Skip to content
| Marketplace
Sign in
Visual Studio Code>Machine Learning>Pliny FrameworkNew to Visual Studio Code? Get it now.
Pliny Framework

Pliny Framework

0xpliny

| (0) | Free
AI-powered documentation generation using the HARVEST methodology. Document entire repos, files, and folders with iterative quality-scored output.
Installation
Launch VS Code Quick Open (Ctrl+P), paste the following command, and press enter.
Copied to clipboard
More Info

🌾 Pliny Framework — Cursor Extension

AI-powered documentation generation using the HARVEST methodology. Point it at any repo or file, and get comprehensive, quality-scored documentation out.


✨ Features

🏗️ Document Entire Repositories — Enter a GitHub Enterprise URL, Pliny clones it, analyzes the codebase, and generates full project documentation

📁 Document Open Folders — Right-click any folder or document your current workspace with one command

📄 HARVEST Single Files — Run the 7-phase HARVEST loop on any open file for deep documentation

🔍 Standards Checking — Validate code against your team's coding standards with violations shown in the Problems panel

📊 Quality Scoring — Every run scores documentation on completeness, accuracy, and consistency (target: 95%+)

🤖 Multi-Provider AI — Works with Cursor's built-in AI, OpenRouter, or Anthropic API

🎨 Sidebar Panel — Quick-access actions, recent run history with quality bars, and settings at a glance


🚀 Installation in Cursor

Step 1: Get the .vsix file

The extension package is located at:

pliny-framework/vscode-extension/pliny-framework-0.1.0.vsix

Step 2: Open Cursor

Launch Cursor (the AI code editor).

Step 3: Open the Command Palette

Press:

Ctrl + Shift + P    (Windows/Linux)
Cmd + Shift + P     (Mac)

Step 4: Install from VSIX

  1. Type Extensions: Install from VSIX in the command palette
  2. Press Enter
  3. A file picker dialog will open

Step 5: Select the file

Navigate to:

pliny-framework/vscode-extension/pliny-framework-0.1.0.vsix

Select it and click Open.

Step 6: Restart Cursor

Cursor will prompt you to reload. Click Reload Now.

Step 7: Verify installation ✅

You should see:

  • 🌾 Pliny icon in the left sidebar (activity bar)
  • 🎯 5 commands when you type "Pliny" in the command palette (Ctrl+Shift+P)

That's it! You're ready to go. 🎉


⚙️ First-Time Setup

Configure an API Key

Before generating documentation, you need an LLM provider:

  1. Press Ctrl+Shift+P
  2. Type Pliny: Configure API Key
  3. Choose OpenRouter or Anthropic
  4. Paste your API key (it's stored securely in Cursor's encrypted secret storage 🔐)

💡 Tip: If you're using Cursor Pro/Business, Pliny can use Cursor's built-in AI automatically — no API key needed! Just set the provider to auto or cursor in settings.

Provider Priority (Auto Mode)

When provider is set to auto, Pliny checks in this order:

  1. 🖥️ Cursor AI — uses your Cursor subscription (free if you have Cursor Pro)
  2. 🌐 OpenRouter — multi-model gateway (recommended for flexibility)
  3. 🔬 Anthropic — direct Claude API access

📖 Usage

🏗️ Document a GitHub Repository

  1. Ctrl+Shift+P → Pliny: Document Repository
  2. Paste a GitHub/GHE URL (e.g., https://ghe.company.com/org/repo)
  3. Pliny clones the repo, analyzes it, and runs 7 HARVEST phases
  4. 📄 The generated documentation opens automatically when complete

📁 Document a Folder

Option A — Command Palette:

  1. Ctrl+Shift+P → Pliny: Document Open Folder
  2. If multiple workspaces are open, pick one

Option B — Right-Click:

  1. Right-click any folder in the Explorer sidebar
  2. Click Pliny: Document Open Folder

📄 HARVEST a Single File

Option A — Command Palette:

  1. Open a file in the editor
  2. Ctrl+Shift+P → Pliny: HARVEST File

Option B — Right-Click:

  1. Right-click inside any open file
  2. Click Pliny: HARVEST File

🔍 Check Standards

  1. Open a .js, .ts, .py, .cs, .cpp, or .vb file
  2. Ctrl+Shift+P → Pliny: Check Standards
  3. Violations appear in the Problems panel (Ctrl+Shift+M) with line numbers and suggestions

