Metadata-Version: 2.4
Name: crewai-olostep
Version: 0.1.0
Summary: CrewAI tools for web scraping and research using Olostep API
Author-email: Olostep <info@olostep.com>
License: MIT
Project-URL: Homepage, https://olostep.com
Project-URL: Documentation, https://docs.olostep.com/integrations/crewai
Project-URL: Repository, https://github.com/olostep/olostep-tools
Project-URL: Issues, https://github.com/olostep/olostep-tools/issues
Keywords: crewai,olostep,web-scraping,ai-agents,multi-agent,automation,research
Classifier: Development Status :: 4 - Beta
Classifier: Intended Audience :: Developers
Classifier: License :: OSI Approved :: MIT License
Classifier: Programming Language :: Python :: 3
Classifier: Programming Language :: Python :: 3.10
Classifier: Programming Language :: Python :: 3.11
Classifier: Programming Language :: Python :: 3.12
Classifier: Topic :: Software Development :: Libraries :: Python Modules
Classifier: Topic :: Internet :: WWW/HTTP :: Indexing/Search
Requires-Python: >=3.10
Description-Content-Type: text/markdown
Requires-Dist: crewai>=0.70.0
Requires-Dist: olostep>=0.9.0
Requires-Dist: pydantic>=2.0.0
Requires-Dist: requests>=2.28.0
Provides-Extra: dev
Requires-Dist: pytest>=7.0.0; extra == "dev"
Requires-Dist: pytest-asyncio>=0.21.0; extra == "dev"
Requires-Dist: black>=23.0.0; extra == "dev"
Requires-Dist: ruff>=0.1.0; extra == "dev"

# CrewAI Olostep Integration

**Give your CrewAI agents the power to scrape, search, and research the web.**

This package provides ready-to-use CrewAI tools that integrate with the [Olostep API](https://olostep.com).

## Installation

```bash
pip install crewai-olostep
```

Or install from source:
```bash
cd olostep-tools/integrations/crewai/crewai-olostep
pip install -e .
```

## Quick Start

```bash
export OLOSTEP_API_KEY="your_api_key_here"
```

```python
from crewai import Agent, Task, Crew
from crewai_olostep import olostep_scrape_tool, olostep_answer_tool

researcher = Agent(
    role="Web Researcher",
    goal="Find accurate information from the web",
    tools=[olostep_scrape_tool, olostep_answer_tool],
)

task = Task(
    description="Research Stripe's pricing",
    expected_output="Summary of Stripe's pricing tiers",
    agent=researcher
)

crew = Crew(agents=[researcher], tasks=[task])
result = crew.kickoff()
```

## Available Tools

| Tool | Purpose |
|------|---------|
| `olostep_scrape_tool` | Scrape single pages (markdown/HTML/text) |
| `olostep_batch_tool` | Process up to 10K URLs in parallel |
| `olostep_crawl_tool` | Crawl entire websites by following links |
| `olostep_sitemap_tool` | Extract all URLs from a website |
| `olostep_answer_tool` | AI-powered web search with structured output |

## Documentation

See full documentation at [docs.olostep.com/integrations/crewai](https://docs.olostep.com/integrations/crewai)

