Skip to main content

Strands Tools Community

License: MIT Python 3.9+ PyPI version Downloads

Community-built production-ready tools for Strands Agents SDK. Build powerful AI agents with seamless integrations for speech processing, CRM operations, and team notifications.

📦 Installation Options

This is a meta-package that bundles three Strands community tools for convenience. For new projects following Strands conventions, consider using individual packages:

# Individual packages (recommended for new projects)
pip install strands-deepgram  # Speech processing
pip install strands-hubspot   # CRM operations
pip install strands-teams     # Teams notifications

# Or install all three via meta-package
pip install strands-tools-community

Individual Package Links:

🚀 Features

This package provides three production-ready tools that extend the capabilities of Strands agents:

Tool Description Key Features
Deepgram Speech & Audio Processing Speech-to-text, text-to-speech, audio intelligence, 30+ languages, speaker diarization
HubSpot CRM Operations Universal CRM access, smart search, CRUD operations, associations, batch processing
Microsoft Teams Notifications & Alerts Adaptive cards, pre-built templates, custom notifications, rich formatting

📦 Installation

# Install the community tools
pip install strands-tools-community

# Install Strands SDK with your preferred model provider
pip install 'strands-agents[anthropic]'  # For Anthropic Claude (recommended)
# OR
pip install 'strands-agents[openai]'     # For OpenAI GPT
# OR
pip install 'strands-agents[bedrock]'    # For AWS Bedrock

🎯 Quick Start

from strands import Agent
from strands_tools_community import deepgram, hubspot, teams

# Create an agent with all tools
agent = Agent(tools=[deepgram, hubspot, teams])

# Use natural language to interact
agent("transcribe this audio file: recording.mp3")
agent("search for contacts in HubSpot with email containing '@example.com'")
agent("send a Teams notification about new leads")

🛠️ Tools Overview

Deepgram - Speech & Audio Processing

Powerful speech processing capabilities powered by Deepgram's API.

Key Features:

  • Speech-to-Text: Transcribe audio with 30+ language support
  • Text-to-Speech: Generate natural-sounding speech in multiple voices
  • Audio Intelligence: Sentiment analysis, topic detection, intent recognition
  • Speaker Diarization: Identify and separate different speakers
  • Multi-format Support: WAV, MP3, M4A, FLAC, and more

Usage Example:

from strands import Agent
from strands_tools_community import deepgram

agent = Agent(tools=[deepgram])

# Transcribe audio with speaker identification
agent("transcribe audio from https://example.com/call.mp3 in Turkish with speaker diarization")

# Text-to-speech
agent("convert this text to speech and save as output.mp3: Hello world")

# Audio intelligence
agent("analyze sentiment and topics in recording.wav")

Configuration:

DEEPGRAM_API_KEY=your_deepgram_api_key  # Required
DEEPGRAM_DEFAULT_MODEL=nova-3            # Optional
DEEPGRAM_DEFAULT_LANGUAGE=en             # Optional

Get your API key at: console.deepgram.com


HubSpot - CRM Operations

Complete CRM integration for managing contacts, deals, companies, and more.

Key Features:

  • Universal CRM Access: Works with ANY HubSpot object type
  • Smart Search: Advanced filtering with property-based queries
  • CRUD Operations: Create, read, update, and delete records
  • Property Discovery: Automatic field detection and validation
  • Association Management: Link related objects (contacts, deals, companies)
  • Rich Console Output: Beautiful table displays with Rich library

Usage Example:

from strands import Agent
from strands_tools_community import hubspot

agent = Agent(tools=[hubspot])

# Search contacts
agent("find all contacts created in the last 30 days")

# Create a deal
agent("create a deal called 'Acme Corp Q4' with amount 50000")

# Update records
agent("update contact 12345 with lifecycle stage 'customer'")

# Get company details
agent("get company information for ID 67890")

Configuration:

HUBSPOT_API_KEY=your_hubspot_api_key  # Required
HUBSPOT_DEFAULT_LIMIT=100              # Optional

Get your API key at: app.hubspot.com/private-apps


Microsoft Teams - Notifications & Alerts

Send rich, interactive notifications to Microsoft Teams channels.

