tools

A set of tools that gives agents powerful capabilities.

Stars: 587

Visit

Strands Agents Tools is a community-driven project that provides a powerful set of tools for your agents to use. It bridges the gap between large language models and practical applications by offering ready-to-use tools for file operations, system execution, API interactions, mathematical operations, and more. The tools cover a wide range of functionalities including file operations, shell integration, memory storage, web infrastructure, HTTP client, Slack client, Python execution, mathematical tools, AWS integration, image and video processing, audio output, environment management, task scheduling, advanced reasoning, swarm intelligence, dynamic MCP client, parallel tool execution, browser automation, diagram creation, RSS feed management, and computer automation.

README:

Strands Agents Tools

A model-driven approach to building AI agents in just a few lines of code.

Documentation ◆ Samples ◆ Python SDK ◆ Tools ◆ Agent Builder ◆ MCP Server

✨ Features

📁 File Operations - Read, write, and edit files with syntax highlighting and intelligent modifications
🖥️ Shell Integration - Execute and interact with shell commands securely
🧠 Memory - Store user and agent memories across agent runs to provide personalized experiences with both Mem0 and Amazon Bedrock Knowledge Bases
🕸️ Web Infrastructure - Perform web searches, extract page content, and crawl websites with Tavily and Exa-powered tools
🌐 HTTP Client - Make API requests with comprehensive authentication support
💬 Slack Client - Real-time Slack events, message processing, and Slack API access
🐍 Python Execution - Run Python code snippets with state persistence, user confirmation for code execution, and safety features
🧮 Mathematical Tools - Perform advanced calculations with symbolic math capabilities
☁️ AWS Integration - Seamless access to AWS services
🖼️ Image Processing - Generate and process images for AI applications
🎥 Video Processing - Use models and agents to generate dynamic videos
🎙️ Audio Output - Enable models to generate audio and speak
🔄 Environment Management - Handle environment variables safely
📝 Journaling - Create and manage structured logs and journals
⏱️ Task Scheduling - Schedule and manage cron jobs
🧠 Advanced Reasoning - Tools for complex thinking and reasoning capabilities
🐝 Swarm Intelligence - Coordinate multiple AI agents for parallel problem solving with shared memory
🔌 Dynamic MCP Client - ⚠️ Dynamically connect to external MCP servers and load remote tools (use with caution - see security warnings)
🔄 Multiple tools in Parallel - Call multiple other tools at the same time in parallel with Batch Tool
🔍 Browser Tool - Tool giving an agent access to perform automated actions on a browser (chromium)
📈 Diagram - Create AWS cloud diagrams, basic diagrams, or UML diagrams using python libraries
📰 RSS Feed Manager - Subscribe, fetch, and process RSS feeds with content filtering and persistent storage
🖱️ Computer Tool - Automate desktop actions including mouse movements, keyboard input, screenshots, and application management

📦 Installation

Quick Install

pip install strands-agents-tools

To install the dependencies for optional tools:

pip install strands-agents-tools[mem0_memory, use_browser, rss, use_computer]

Development Install

# Clone the repository
git clone https://github.com/strands-agents/tools.git
cd tools

# Create and activate virtual environment
python3 -m venv .venv
source .venv/bin/activate  # On Windows: venv\Scripts\activate

# Install in development mode
pip install -e ".[dev]"

# Install pre-commit hooks
pre-commit install

Tools Overview

Below is a comprehensive table of all available tools, how to use them with an agent, and typical use cases:

