raereverse-api-engineer

Introduction

Reverse-engineer any website's API and get a production-ready Python client in minutes.

Reverse API Engineer is a CLI tool that captures browser traffic and uses your configured AI SDK to generate production-ready Python (or JavaScript / TypeScript) API clients. No more manual reverse engineering: browse, capture, and get clean API code.

Agent mode capturing a job board
Agent mode: the AI browses, captures, and writes the client end-to-end.
Install

Get the CLI running in under a minute.

Quick start

From install to a working Python client.

Usage modes

Agent, Manual, Engineer, Collector.

Configuration

Models, providers, SDKs, output.

What you can do with it

Reverse-engineer any HTTP-based API

Job boards, e-commerce, SaaS dashboards, social platforms, internal admin tools: if it's a website that talks to a backend, Reverse API Engineer can map that backend for you. The generated client wraps the same endpoints your browser called, with auth, pagination, and error handling already wired up.

Drive captures from another agent

Scripted commands are available for agent workflows. agent and engineer support --json plus non-interactive execution, list and show support JSON output, and run supports --no-interactive for script selection and dependency prompts. Easy to wrap in a CI job, a Claude Agent SDK loop, or a cron task.

Feature deep-dive

Browser automation with stealth

Built on Playwright with anti-detection patches and viewport randomisation. Captures every request as HAR: headers, cookies, request bodies, response bodies, timing.

Autonomous agent loop

Plug an MCP-driven agent into the loop and it browses on your behalf. Two providers shipped:

  • Playwright MCP (default): headless capture, fully self-contained.
  • Chrome DevTools MCP: drives your real Chrome with existing sessions, cookies, and auth.

The agent reverse-engineers the API in real time while it browses, so by the time the run ends, the client is already generated.

AI-powered codegen with Claude

The HAR is fed to your configured model (Claude by default) along with a tuned system prompt. Output:

  • Typed Python (or TS / JS) clients with docstrings.
  • Authentication handling: cookies, bearers, CSRF tokens.
  • Pagination helpers, error types, retry-safe operations.
  • A runnable example_usage.* and a generated README.md.

Multi-SDK: Claude, OpenCode, Copilot, or Cursor

Use Anthropic's API directly (default) or route through OpenCode running locally. Copilot and Cursor SDK backends are also available when their optional dependencies and credentials are configured.

Interactive CLI with mode cycling

Press Shift+Tab to cycle between modes. Slash commands (/settings, /history, /messages) keep configuration and run inspection one keystroke away.

Session history & cost tracking

Every run is saved to ~/.reverse-api/runs/. View past captures, generated scripts, and full message logs. Token usage and cost are tracked per run with cache-hit awareness, useful when iterating with engineer mode on the same HAR.

Production-ready output

Generated scripts include type hints, structured error handling, and inline documentation. They're not "demo" snippets; they're meant to be checked into your codebase and called from production.

Output in Python, JavaScript, or TypeScript

Switch the target language in /settings. Same capture, different code. Useful when you want the same API client surfaced to multiple stacks.

Limitations

License

MIT. See LICENSE.