 (0.1¢)
50% → Website owner
46% → Treasury buyback
3% → Indexer
1% → Infrastructure
FDRY Token
Definition: The native currency of the Unbrowse ecosystem.
Utility:
Required for platform access
Indexer rewards (earn in FDRY)
Deflationary (permanent burns)
Governance (future)
Supply mechanics:
Total: 1,000,000,000 tokens (1 billion)
Fixed supply (no inflation)
Deflationary via burns
Value drivers:
Usage-backed demand
More agents = more FDRY needed
Platform growth = token demand growth
Deflationary burns
50% of all buybacks permanently burned
Supply decreases every day
At scale: millions of dollars burned monthly
Network effects
Better index = more agents
More agents = more revenue
More revenue = more burns
More burns = higher value
Investment thesis:
Real utility (required for platform)
Real revenue (usage-based)
Real burns (permanent supply reduction)
Early holders benefit most from scarcity
Next: Understand the Technical Details of how everything fits together.
Last updated