Tool	Agent Usage	Use Case
a2a_client	`provider = A2AClientToolProvider(known_agent_urls=["http://localhost:9000"]); agent = Agent(tools=provider.tools)`	Discover and communicate with A2A-compliant agents, send messages between agents
file_read	`agent.tool.file_read(path="path/to/file.txt")`	Reading configuration files, parsing code files, loading datasets
file_write	`agent.tool.file_write(path="path/to/file.txt", content="file content")`	Writing results to files, creating new files, saving output data
editor	`agent.tool.editor(command="view", path="path/to/file.py")`	Advanced file operations like syntax highlighting, pattern replacement, and multi-file edits
shell*	`agent.tool.shell(command="ls -la")`	Executing shell commands, interacting with the operating system, running scripts
http_request	`agent.tool.http_request(method="GET", url="https://api.example.com/data")`	Making API calls, fetching web data, sending data to external services
tavily_search	`agent.tool.tavily_search(query="What is artificial intelligence?", search_depth="advanced")`	Real-time web search optimized for AI agents with a variety of custom parameters
tavily_extract	`agent.tool.tavily_extract(urls=["www.tavily.com"], extract_depth="advanced")`	Extract clean, structured content from web pages with advanced processing and noise removal
tavily_crawl	`agent.tool.tavily_crawl(url="www.tavily.com", max_depth=2, instructions="Find API docs")`	Crawl websites intelligently starting from a base URL with filtering and extraction
tavily_map	`agent.tool.tavily_map(url="www.tavily.com", max_depth=2, instructions="Find all pages")`	Map website structure and discover URLs starting from a base URL without content extraction
exa_search	`agent.tool.exa_search(query="Best project management tools", text=True)`	Intelligent web search with auto mode (default) that combines neural and keyword search for optimal results
exa_get_contents	`agent.tool.exa_get_contents(urls=["https://example.com/article"], text=True, summary={"query": "key points"})`	Extract full content and summaries from specific URLs with live crawling fallback
python_repl*	`agent.tool.python_repl(code="import pandas as pd\ndf = pd.read_csv('data.csv')\nprint(df.head())")`	Running Python code snippets, data analysis, executing complex logic with user confirmation for security
calculator	`agent.tool.calculator(expression="2 * sin(pi/4) + log(e**2)")`	Performing mathematical operations, symbolic math, equation solving
code_interpreter	`code_interpreter = AgentCoreCodeInterpreter(region="us-west-2"); agent = Agent(tools=[code_interpreter.code_interpreter])`	Execute code in isolated sandbox environments with multi-language support (Python, JavaScript, TypeScript), persistent sessions, and file operations
use_aws	`agent.tool.use_aws(service_name="s3", operation_name="list_buckets", parameters={}, region="us-west-2")`	Interacting with AWS services, cloud resource management
retrieve	`agent.tool.retrieve(text="What is STRANDS?")`	Retrieving information from Amazon Bedrock Knowledge Bases
nova_reels	`agent.tool.nova_reels(action="create", text="A cinematic shot of mountains", s3_bucket="my-bucket")`	Create high-quality videos using Amazon Bedrock Nova Reel with configurable parameters via environment variables
agent_core_memory	`agent.tool.agent_core_memory(action="record", content="Hello, I like vegetarian food")`	Store and retrieve memories with Amazon Bedrock Agent Core Memory service
mem0_memory	`agent.tool.mem0_memory(action="store", content="Remember I like to play tennis", user_id="alex")`	Store user and agent memories across agent runs to provide personalized experience
memory	`agent.tool.memory(action="retrieve", query="product features")`	Store, retrieve, list, and manage documents in Amazon Bedrock Knowledge Bases with configurable parameters via environment variables
environment	`agent.tool.environment(action="list", prefix="AWS_")`	Managing environment variables, configuration management
generate_image_stability	`agent.tool.generate_image_stability(prompt="A tranquil pool")`	Creating images using Stability AI models
generate_image	`agent.tool.generate_image(prompt="A sunset over mountains")`	Creating AI-generated images for various applications
image_reader	`agent.tool.image_reader(image_path="path/to/image.jpg")`	Processing and reading image files for AI analysis
journal	`agent.tool.journal(action="write", content="Today's progress notes")`	Creating structured logs, maintaining documentation
think	`agent.tool.think(thought="Complex problem to analyze", cycle_count=3)`	Advanced reasoning, multi-step thinking processes
load_tool	`agent.tool.load_tool(path="path/to/custom_tool.py", name="custom_tool")`	Dynamically loading custom tools and extensions
swarm	`agent.tool.swarm(task="Analyze this problem", swarm_size=3, coordination_pattern="collaborative")`	Coordinating multiple AI agents to solve complex problems through collective intelligence
current_time	`agent.tool.current_time(timezone="US/Pacific")`	Get the current time in ISO 8601 format for a specified timezone
sleep	`agent.tool.sleep(seconds=5)`	Pause execution for the specified number of seconds, interruptible with SIGINT (Ctrl+C)
agent_graph	`agent.tool.agent_graph(agents=["agent1", "agent2"], connections=[{"from": "agent1", "to": "agent2"}])`	Create and visualize agent relationship graphs for complex multi-agent systems
cron*	`agent.tool.cron(action="schedule", name="task", schedule="0 * * * *", command="backup.sh")`	Schedule and manage recurring tasks with cron job syntax **Does not work on Windows
slack	`agent.tool.slack(action="post_message", channel="general", text="Hello team!")`	Interact with Slack workspace for messaging and monitoring
speak	`agent.tool.speak(text="Operation completed successfully", style="green", mode="polly")`	Output status messages with rich formatting and optional text-to-speech
stop	`agent.tool.stop(message="Process terminated by user request")`	Gracefully terminate agent execution with custom message
handoff_to_user	`agent.tool.handoff_to_user(message="Please confirm action", breakout_of_loop=False)`	Hand off control to user for confirmation, input, or complete task handoff
use_llm	`agent.tool.use_llm(prompt="Analyze this data", system_prompt="You are a data analyst")`	Create nested AI loops with customized system prompts for specialized tasks
workflow	`agent.tool.workflow(action="create", name="data_pipeline", steps=[{"tool": "file_read"}, {"tool": "python_repl"}])`	Define, execute, and manage multi-step automated workflows
mcp_client	`agent.tool.mcp_client(action="connect", connection_id="my_server", transport="stdio", command="python", args=["server.py"])`	⚠️ SECURITY WARNING: Dynamically connect to external MCP servers via stdio, sse, or streamable_http, list tools, and call remote tools. This can pose security risks as agents may connect to malicious servers. Use with caution in production.
batch	`agent.tool.batch(invocations=[{"name": "current_time", "arguments": {"timezone": "Europe/London"}}, {"name": "stop", "arguments": {}}])`	Call multiple other tools in parallel.
browser	`browser = LocalChromiumBrowser(); agent = Agent(tools=[browser.browser])`	Web scraping, automated testing, form filling, web automation tasks
diagram	`agent.tool.diagram(diagram_type="cloud", nodes=[{"id": "s3", "type": "S3"}], edges=[])`	Create AWS cloud architecture diagrams, network diagrams, graphs, and UML diagrams (all 14 types)
rss	`agent.tool.rss(action="subscribe", url="https://example.com/feed.xml", feed_id="tech_news")`	Manage RSS feeds: subscribe, fetch, read, search, and update content from various sources
use_computer	`agent.tool.use_computer(action="click", x=100, y=200, app_name="Chrome")`	Desktop automation, GUI interaction, screen capture

