Dragonote

Export repository context from a Rust CLI or Tauri desktop app, with shared scanning rules and configurable output budgets.

One Rust core, two interfaces.

Dragonote mascot

One Rust Core, Two Interfaces

The dragonote CLI and Tauri desktop app call the same Rust scanner. The desktop interface adds a file tree, checkboxes, and a directory picker; scanning, filtering, export, and chunking remain in the shared core.

CLI CLI Dragon
Desktop GUI GUI Dragon
dragonote <path>
--extra-ignore "*.log,temp/"   # skip matching patterns
--force-include "config.toml"   # override ignores
--include-resources   # include assets/static dirs
--test-mode separate|inline|exclude
--max-code-tokens 500000   # custom limits
--budget 128000   # exact token budget
--split   # auto-split large exports
--zip   # archive output
The Dragon's Vault of Code Context

Repository Scanning

Point Dragonote at a project directory and it applies practical default filters. Existing .gitignore rules are respected without additional configuration. Binary files, node_modules, build artifacts, and common junk directories are detected and skipped before a single token is counted.

Test directories (tests/, __tests__/, spec/) are automatically detected and exported separately so your LLM gets clean source context without test noise mixed in. Resource directories like assets/ and static/ are flagged and toggleable.

.dragignore is a persistent, project-level ignore file that sits alongside your .gitignore and provides project-specific control over the exported files.

5 Critical Export Artifacts

Every scan produces a complete set of structured Markdown artifacts, ready to paste directly into any LLM conversation window.

🌳
File Tree
Full directory structure with sizes
📄
Source Code
Partitioned, token-aware code context
🧪
Test Files
Separately exported test context
📊
Raw CSVs
Detected, copied & consolidated
📝
Starter Prompt
Analysis prompt & usage readme
Truncation Mode Comparison

Precise Token Truncation

Dragonote can limit exports by characters or by tokens counted with cl100k_base. The token count is exact for that encoding; model-specific wrappers, prompts, and conversation overhead are outside the export budget.

Auto-split partitions large exports, including test files, into chunks that fit the configured content budget.

Capabilities

What the scanner, the exporter and the desktop shell can each do.

Scanning

  • Smart defaults: scan any project directory
  • Automatic .gitignore & binary detection
  • Multi-root project scanning
  • Parallel scanning (rayon)
  • Configurable test directories & wildcards
  • .dragignore: persistent project-level ignore rules
  • Extra ignore patterns (glob)
  • Force-include overrides
  • Resource directory toggle

Output

  • File tree + code context output
  • Test export modes (separate / inline / exclude)
  • CSV detection, copying & consolidation
  • Auto-split & consolidated output
  • ZIP archive export
  • Analysis prompt & usage readme

Truncation

  • Custom token & character limits
  • Exact token budget mode (tiktoken cl100k_base)

Desktop GUI

  • Native directory picker
  • Multi-root add/remove chips
  • File-level checkbox control
  • Resource directory picker
CLI Dragon

Built for the Terminal

The CLI is distributed as a single native executable. It can run from a shell, script, or CI job and write structured context in one command.

Build targets v0.1.0 alpha

Configured packaging targets for the private alpha. No public installers have been published.

🪟

Windows

NSIS installer .exe MSI package .msi Standalone CLI .exe
🍎

macOS

Disk image .dmg Standalone CLI x86_64 Standalone CLI aarch64
🐧

Linux

Debian package .deb Portable bundle .AppImage Standalone CLI x86_64

Private alpha: the targets above are packaging configurations, not download links. There is no public installer or hosted demo yet.

Tech Specs

What powers Dragonote under the hood.

Core Engine

  • Language: Rust (no GC, no interpreter)
  • CLI binary: single native executable, nothing to install alongside it
  • Scanning: walkdir + the ignore crate for .gitignore semantics
  • Pattern matching: globset
  • Token counting: tiktoken-rs (cl100k_base)
  • Parallel mode: rayon
  • Archive export: zip crate

Desktop GUI

  • Framework: Tauri 2.0
  • Frontend: vanilla HTML / CSS / JS, no Node.js
  • Renderer: OS-native WebView
  • IPC: typed Rust commands, JSON serialization
  • Dialogs: native OS file pickers

Resource Footprint

  • Idle RAM: measured locally at approximately 30-50 MB
  • Background processes: none
  • Runtime deps: OS WebView only

Cross-Platform

  • Windows: 10+ (NSIS, MSI, standalone CLI)
  • macOS: 10.15+ (DMG, standalone CLI)
  • Linux: .deb, .AppImage, standalone CLI
  • Architecture: x86_64 on all three; Apple Silicon (aarch64) on macOS
  • CI-tested: 132 unit & integration tests in CI
Why Tauri? GUI technology considerations

Why not Electron?

Tauri uses the operating system's WebView rather than bundling Chromium with the application. That fits a form-driven utility and keeps the desktop shell smaller than an Electron distribution.

No npm frontend step

The frontend is static HTML, CSS, and vanilla JavaScript. No npm install, no node_modules, and no webpack step in the frontend build.

Where pure-Rust GUIs (egui) shine instead

A pure-Rust GUI would be a reasonable choice for a canvas-heavy application. Dragonote is mostly forms, file lists, and controls, which map directly to HTML and CSS.

Tauri keeps the scanning engine in Rust while allowing the desktop controls to use a small HTML, CSS, and JavaScript frontend.

Questions about the internals, or want an alpha build? Use the contact section of this site.