Integuru

Source#

• Repository: Integuru-AI/Integuru
• Last source update: 2026-04-05
• Last verified: 2026-04-05

Tags#

Integration notes#

Repository is workflow-oriented; map each workflow step to explicit worker contracts for predictability.

worker.md example#

Starter worker.md contract mapped from this registry entry. Copy this file and adapt schemas, constraints, and statuses for your task.

---
id: integuru-repo-derived-worker
name: Integuru Repo-Derived Worker
version: 1.0.0
source_registry_url: https://worker.md/registry/integuru/
source_repository: https://github.com/Integuru-AI/Integuru
repository_default_branch: main
repository_language: Python
repository_license: AGPL-3.0
repository_updated_at: 2026-04-05
worker_mode: workflow-automation-worker
derivation_method: github_repository_metadata_plus_raw_readme
derivation_confidence: 0.9
derived_on: 2026-04-05
tags:
  - agent
  - agents
  - ai-agent
  - ai-agents
  - api
  - apis
---

# Integuru Repo-Derived Worker

## Repo-derived summary
- Registry summary: The first AI agent that builds permissionless integrations through reverse engineering platforms' internal APIs.
- Repository description: The first AI agent that builds permissionless integrations through reverse engineering platforms' internal APIs.
- Stars (snapshot): 4,565
- Primary language: Python
- Worker mode classification: workflow-automation-worker

## Extracted from
- https://github.com/Integuru-AI/Integuru
- https://github.com/Integuru-AI/Integuru/blob/main/README.md
- https://github.com/Integuru-AI/APIs-by-Integuru

## Evidence notes (from repository text)
- README summary paragraph: First version of the AI agent that generates integration code by reverse-engineering platforms' internal APIs.
- First version of the AI agent that generates integration code by reverse-engineering platforms' internal APIs.
- 1. The agent identifies the request that downloads the utility bills.
- 5. The agent traverses up the graph, starting from nodes (requests) with no outgoing edges until it reaches the master node while converting each node to a runnable function.
- The tool uses a cloud-based LLM (OpenAI's GPT-4o and o1-preview models).
- The LLM is not trained or improved by the usage of this tool.

## Installation hints found in README
- No explicit package installation command detected in README text.

## worker.md contract (derived starter)
Purpose: Execute one automation workflow step in a bounded worker run.

### Input schema
```json
{
  "type": "object",
  "additionalProperties": false,
  "required": [
    "run_id",
    "trigger",
    "step"
  ],
  "properties": {
    "run_id": {
      "type": "string"
    },
    "trigger": {
      "type": "object"
    },
    "step": {
      "type": "string"
    }
  }
}
```

### Output schema
```json
{
  "type": "object",
  "additionalProperties": false,
  "required": [
    "run_id",
    "step",
    "status",
    "artifacts"
  ],
  "properties": {
    "run_id": {
      "type": "string"
    },
    "step": {
      "type": "string"
    },
    "status": {
      "type": "string",
      "enum": [
        "ok",
        "retryable_error",
        "invalid_request",
        "invalid_output"
      ]
    },
    "artifacts": {
      "type": "array"
    }
  }
}
```

### Constraints
- timeout_seconds: 30
- max_attempts: 2
- idempotency_key: run_id
- status_enum: [ok, retryable_error, invalid_request, invalid_output]
- notes: adapt to concrete APIs/classes documented in this repository before production use

## How this should be used
1. Treat this file as a repo-derived starter profile, not a claim of an official repository API contract.
2. Replace schemas with exact interfaces from code/docs you adopt.
3. Keep execution bounded and auditable using worker protocol constraints.

How to use#

• Save this as a worker spec file (for example: integuru-my-task.worker.md).
• Replace the input/output schemas and purpose with your real bounded task.
• Enforce schema validation + timeout + retry policy in your runtime before production use.

Citation#

Reference URL: https://worker.md/registry/integuru/

Source URL: https://github.com/Integuru-AI/Integuru