* These tools do not work on windows

💻 Usage Examples

File Operations

from strands import Agent
from strands_tools import file_read, file_write, editor

agent = Agent(tools=[file_read, file_write, editor])

agent.tool.file_read(path="config.json")
agent.tool.file_write(path="output.txt", content="Hello, world!")
agent.tool.editor(command="view", path="script.py")

Dynamic MCP Client Integration

⚠️ SECURITY WARNING: The Dynamic MCP Client allows agents to autonomously connect to external MCP servers and load remote tools at runtime. This poses significant security risks as agents can potentially connect to malicious servers and execute untrusted code. Use with extreme caution in production environments.

This tool is different from the static MCP server implementation in the Strands SDK (see MCP Tools Documentation) which uses pre-configured, trusted MCP servers.

from strands import Agent
from strands_tools import mcp_client

agent = Agent(tools=[mcp_client])

# Connect to a custom MCP server via stdio
agent.tool.mcp_client(
    action="connect",
    connection_id="my_tools",
    transport="stdio",
    command="python",
    args=["my_mcp_server.py"]
)

# List available tools on the server
tools = agent.tool.mcp_client(
    action="list_tools",
    connection_id="my_tools"
)

# Call a tool from the MCP server
result = agent.tool.mcp_client(
    action="call_tool",
    connection_id="my_tools",
    tool_name="calculate",
    tool_args={"x": 10, "y": 20}
)

# Connect to a SSE-based server
agent.tool.mcp_client(
    action="connect",
    connection_id="web_server",
    transport="sse",
    server_url="http://localhost:8080/sse"
)

# Connect to a streamable HTTP server
agent.tool.mcp_client(
    action="connect",
    connection_id="http_server",
    transport="streamable_http",
    server_url="https://api.example.com/mcp",
    headers={"Authorization": "Bearer token"},
    timeout=60
)

