HN Showcase
Back to browse
GitHub Repository

flow + prompt = flompt - Visual AI Prompt Builder. Decompose, edit as flowchart, recompile into optimized machine-readable prompts

115 starsTypeScript

Flompt – Visual prompt builder that decomposes prompts into blocks

by hkonte·Mar 6, 2026·1 point·1 comment
Visit ProjectView on HN

AI Analysis

●●SolidBig BrainSolve My ProblemSlick

Figma for prompts with React Flow—but prompt engineering tools already exist.

Strengths
  • •12-block taxonomy maps directly to Claude's documented best practices, not arbitrary UI fiction
  • •Three interfaces (web, extension, MCP) let you prompt-engineer in-context without tab-switching
  • •Decomposition uses Claude itself, preserving semantic intent while breaking into editable chunks
Weaknesses
  • •Prompt engineering is already solved by ChatGPT's UI, Claude's web interface, and tools like Prompt.com
  • •Browser extension competes with ChatGPT's native prompt editing without clear DX advantage over built-in
Target Audience

AI engineers, prompt engineers, Claude power users

Similar To

Anthropic Prompt Templates · OpenAI's prompt engineering guides · ChatGPT custom instructions

Post Description

Anthropic's research shows prompt structure matters more than model choice. Flompt takes any raw prompt, decomposes it into 12 typed blocks (role, context, objective, constraints, examples, chain-of-thought, output format, etc.), and compiles them into Claude-optimized XML.

Three interfaces: web app (React Flow canvas), browser extension (injects into ChatGPT/Claude/Gemini toolbars), and MCP server for Claude Code.

Stack: React + TypeScript + React Flow + Zustand, FastAPI + Claude API backend, Caddy.

Free, no account, open-source. Demo: https://youtu.be/hFVTnnw9wIU

Similar Projects

AI/ML●●Solid

Prompt Builder – A block-based editor for composing AI prompts

The block metaphor and live compiled preview are honest, practical improvements for anyone wrestling with long, conditional prompts — toggles for A/B testing and global {{vars}} are especially handy. Multi-model execution and editable response panes show the author thought about iteration and comparison, but the screenshot feels safe and functional rather than boldly new; I want to know how it handles collaboration, exports, and model/credit management.

Solve My ProblemNiche Gem
Jaber_Said
104mo ago