# Integuru-AI/Integuru

The first AI agent that builds permissionless integrations through reverse engineering platforms' internal APIs.

Repository: https://github.com/Integuru-AI/Integuru
Canonical: https://ross.abutalabs.com/products/integuru
Homepage: https://integuru.ai
Language: Python
License: AGPL-3.0
License Family: copyleft
Topics: agents, ai-agent, llm, integrations, integration, agent, ai-agents, openapi, unofficial-api, unofficial-apis, automation, robotic-process-automation, rpa, api, apis, open-source
Last push: 2026-06-24T19:23:18+00:00

## Health v2 (maintenance only)
Score: 62/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 89, release rhythm 35, longevity 48
- inputs: {"age_days": 680, "days_push": 70, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 4760, forks 382 (observed 2026-08-28T04:08:59.048529+00:00)

## What it is
Integuru is an AI agent that reverse-engineers platforms' internal APIs by analyzing browser network requests (HAR files) and building dependency graphs of HTTP calls. It generates runnable Python integration code for platforms that lack official APIs, without browser automation or RPA.

## Use cases
- build integrations for platforms without official APIs
- reverse engineer a website's internal API
- generate Python code to download data from a web portal
- automate actions on SaaS platforms via direct HTTP requests
- replace brittle browser automation with direct API calls
- map dependencies between a website's network requests

## When to choose
- the target platform has no official API or documentation
- you want direct HTTP integrations instead of flaky browser automation
- you need to automate authenticated web workflows programmatically

## When to avoid
- the platform offers an official, supported API
- you need a fully supported, maintained commercial integration (the hosted Integuru service covers that)
- you cannot legally or ethically access the platform's internal endpoints

## Facets
- artifact type: library
- maturity: active
- function: agent-framework, llm-inference, web-scraping, http-client, workflow-automation
- domain: apis, developer-tools, reverse-engineering
- platform: python, cli, cross-platform
- tags: reverse-engineering, unofficial-apis, integration-generation, har-analysis, rpa-alternative, openapi, llm-agent, ai-agents, automation

## Member repositories
- Integuru-AI/Integuru (main) score 62

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:08:59.048529+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 2026-08-29T18:18:51.690251+00:00, confidence not recorded.
  - readme: https://github.com/Integuru-AI/Integuru (fetched 2026-08-28T04:08:59.048529+00:00, sha ccb9b518099b)
  - homepage: https://integuru.ai (fetched 2026-08-29T09:02:18.904403+00:00, sha 387bdca30783)
  - site_page: https://www.integuru.com/faq (fetched 2026-08-29T09:02:18.913640+00:00, sha a6c95e4d66b0)
  - site_page: https://www.integuru.com/integrations (fetched 2026-08-29T09:02:18.915630+00:00, sha b0d5588b1c4a)
- Data as of 2026-08-30T08:39:29.467469+00:00.