# Load MCP tools into agent's registry for direct access
# ⚠️ WARNING: This loads external tools directly into the agent
agent.tool.mcp_client(
    action="load_tools",
    connection_id="my_tools"
)
# Now you can call MCP tools directly as: agent.tool.calculate(x=10, y=20)

Shell Commands

Note: shell does not work on Windows.

from strands import Agent
from strands_tools import shell

agent = Agent(tools=[shell])

# Execute a single command
result = agent.tool.shell(command="ls -la")

# Execute a sequence of commands
results = agent.tool.shell(command=["mkdir -p test_dir", "cd test_dir", "touch test.txt"])

# Execute commands with error handling
agent.tool.shell(command="risky-command", ignore_errors=True)

HTTP Requests

from strands import Agent
from strands_tools import http_request

agent = Agent(tools=[http_request])

# Make a simple GET request
response = agent.tool.http_request(
    method="GET",
    url="https://api.example.com/data"
)

# POST request with authentication
response = agent.tool.http_request(
    method="POST",
    url="https://api.example.com/resource",
    headers={"Content-Type": "application/json"},
    body=json.dumps({"key": "value"}),
    auth_type="Bearer",
    auth_token="your_token_here"
)

# Convert HTML webpages to markdown for better readability
response = agent.tool.http_request(
    method="GET",
    url="https://example.com/article",
    convert_to_markdown=True
)

Tavily Search, Extract, Crawl, and Map

from strands import Agent
from strands_tools.tavily import (
    tavily_search, tavily_extract, tavily_crawl, tavily_map
)

# For async usage, call the corresponding *_async function with await.
# Synchronous usage 
agent = Agent(tools=[tavily_search, tavily_extract, tavily_crawl, tavily_map])

# Real-time web search
result = agent.tool.tavily_search(
    query="Latest developments in renewable energy",
    search_depth="advanced",
    topic="news",
    max_results=10,
    include_raw_content=True
)

# Extract content from multiple URLs
result = agent.tool.tavily_extract(
    urls=["www.tavily.com", "www.apple.com"],
    extract_depth="advanced",
    format="markdown"
)

# Advanced crawl with instructions and filtering
result = agent.tool.tavily_crawl(
    url="www.tavily.com",
    max_depth=2,
    limit=50,
    instructions="Find all API documentation and developer guides",
    extract_depth="advanced",
    include_images=True
)

# Basic website mapping
result = agent.tool.tavily_map(url="www.tavily.com")

Exa Search and Contents

from strands import Agent
from strands_tools.exa import exa_search, exa_get_contents

agent = Agent(tools=[exa_search, exa_get_contents])

# Basic search (auto mode is default and recommended)
result = agent.tool.exa_search(
    query="Best project management software",
    text=True
)

# Company-specific search when needed
result = agent.tool.exa_search(
    query="Anthropic AI safety research",
    category="company",
    include_domains=["anthropic.com"],
    num_results=5,
    summary={"query": "key research areas and findings"}
)

# News search with date filtering
result = agent.tool.exa_search(
    query="AI regulation policy updates",
    category="news",
    start_published_date="2024-01-01T00:00:00.000Z",
    text=True
)

# Get detailed content from specific URLs
result = agent.tool.exa_get_contents(
    urls=[
        "https://example.com/blog-post",
        "https://github.com/microsoft/semantic-kernel"
    ],
    text={"maxCharacters": 5000, "includeHtmlTags": False},
    summary={
        "query": "main points and practical applications"
    },
    subpages=2,
    extras={"links": 5, "imageLinks": 2}
)

# Structured summary with JSON schema
result = agent.tool.exa_get_contents(
    urls=["https://example.com/article"],
    summary={
        "query": "main findings and recommendations",
        "schema": {
            "type": "object",
            "properties": {
                "main_points": {"type": "string", "description": "Key points from the article"},
                "recommendations": {"type": "string", "description": "Suggested actions or advice"},
                "conclusion": {"type": "string", "description": "Overall conclusion"},
                "relevance": {"type": "string", "description": "Why this matters"}
            },
            "required": ["main_points", "conclusion"]
        }
    }
)

Python Code Execution

Note: python_repl does not work on Windows.