🎛️ Sidebar Panel

Click the 🌾 Pliny icon in the activity bar to open the sidebar:

┌─────────────────────────┐
│ Pliny Framework         │
├─────────────────────────┤
│ 📦 Document Repository  │
│ 📁 Document Open Folder │
│ 📄 HARVEST File         │
│ 🔍 Check Standards      │
├─────────────────────────┤
│ 📊 RECENT RUNS          │
│  ✅ my-api-server      │
│     96.2% · 45s · 3/26  │
│  ✅ pliny-framework     │
│     94.8% · 62s · 3/25  │
├─────────────────────────┤
│ ⚙️ CONFIGURATION        │
│   Provider: auto        │
│   Model: (default)      │
│   Quality: 95%          │
│   OpenRouter: 🟢        │
│   Anthropic: 🔴         │
└─────────────────────────┘
  • Click any recent run to open its output documentation
  • Quality bars show the overall score visually
  • Status dots show which API keys are configured

⚙️ Settings

Open Cursor settings (Ctrl+,) and search for "Pliny":

Setting Default Description
pliny.provider auto LLM provider: auto, openrouter, anthropic, cursor
pliny.model (empty) Model override (e.g., anthropic/claude-3.5-sonnet)
pliny.qualityThreshold 0.95 Minimum quality score (0.5–1.0)
pliny.maxIterations 5 Max HARVEST loop iterations (1–10)
pliny.maxFiles 50 Max files to analyze per repo (10–200)
pliny.outputDirectory ./output Where generated docs are saved

🔄 How HARVEST Works

The HARVEST engine runs 7 phases in an iterative loop until quality threshold is met:

Phase 1: 🌾 Harvest    → Extract all information from the code
Phase 2: 🔬 Analyze    → Identify patterns and architecture
Phase 3: 📐 Restructure → Apply 3-layer documentation template
Phase 4: ✅ Verify     → Score quality (completeness, accuracy, consistency)
Phase 5: 📚 Extend     → Add examples, getting started, troubleshooting
Phase 6: 🔗 Synthesize → Create cross-references and glossary
Phase 7: ✨ Transform  → Polish to publication-ready Markdown

If quality < threshold → repeat all 7 phases (up to max iterations).

📄 Output Structure

Generated docs follow a 3-layer framework:

  • Layer 1: Project Understanding — Purpose, architecture, tech stack, key concepts
  • Layer 2: System Intelligence — Module relationships, data flows, critical paths, error handling
  • Layer 3: Reference — Module inventory, API surface, config reference, dependencies, known issues

Plus: getting started guide, development workflow, troubleshooting, glossary, and 10+ cross-references per section.


🛠️ CLI Usage (Alternative)

The Pliny Framework also works as a standalone CLI:

cd pliny-framework
npm install

# Document a repo
node bin/pliny.js document https://ghe.company.com/org/repo

# Document a local folder
node bin/pliny.js document ./path/to/project

# HARVEST a single file
node bin/pliny.js harvest path/to/file.js

# Check standards
node bin/pliny.js check standards --type js path/to/file.js

🐛 Troubleshooting

❓ "No LLM provider available"

→ Run Pliny: Configure API Key to set up OpenRouter or Anthropic, or switch to Cursor AI in settings.

❓ Extension not appearing after install

→ Reload Cursor: Ctrl+Shift+P → Developer: Reload Window

❓ Clone fails for private repo

→ Make sure your Git credentials are configured for GHE: git config --global credential.helper manager

❓ Documentation quality is low

→ Increase pliny.maxIterations (default 5) and pliny.maxFiles (default 50) in settings.

❓ Output channel logs

→ Open the Output panel (Ctrl+Shift+U) and select Pliny from the dropdown to see detailed phase logs.


📋 Requirements

  • Cursor v1.93+ (or VS Code v1.93+)
  • Node.js 18+ (bundled with Cursor)
  • Git (for cloning repositories)
  • One of: Cursor Pro subscription, OpenRouter API key, or Anthropic API key

👨‍💻 Author

Chase Logan — Built with the Pliny R-I-S-E, C-A-R-E, and HARVEST frameworks.


📄 License

MIT

  • Contact us
  • Jobs
  • Privacy
  • Manage cookies
  • Terms of use
  • Trademarks
© 2026 Microsoft