Generate AI-ready context bundles from your React/TypeScript codebase in seconds. Zero config, up to 70% token savings.

Fast • Deterministic • Open Source

$npm install -g logicstamp-context

Just Launched100% Open Source

LogicStamp CLI - Open Source & Active Development

...

Stars

...

Contributors

...

Forks

...

Last Updated

Join the Movement

Built by Developers, for Developers

LogicStamp is 100% open source and community-driven. Contribute code, report issues, suggest features, or just star the repo to show your support.

Stop Pasting Code.

Start Stamping Context.

One command. Instant AI-ready context bundles. Zero manual work.

Why Developers Choose LogicStamp

Professional-grade tooling for modern development workflows

How it works

Instant setup→AI-ready context

Works with your favorite tools

Seamlessly integrate with your existing development workflow and boost productivity

Supported Frameworks

AI-ready context generation for modern frontend frameworks and TypeScript codebases.

TypeScript-first by design

LogicStamp Context currently analyzes .ts and .tsx files only. JavaScript .js and .jsx files are not analyzed yet, so components written in JS won’t appear in context bundles.

Development Tools

Works with your existing development tools and CI/CD pipelines

VS Code

Cursor

GitHub Actions

GitLab CI

Vercel

Netlify

Docker

pnpm

All trademarks and logos are the property of their respective owners. LogicStamp is an independent open-source project and is not affiliated with or endorsed by the listed frameworks.

FAQs

Quick answers to common questions

LogicStamp Context scans your React/TypeScript codebase and generates structured context bundles optimized for AI consumption. It analyzes component structure, extracts logic signatures (props, state, events), builds dependency graphs, and packages everything into machine-readable JSON with built-in token optimization. No configuration needed—just run `stamp context` and get instant AI-ready context bundles.

Pasting raw code wastes tokens on boilerplate, imports, and redundant formatting. LogicStamp Context extracts only what AI needs—component contracts, dependency relationships, and logic signatures—saving up to 65% tokens compared to full source code. Plus, it provides structured context that AI can actually parse and understand, not just raw text.

Yes! LogicStamp Context is completely free and open-source. Install it globally with npm i -g logicstamp-context and use it without limits. The CLI is production-ready and includes context generation, drift detection, validation, and token optimization. Upcoming enhancements include advanced contract verification and enhanced contract management features.

Currently supports React and TypeScript projects (including Next.js). MCP integration is available in beta (v0.1.0). Coming soon: Vue 3 and other modern frameworks. Works with any React/TypeScript codebase regardless of styling solution (Tailwind, styled-components, CSS modules, etc.).

Install globally with `npm i -g logicstamp-context`, navigate to your project directory, and run `stamp context`. The CLI generates multiple `context.json` files (one per folder) plus a `context_main.json` index with AI-ready bundles. Share these files with Claude, ChatGPT, or any AI assistant for instant codebase understanding. Use `stamp context validate` to verify the output.

LogicStamp Context offers three modes: `none` (contracts only, up to 80% savings), `header` (recommended, up to 65% savings with JSDoc headers), and `full` (complete source). The header mode includes just enough context for AI to understand component logic without wasting tokens on implementation details. Use `–compare-modes` to see exact savings for your codebase. Token estimation: LogicStamp Context includes @dqbd/tiktoken (GPT-4) and @anthropic-ai/tokenizer (Claude) as optional dependencies. npm will automatically attempt to install them when you install logicstamp-context. If installation succeeds, you get model-accurate token counts. If installation fails or is skipped (normal for optional dependencies), the tool gracefully falls back to character-based estimation. Manual installation is optional—only needed if you need accurate token counts AND automatic installation failed: npm install @dqbd/tiktoken @anthropic-ai/tokenizer

LogicStamp Context generates per-root bundles (one bundle per page/feature component) rather than individual files per component. Each bundle contains the root component plus its complete dependency graph—all related components together. This design matches how developers work: when you need help with a specific page or feature, share that bundle and the AI has complete context in one self-contained unit.

The `stamp context style` command generates context bundles with visual and layout metadata included. It extracts style information from your components including Tailwind CSS classes, SCSS/CSS modules, inline styles, styled-components/Emotion, framer-motion animations, and Material UI components. This enables AI assistants to understand visual design, suggest visually consistent components, analyze layout patterns, track color palettes, and identify animations. Use it when you need AI to understand the visual aspects of your UI, not just the logic. Note: Style metadata adds more tokens (~58-65% of raw source vs ~30% for header mode), so use `–compare-modes` to see the exact cost impact for your codebase.

Watch mode is currently under evaluation. The context and compare workflow may work better with MCP (Model Context Protocol) integration without watch mode, as MCP provides more efficient and controlled context updates. We’re exploring whether watch mode adds value or if the MCP-based approach offers a superior developer experience.

Ready to supercharge your AI workflow?

Generate AI-ready context from your codebase in seconds. Fast, deterministic, zero-config.

"Stop pasting code. Start sharing structured context bundles that AI actually understands. LogicStamp Context transforms your codebase into machine-readable documentation with built-in token optimization."

— LogicStamp Team