from strands import Agent
from strands_tools import python_repl

agent = Agent(tools=[python_repl])

# Execute Python code with state persistence
result = agent.tool.python_repl(code="""
import pandas as pd

# Load and process data
data = pd.read_csv('data.csv')
processed = data.groupby('category').mean()

processed.head()
""")

Code Interpreter

from strands import Agent
from strands_tools.code_interpreter import AgentCoreCodeInterpreter

# Create the code interpreter tool
bedrock_agent_core_code_interpreter = AgentCoreCodeInterpreter(region="us-west-2")
agent = Agent(tools=[bedrock_agent_core_code_interpreter.code_interpreter])

# Create a session
agent.tool.code_interpreter({
    "action": {
        "type": "initSession",
        "description": "Data analysis session",
        "session_name": "analysis-session"
    }
})

# Execute Python code
agent.tool.code_interpreter({
    "action": {
        "type": "executeCode",
        "session_name": "analysis-session",
        "code": "print('Hello from sandbox!')",
        "language": "python"
    }
})

Swarm Intelligence

from strands import Agent
from strands_tools import swarm

agent = Agent(tools=[swarm])

# Create a collaborative swarm of agents to tackle a complex problem
result = agent.tool.swarm(
    task="Generate creative solutions for reducing plastic waste in urban areas",
    swarm_size=5,
    coordination_pattern="collaborative"
)

# Create a competitive swarm for diverse solution generation
result = agent.tool.swarm(
    task="Design an innovative product for smart home automation",
    swarm_size=3,
    coordination_pattern="competitive"
)

# Hybrid approach combining collaboration and competition
result = agent.tool.swarm(
    task="Develop marketing strategies for a new sustainable fashion brand",
    swarm_size=4,
    coordination_pattern="hybrid"
)

Use AWS

from strands import Agent
from strands_tools import use_aws

agent = Agent(tools=[use_aws])

# List S3 buckets
result = agent.tool.use_aws(
    service_name="s3",
    operation_name="list_buckets",
    parameters={},
    region="us-east-1",
    label="List all S3 buckets"
)

# Get the contents of a specific S3 bucket
result = agent.tool.use_aws(
    service_name="s3",
    operation_name="list_objects_v2",
    parameters={"Bucket": "example-bucket"},  # Replace with your actual bucket name
    region="us-east-1",
    label="List objects in a specific S3 bucket"
)

# Get the list of EC2 subnets
result = agent.tool.use_aws(
    service_name="ec2",
    operation_name="describe_subnets",
    parameters={},
    region="us-east-1",
    label="List all subnets"
)

Batch Tool

import os
import sys

from strands import Agent
from strands_tools import batch, http_request, use_aws

# Example usage of the batch with http_request and use_aws tools
agent = Agent(tools=[batch, http_request, use_aws])

result = agent.tool.batch(
    invocations=[
        {"name": "http_request", "arguments": {"method": "GET", "url": "https://api.ipify.org?format=json"}},
        {
            "name": "use_aws",
            "arguments": {
                "service_name": "s3",
                "operation_name": "list_buckets",
                "parameters": {},
                "region": "us-east-1",
                "label": "List S3 Buckets"
            }
        },
    ]
)

AgentCore Memory

from strands import Agent
from strands_tools.agent_core_memory import AgentCoreMemoryToolProvider


provider = AgentCoreMemoryToolProvider(
    memory_id="memory-123abc",  # Required
    actor_id="user-456",        # Required
    session_id="session-789",   # Required
    namespace="default",        # Required
    region="us-west-2"          # Optional, defaults to us-west-2
)

agent = Agent(tools=provider.tools)

# Create a new memory
result = agent.tool.agent_core_memory(
    action="record",
    content="I am allergic to shellfish"
)

# Search for relevant memories
result = agent.tool.agent_core_memory(
    action="retrieve",
    query="user preferences"
)

# List all memories
result = agent.tool.agent_core_memory(
    action="list"
)

# Get a specific memory by ID
result = agent.tool.agent_core_memory(
    action="get",
    memory_record_id="mr-12345"
)

Browser

from strands import Agent
from strands_tools.browser import LocalChromiumBrowser

# Create browser tool
browser = LocalChromiumBrowser()
agent = Agent(tools=[browser.browser])

# Simple navigation
result = agent.tool.browser({
    "action": {
        "type": "navigate",
        "url": "https://example.com"
    }
})