Key Features:

  • Adaptive Cards: Rich, interactive message cards
  • Pre-built Templates: Notifications, approvals, status updates
  • Custom Cards: Full adaptive card schema support
  • Action Buttons: Add interactive elements to messages
  • Rich Formatting: Markdown support, images, and media

Usage Example:

from strands import Agent
from strands_tools_community import teams

agent = Agent(tools=[teams])

# Simple notification
agent("send a Teams message: New lead from Acme Corp")

# Use pre-built templates
agent("send an approval request to Teams for the Q4 budget")

# Status updates
agent("send a status update to Teams: website redesign is 75% complete")

Configuration:

TEAMS_WEBHOOK_URL=your_webhook_url  # Optional - can be provided per call

Setup webhook: Teams Channel → Connectors → Incoming Webhook

🌟 Real-World Examples

Call Analytics Workflow

from strands import Agent
from strands_tools_community import deepgram, hubspot, teams

agent = Agent(tools=[deepgram, hubspot, teams])

# Automated call processing
agent("""
1. Transcribe the call recording at: call_recording.mp3
2. Search HubSpot for the contact with phone number from the call
3. Create a call activity in HubSpot with the transcript
4. Send a Teams notification about the call summary
""")

Lead Qualification Pipeline

# Qualify and notify about new leads
agent("""
Search HubSpot for all leads with:
- Lifecycle stage: Marketing Qualified Lead
- Created in the last 7 days
- Company size: 50+ employees

Then send a summary to Teams with the count and top 5 leads
""")

Daily Sales Digest

# Automated daily reporting
agent("""
1. Get all deals closed today from HubSpot
2. Get all new contacts created today
3. Calculate total revenue
4. Send a formatted digest to Teams with the results
""")

⚙️ Configuration

All tools support environment variables for API keys and default settings. You can also pass configuration directly when calling tools through the agent.

Environment Variables

# Deepgram Configuration
DEEPGRAM_API_KEY=your_deepgram_api_key
DEEPGRAM_DEFAULT_MODEL=nova-3
DEEPGRAM_DEFAULT_LANGUAGE=en

# HubSpot Configuration
HUBSPOT_API_KEY=your_hubspot_api_key
HUBSPOT_DEFAULT_LIMIT=100

# Microsoft Teams Configuration
TEAMS_WEBHOOK_URL=your_teams_webhook_url

API Key Resources

📚 Documentation

For more information about the Strands Agent SDK:

🤝 Contributing

Contributions are welcome! Please feel free to submit a Pull Request.

  1. Fork the repository
  2. Create your feature branch (git checkout -b feature/amazing-feature)
  3. Commit your changes (git commit -m 'Add amazing feature')
  4. Push to the branch (git push origin feature/amazing-feature)
  5. Open a Pull Request

📄 License

This project is licensed under the MIT License - see the LICENSE file for details.

🙏 Acknowledgments

💬 Support


Made with ❤️ by the community

Metadata

Release files for strands-tools-community 0.2.0

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Source distribution (sdist)

Source distribution for strands-tools-community 0.2.0
File Size Uploaded
strands_tools_community-0.2.0.tar.gz 25.8 kB Details

Built distribution (wheel)

Table of built distributions (wheels) for strands-tools-community 0.2.0
File Interpreter ABI Platform
strands_tools_community-0.2.0-py3-none-any.whl Python 3 none any Details

Total release size: 52.1 kB

Release files / strands_tools_community-0.2.0.tar.gz

Download URL strands_tools_community-0.2.0.tar.gz
Size 25.8 kB
Tags Source
SHA-256 checksum
How to use checksums
3473add49d6a44694cfb4d235c19bf053dd78edd4ff26b54f7746e4fd9a9f667
BLAKE2b-256 checksum
How to use checksums
2903bbfbc7d64ab56406228dbaf9fa5f6d88a89244c1d941e75c6caae98f1c07
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
Yes
Uploaded via twine/6.1.0 CPython/3.13.7

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

PyPI Publish Attestation

PyPI verified that this artifact, at this checksum, originated from the publisher listed below.

Signed by GitHub Actions, verified by PyPI on Oct 14, 2025.

Transparency log

Release files / strands_tools_community-0.2.0-py3-none-any.whl

Download URL strands_tools_community-0.2.0-py3-none-any.whl
Size 26.3 kB
Tags Python 3
SHA-256 checksum
How to use checksums
eea8b1ccd1f5243933e54639c25d8005973c6b6162f705acb24f6ad63e10b7af
BLAKE2b-256 checksum
How to use checksums
ad9542a6abd00b51fc43c63e2a91d0cdb0b601e325b5320f092b122301858f31
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
Yes
Uploaded via twine/6.1.0 CPython/3.13.7

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

PyPI Publish Attestation

PyPI verified that this artifact, at this checksum, originated from the publisher listed below.

Signed by GitHub Actions, verified by PyPI on Oct 14, 2025.

Transparency log

Release history Release notifications | RSS feed

This release

0.2.0 This release

2 release files

0.1.0

2 release files

Anthropic, PBC Visionary sponsor Bloomberg Visionary sponsor Hudson River Trading Visionary sponsor Meta Visionary sponsor NVIDIA Visionary sponsor Microsoft Sustainability sponsor Depot Continuous Integration AWS Cloud computing and Security Sponsor Datadog Monitoring Fastly CDN Google Download Analytics Sentry Error logging StatusPage Status page