Docsgene (v1.0.0) is an AI-focused tool that bundles codebase context into a single file optimized for LLM ingestion. It scans project files, intelligently selects relevant code, and outputs a compact representation that preserves dependencies and structure, reducing token overhead. Released as initial stable version; no established release cadence yet. Key differentiator: purpose-built for LLM context windows, unlike generic bundlers.
npm install docsgeneVerified import paths — ran on the pinned version, not inferred.
Shows how to import and use the main bundleCodebase function to generate an LLM-friendly context file from a source directory.
Use import syntax. If using Node.js, set "type": "module" in package.json or use .mjs extension.
Explicitly pass ignorePatterns for all non-essential directories.
Monitor tokenCount in result and adjust maxTokens or ignorePatterns accordingly.
Use import { bundleCodebase } from 'docsgene' or const { bundleCodebase } = await import('docsgene').Add "type": "module" to package.json, rename file to .mjs, or use dynamic import().
Run 'npm install docsgene' and ensure correct import path.
No dependency data recorded yet.