# Initialize a session first
result = agent.tool.browser({
    "action": {
        "type": "initSession",
        "session_name": "main-session",
        "description": "Web automation session"
    }
})

Handoff to User

from strands import Agent
from strands_tools import handoff_to_user

agent = Agent(tools=[handoff_to_user])

# Request user confirmation and continue
response = agent.tool.handoff_to_user(
    message="I need your approval to proceed with deleting these files. Type 'yes' to confirm.",
    breakout_of_loop=False
)

# Complete handoff to user (stops agent execution)
agent.tool.handoff_to_user(
    message="Task completed. Please review the results and take any necessary follow-up actions.",
    breakout_of_loop=True
)

A2A Client

from strands import Agent
from strands_tools.a2a_client import A2AClientToolProvider

# Initialize the A2A client provider with known agent URLs
provider = A2AClientToolProvider(known_agent_urls=["http://localhost:9000"])
agent = Agent(tools=provider.tools)

# Use natural language to interact with A2A agents
response = agent("discover available agents and send a greeting message")

# The agent will automatically use the available tools:
# - discover_agent(url) to find agents
# - list_discovered_agents() to see all discovered agents
# - send_message(message_text, target_agent_url) to communicate

Diagram

from strands import Agent
from strands_tools import diagram

agent = Agent(tools=[diagram])

# Create an AWS cloud architecture diagram
result = agent.tool.diagram(
    diagram_type="cloud",
    nodes=[
        {"id": "users", "type": "Users", "label": "End Users"},
        {"id": "cloudfront", "type": "CloudFront", "label": "CDN"},
        {"id": "s3", "type": "S3", "label": "Static Assets"},
        {"id": "api", "type": "APIGateway", "label": "API Gateway"},
        {"id": "lambda", "type": "Lambda", "label": "Backend Service"}
    ],
    edges=[
        {"from": "users", "to": "cloudfront"},
        {"from": "cloudfront", "to": "s3"},
        {"from": "users", "to": "api"},
        {"from": "api", "to": "lambda"}
    ],
    title="Web Application Architecture"
)

# Create a UML class diagram
result = agent.tool.diagram(
    diagram_type="class",
    elements=[
        {
            "name": "User",
            "attributes": ["+id: int", "-name: string", "#email: string"],
            "methods": ["+login(): bool", "+logout(): void"]
        },
        {
            "name": "Order",
            "attributes": ["+id: int", "-items: List", "-total: float"],
            "methods": ["+addItem(item): void", "+calculateTotal(): float"]
        }
    ],
    relationships=[
        {"from": "User", "to": "Order", "type": "association", "multiplicity": "1..*"}
    ],
    title="E-commerce Domain Model"
)

RSS Feed Management

from strands import Agent
from strands_tools import rss

agent = Agent(tools=[rss])

# Subscribe to a feed
result = agent.tool.rss(
    action="subscribe",
    url="https://news.example.com/rss/technology"
)

# List all subscribed feeds
feeds = agent.tool.rss(action="list")

# Read entries from a specific feed
entries = agent.tool.rss(
    action="read",
    feed_id="news_example_com_technology",
    max_entries=5,
    include_content=True
)

# Search across all feeds
search_results = agent.tool.rss(
    action="search",
    query="machine learning",
    max_entries=10
)

# Fetch feed content without subscribing
latest_news = agent.tool.rss(
    action="fetch",
    url="https://blog.example.org/feed",
    max_entries=3
)

Use Computer

from strands import Agent
from strands_tools import use_computer

agent = Agent(tools=[use_computer])

# Find mouse position
result = agent.tool.use_computer(action="mouse_position")

# Automate adding text
result = agent.tool.use_computer(action="type", text="Hello, world!", app_name="Notepad")

# Analyze current computer screen
result = agent.tool.use_computer(action="analyze_screen")

result = agent.tool.use_computer(action="open_app", app_name="Calculator")
result = agent.tool.use_computer(action="close_app", app_name="Calendar")

result = agent.tool.use_computer(
    action="hotkey",
    hotkey_str="command+ctrl+f",  # For macOS
    app_name="Chrome"
)

🌍 Environment Variables Configuration

Agents Tools provides extensive customization through environment variables. This allows you to configure tool behavior without modifying code, making it ideal for different environments (development, testing, production).

