Generated by Code IQ · v1.0

dexter
Knowledge Tutorial

A chapter-by-chapter walkthrough of dexter, generated from its source code and tutorial markdown.

7
Chapters
-
Subsystems
∞
Rabbit Holes
▶ Start Reading ⎇ View on GitHub
System Architecture

How the pieces fit

dexter is organized as connected concepts and components. Start broad, then drill down chapter by chapter.

⚙️
Interactive CLI & State Management
Interactive CLI & State Management
👥
The Recursive Agent Loop
The Recursive Agent Loop
⚙️
Skills System
Skills System
🔧
Tool Registry & Execution
Tool Registry & Execution
⚙️
Financial Data Layer
Financial Data Layer
⚙️
Communication Gateway
Communication Gateway
⚙️
Evaluation & Benchmarking
Evaluation & Benchmarking
dexter — bash
➜open tutorial
◆ Scanning numbered chapters
◆ Building navigation and Mermaid diagrams
◆ Generating chapter and subsystem pages
✓ 7 chapter pages built
✓ Theme toggle enabled
➜
Repository Overview

Intro and Architecture Diagram

Dexter is an autonomous financial research agent that bridges natural language queries with complex financial data. Instead of a linear script, it uses a recursive loop to iteratively "think," select from a registry of specialized tools and skills (like DCF analysis), and execute actions until a comprehensive answer is found. The system supports interaction via a CLI or messaging platforms like WhatsApp, backed by a rigorous benchmarking framework to ensure accuracy.

Source Repository: https://github.com/virattt/dexter

flowchart TD A0["The Recursive Agent Loop"] A1["Tool Registry & Execution"] A2["Financial Data Layer"] A3["Skills System"] A4["Interactive CLI & State Management"] A5["Communication Gateway"] A6["Evaluation & Benchmarking"] A4 -->|"Invokes and visualizes"| A0 A5 -->|"Routes messages to"| A0 A6 -->|"Tests and scores"| A0 A0 -->|"Selects and executes"| A1 A0 -->|"Injects prompt context from"| A3 A1 -->|"Wraps and registers"| A2 A1 -->|"Exposes as tools"| A3
Tutorial Chapters

All 7 chapters

Follow sequentially or jump to any topic. Start with Interactive CLI & State Management.

Ch.01 CORE
Interactive CLI & State Management
Welcome to Dexter! If you are building an autonomous AI agent, you need a way to talk to it and see what it is doing.
↗
Ch.02 AGENTS
The Recursive Agent Loop
In the previous chapter, Interactive CLI & State Management, we built the dashboard (the body) of our application. We created a way to see…
↗
Ch.03 CORE
Skills System
In the previous chapter, The Recursive Agent Loop, we built the "Brain" of our agent. We gave it a loop that allows it to Think, Act, and O…
↗
Ch.04 TOOLS
Tool Registry & Execution
In the previous chapter, Skills System, we gave our agent a "Manual." It knows what steps to take to solve a problem (like a DCF Valuation).
↗
Ch.05 CORE
Financial Data Layer
In the previous chapter, Tool Registry & Execution, we gave our agent "hands" (Tools) and a way to use them (The Executor). We taught it ho…
↗
Ch.06 CORE
Communication Gateway
In the previous chapter, Financial Data Layer, we turned our agent into a capable financial analyst. It can read balance sheets and analyze…
↗
Ch.07 CORE
Evaluation & Benchmarking
In the previous chapter, Communication Gateway, we connected Dexter to the outside world, allowing users to chat via WhatsApp.
↗
About This Project

Generated by Code IQ

This tutorial was automatically generated by Code IQ and rendered with the shared tutorial site builder. It can be produced for any repository tutorial folder that follows the numbered markdown chapter layout.

View Code IQ ↗
python build_site.py '/home/runner/work/Code-IQ/Code-IQ/output/dexter'

// → 7 chapters
// → source: virattt/dexter