AgentIndex icon
AgentIndex
ToolsMCP ServersHOTCategoriesTrendingNewBest ListsCompareGuides
Submit Tool
ToolsMCP ServersHOTCategoriesTrendingNewBest ListsCompareGuides
Home/
API Integration/
Integuru
Integuru logo

Integuru

Active·★ 4.8k·AGPL-3.0·Updated 2026-06-24

Integuru v0 is the first version of an AI agent that generates integration code by reverse-engineering a platform's internal APIs. You run `create_har.py` to open a browser, log in and perform the action you want to automate (for example downloading a utility bill), which saves a HAR file of the network requests plus cookies; then you give Integuru a prompt such as "download utility bills". The agent outputs runnable Python code that performs the action.

The README explains the method: it identifies the request that performs the action, finds which parts of it (such as account or user IDs) depend on other requests, locates the requests that supply those values and attaches them to build a dependency graph, repeats until only authentication cookies are needed, then walks up the graph converting each request into a runnable function. Features are dependency-graph generation, input variables (currently supported for graph generation only, with code-generation support coming) and code generation for all requests in the graph. Setup needs an OpenAI API key (gpt-4o is recommended for graph generation, switching to o1-preview for code generation if available) and Poetry. A note covers two-factor authentication. It is AGPL-3.0 licensed.

This write-up is based on the project's README and public repository data. We have not hand-tested the tool. Data as of 2026-10-25.

License
AGPL-3.0
Latest release
No GitHub releases
Last commit
2026-06-24
Contributors
7
Forks
377
Open issues and PRs
25
First published
2024-10-22

Source: GitHub, npm and PyPI public APIs.

#AI Agent#API Reverse-engineering#Code Generation#Python#LLM#Coding
$ Install
$ poetry install
↗ Visit site★ GitHub
01

Features

01Generates a dependency graph of requests for desired actions.
02Supports input variables for graph generation (code generation support coming soon).
03Generates executable Python code to hit all requests in the graph.
04Handles two-factor authentication (2FA) by utilizing post-2FA cookies/tokens.
05Built by Integuru.ai, offering custom integrations and hosting services.
02

Why choose it

+Turns a recorded browser session (HAR file and cookies) into runnable Python code for the action you performed.
+Builds a dependency graph of requests, so values like account IDs are fetched from the earlier requests that provide them.
+Useful for platforms with no public API, since it works from the internal requests the site's own front end makes.
+Setup is documented step by step, with a Jupyter notebook and unit tests.
03

Trade-offs

!It is labelled v0 and input variables are only supported for graph generation so far, with code-generation support still coming.
!It needs an OpenAI API key with access to capable models (gpt-4o, and o1-preview for code generation), which costs money per run.
!Reverse-engineering a platform's internal API may breach its terms of service, internal endpoints can change without notice, and the README has a note on 2FA limitations.
04

Maintenance check

SlowingChecked: 2026-10-26
Last commit
2026-05-26
Commits, last 90 days
0
Releases, last 90 days
0
Latest release
—
Open issues
25
Recent issues with at least one comment
4/10
Commits per week, last 12 weeks
Commits per week, last 12 weeks: 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0

Oldest week on the left; the latest four weeks are orange. Source: GitHub commit activity.

Status rule: archived on GitHub = Archived; last commit within 90 days = Active; 91 to 365 days = Slowing; older = Stale. All figures come from the GitHub API on the date shown.

Most discussed open issues

  • #17 `jiter` build fails when running `poetry install` on Darwin2 comments · 2024-11-01
  • #38 Is this organization still active or not?1 comments · 2025-11-12
  • #30 Maximum context length errors with OpenAI1 comments · 2025-01-08
  • #35 Support for HTML SSR sites0 comments · 2025-06-04
  • #34 Automatic navigation / interactions0 comments · 2025-06-04

Issue titles are quoted from GitHub. Open the link to check whether a problem still applies to the version you use.

05

Compatibility

OpenAI Models
Supported
Verified via docs
06

Quick start

1
$ poetry install
07

Use cases

↳Automating interactions with undocumented internal APIs of various platforms.
↳Generating custom integration code for platforms without official SDKs.
↳Reverse-engineering complex multi-step API workflows for data extraction or task automation.
08

Alternatives

⚡Top VS:
VSOpen Interpreter★68.7k→VSwhatsapp-mcp★6.7k→VSgoogle_workspace_mcp★3.4k→VSpython-utcp★653→
Open Interpreter logo
Open Interpreter★ 68.7k
A coding agent for the terminal, optimized for low-cost and open models. Forked from OpenAI's Codex, it can emulate other agent harnesses and runs commands in a native sandbox.
VSCompare→
whatsapp-mcp logo
whatsapp-mcp★ 6.7k
WhatsApp MCP server
VSCompare→
google_workspace_mcp logo
google_workspace_mcp★ 3.4k
Control Gmail, Google Calendar, Docs, Sheets, Slides, Chat, Forms, Tasks, Search & Drive with AI - Comprehensive Google Workspace / G Suite MCP Server
VSCompare→
python-utcp logo
python-utcp★ 653
Official python implementation of UTCP. UTCP is an open standard that lets AI agents call any API directly, without extra middleware.
VSCompare→
Context7 logo
Context7★ 63.8k
MCP Server that provides up-to-date code documentation for LLMs and AI code editors.
VSCompare→
GPT Researcher logo
GPT Researcher★ 30.3k
An autonomous agent that conducts deep research on any data using any LLM provider, producing detailed reports with citations from web and local sources.
VSCompare→
Pydantic AI logo
Pydantic AI★ 20.9k
GenAI Agent Framework, the Pydantic way. A Python agent framework designed for production with type safety at its core.
VSCompare→
DeepCode logo
DeepCode★ 16.8k
DeepCode is an open-source coding agent from HKUDS for real software engineering: goal-driven loops, evidence-based verification, durable sessions, and Paper2Code research reproduction.
VSCompare→
See all alternatives →

Comments

Log in to leave a comment

No comments yet. Be the first!

On this page
01Features02Why choose it03Trade-offs04Maintenance check05Compatibility06Quick start07Use cases08Alternatives
Integuru-AI /
Integuru
↗

Agent that reverse-engineers a site's internal API calls into runnable Python code

4.8k377AGPL-3.0
Last commit4mo ago
StatusActive
CategoryAPI Integration
Contributors7
Links
Documentation↗Discussion↗Issues↗Releases↗
Cloud Infrastructure
Ad

Deploy on DigitalOcean

Host your MCP servers, Docker containers, and AI agents with $200 free credit over 60 days.

Claim $200 Free Credit
© 2026 AgentIndex.app|Built by a 10-year iOS Developer.
Best by use caseAboutContactAdvertisePrivacy PolicyTerms of UseQYSGitHubBuy me a coffee ☕

Browse by Category

MCP ServersCode AssistantWorkflow AutomationRAG / Knowledge BaseMulti-AgentBrowser AutomationLLM InfraDev ToolingObservability

Not affiliated with Anthropic, OpenAI or Microsoft.