Global Environment Variables

These variables affect multiple tools:

Environment Variable	Description	Default	Affected Tools
BYPASS_TOOL_CONSENT	Bypass consent for tool invocation, set to "true" to enable	false	All tools that require consent (e.g. shell, file_write, python_repl)
STRANDS_TOOL_CONSOLE_MODE	Enable rich UI for tools, set to "enabled" to enable	disabled	All tools that have optional rich UI
AWS_REGION	Default AWS region for AWS operations	us-west-2	use_aws, retrieve, generate_image, memory, nova_reels
AWS_PROFILE	AWS profile name to use from ~/.aws/credentials	default	use_aws, retrieve
LOG_LEVEL	Logging level (DEBUG, INFO, WARNING, ERROR)	INFO	All tools

Tool-Specific Environment Variables

Calculator Tool

Environment Variable	Description	Default
CALCULATOR_MODE	Default calculation mode	evaluate
CALCULATOR_PRECISION	Number of decimal places for results	10
CALCULATOR_SCIENTIFIC	Whether to use scientific notation for numbers	False
CALCULATOR_FORCE_NUMERIC	Force numeric evaluation of symbolic expressions	False
CALCULATOR_FORCE_SCIENTIFIC_THRESHOLD	Threshold for automatic scientific notation	1e21
CALCULATOR_DERIVE_ORDER	Default order for derivatives	1
CALCULATOR_SERIES_POINT	Default point for series expansion	0
CALCULATOR_SERIES_ORDER	Default order for series expansion	5

Current Time Tool

Environment Variable	Description	Default
DEFAULT_TIMEZONE	Default timezone for current_time tool	UTC

Sleep Tool

Environment Variable	Description	Default
MAX_SLEEP_SECONDS	Maximum allowed sleep duration in seconds	300

Tavily Search, Extract, Crawl, and Map Tools

Environment Variable	Description	Default
TAVILY_API_KEY	Tavily API key (required for all Tavily functionality)	None

Visit https://www.tavily.com/ to create a free account and API key.

Exa Search and Contents Tools

Environment Variable	Description	Default
EXA_API_KEY	Exa API key (required for all Exa functionality)	None

Visit https://dashboard.exa.ai/api-keys to create a free account and API key.

Mem0 Memory Tool

The Mem0 Memory Tool supports three different backend configurations:

Mem0 Platform:
- Uses the Mem0 Platform API for memory management
- Requires a Mem0 API key
OpenSearch (Recommended for AWS environments):
- Uses OpenSearch as the vector store backend
- Requires AWS credentials and OpenSearch configuration
FAISS (Default for local development):
- Uses FAISS as the local vector store backend
- Requires faiss-cpu package for local vector storage

Environment Variable	Description	Default	Required For
MEM0_API_KEY	Mem0 Platform API key	None	Mem0 Platform
OPENSEARCH_HOST	OpenSearch Host URL	None	OpenSearch
AWS_REGION	AWS Region for OpenSearch	us-west-2	OpenSearch
DEV	Enable development mode (bypasses confirmations)	false	All modes
MEM0_LLM_PROVIDER	LLM provider for memory processing	aws_bedrock	All modes
MEM0_LLM_MODEL	LLM model for memory processing	anthropic.claude-3-5-haiku-20241022-v1:0	All modes
MEM0_LLM_TEMPERATURE	LLM temperature (0.0-2.0)	0.1	All modes
MEM0_LLM_MAX_TOKENS	LLM maximum tokens	2000	All modes
MEM0_EMBEDDER_PROVIDER	Embedder provider for vector embeddings	aws_bedrock	All modes
MEM0_EMBEDDER_MODEL	Embedder model for vector embeddings	amazon.titan-embed-text-v2:0	All modes

Note:

If MEM0_API_KEY is set, the tool will use the Mem0 Platform
If OPENSEARCH_HOST is set, the tool will use OpenSearch
If neither is set, the tool will default to FAISS (requires faiss-cpu package)
LLM configuration applies to all backend modes and allows customization of the language model used for memory processing

Memory Tool

Environment Variable	Description	Default
MEMORY_DEFAULT_MAX_RESULTS	Default maximum results for list operations	50
MEMORY_DEFAULT_MIN_SCORE	Default minimum relevance score for filtering results	0.4

