# nottelabs/reverse-api-engineer

The agent that turns websites into APIs!

Repository: https://github.com/nottelabs/reverse-api-engineer
Canonical: https://ross.abutalabs.com/products/reverse-api-engineer
Homepage: https://reverseapi.dev
Language: Python
License: MIT
License Family: permissive
Topics: playwright, claude, web-scraping, ai, ai-agents, cli, mcp, openapi, scraping
Last push: 2026-08-30T14:40:26+00:00

## Health v2 (maintenance only)
Score: 84/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 100, release rhythm 100, longevity 18
- inputs: {"age_days": 253, "days_push": 3, "days_rel": 3, "gap_med": 2.5, "n_releases_24m": 27}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1113, forks 98 (observed 2026-09-01T02:14:05.384633+00:00)

## What it is
Reverse API Engineer is a Python CLI tool that captures browser network traffic (HAR) from a website and uses a configured AI model to generate a production-ready, typed API client in languages like Python, TypeScript, Go, and more. It supports manual browsing, an autonomous AI agent mode via Playwright or browser MCP servers, and JSON-streamed output for integration into other agent workflows.

## Use cases
- reverse-engineer an undocumented website API into a typed client
- scrape job board listings without brittle selectors
- generate API clients from e-commerce site traffic
- capture authenticated dashboard endpoints using existing browser sessions
- document backend calls of internal admin tools
- run autonomous agent-driven web data collection
- replace manual DevTools and cURL copying with automated client generation

## When to choose
- a website has no public API but your browser can reach the data
- you want a typed, reusable client instead of one-off scraping scripts
- you need to capture endpoints behind existing cookies or sessions
- you want agent-friendly JSON/NDJSON output for CI or agent loops

## When to avoid
- the target site offers an official documented API
- the site's terms of service prohibit automated access or scraping
- you need a hosted service with accounts and analytics rather than a local tool
- the endpoints rely on heavy client-side logic that HAR capture cannot generalize

## Facets
- artifact type: cli-tool
- maturity: active
- function: web-scraping, agent-framework, cli, developer-tools, mcp, data-generation
- domain: web-development, developer-tools, crawlers, apis, artificial-intelligence
- platform: cli, python, cross-platform
- tags: har-capture, api-reverse-engineering, openapi, playwright, browser-automation, code-generation, typed-clients, automation

## Member repositories
- nottelabs/reverse-api-engineer (main) score 84

## Provenance
- Observed fields: from GitHub, fetched 2026-09-01T02:14:05.384633+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T06:49:18.959215+00:00, confidence not recorded.
  - readme: https://github.com/nottelabs/reverse-api-engineer (fetched 2026-09-01T02:14:05.384633+00:00, sha a1d84711b24d)
  - homepage: https://reverseapi.dev (fetched 2026-08-29T12:51:51.851264+00:00, sha e58c8f4d064b)
  - site_page: https://reverseapi.dev/docs (fetched 2026-08-29T12:51:51.860555+00:00, sha 5d7c47acfc81)
  - site_page: https://reverseapi.dev/docs/quick-start (fetched 2026-08-29T12:51:51.862589+00:00, sha b34fcb1b7f03)
- Data as of 2026-08-30T08:39:29.467469+00:00.