Nova Reels Tool

Environment Variable	Description	Default
NOVA_REEL_DEFAULT_SEED	Default seed for video generation	0
NOVA_REEL_DEFAULT_FPS	Default frames per second for generated videos	24
NOVA_REEL_DEFAULT_DIMENSION	Default video resolution in WIDTHxHEIGHT format	1280x720
NOVA_REEL_DEFAULT_MAX_RESULTS	Default maximum number of jobs to return for list action	10

Python REPL Tool

Environment Variable	Description	Default
PYTHON_REPL_BINARY_MAX_LEN	Maximum length for binary content before truncation	100
PYTHON_REPL_INTERACTIVE	Whether to enable interactive PTY mode	None
PYTHON_REPL_RESET_STATE	Whether to reset the REPL state before execution	None

Shell Tool

Environment Variable	Description	Default
SHELL_DEFAULT_TIMEOUT	Default timeout in seconds for shell commands	900

Slack Tool

Environment Variable	Description	Default
SLACK_DEFAULT_EVENT_COUNT	Default number of events to retrieve	42
STRANDS_SLACK_AUTO_REPLY	Enable automatic replies to messages	false
STRANDS_SLACK_LISTEN_ONLY_TAG	Only process messages containing this tag	None

Speak Tool

Environment Variable	Description	Default
SPEAK_DEFAULT_STYLE	Default style for status messages	green
SPEAK_DEFAULT_MODE	Default speech mode (fast/polly)	fast
SPEAK_DEFAULT_VOICE_ID	Default Polly voice ID	Joanna
SPEAK_DEFAULT_OUTPUT_PATH	Default audio output path	speech_output.mp3
SPEAK_DEFAULT_PLAY_AUDIO	Whether to play audio by default	True

Editor Tool

Environment Variable	Description	Default
EDITOR_DIR_TREE_MAX_DEPTH	Maximum depth for directory tree visualization	2
EDITOR_DEFAULT_STYLE	Default style for output panels	default
EDITOR_DEFAULT_LANGUAGE	Default language for syntax highlighting	python

Environment Tool

Environment Variable	Description	Default
ENV_VARS_MASKED_DEFAULT	Default setting for masking sensitive values	true

Dynamic MCP Client Tool

Environment Variable	Description	Default
STRANDS_MCP_TIMEOUT	Default timeout in seconds for MCP operations	30.0

File Read Tool

Environment Variable	Description	Default
FILE_READ_RECURSIVE_DEFAULT	Default setting for recursive file searching	true
FILE_READ_CONTEXT_LINES_DEFAULT	Default number of context lines around search matches	2
FILE_READ_START_LINE_DEFAULT	Default starting line number for lines mode	0
FILE_READ_CHUNK_OFFSET_DEFAULT	Default byte offset for chunk mode	0
FILE_READ_DIFF_TYPE_DEFAULT	Default diff type for file comparisons	unified
FILE_READ_USE_GIT_DEFAULT	Default setting for using git in time machine mode	true
FILE_READ_NUM_REVISIONS_DEFAULT	Default number of revisions to show in time machine mode	5

Browser Tool

Environment Variable	Description	Default
STRANDS_DEFAULT_WAIT_TIME	Default setting for wait time with actions	1
STRANDS_BROWSER_MAX_RETRIES	Default number of retries to perform when an action fails	3
STRANDS_BROWSER_RETRY_DELAY	Default retry delay time for retry mechanisms	1
STRANDS_BROWSER_SCREENSHOTS_DIR	Default directory where screenshots will be saved	screenshots
STRANDS_BROWSER_USER_DATA_DIR	Default directory where data for reloading a browser instance is stored	~/.browser_automation
STRANDS_BROWSER_HEADLESS	Default headless setting for launching browsers	false
STRANDS_BROWSER_WIDTH	Default width of the browser	1280
STRANDS_BROWSER_HEIGHT	Default height of the browser	800

RSS Tool

Environment Variable	Description	Default
STRANDS_RSS_MAX_ENTRIES	Default setting for maximum number of entries per feed	100
STRANDS_RSS_UPDATE_INTERVAL	Default amount of time between updating rss feeds in minutes	60
STRANDS_RSS_STORAGE_PATH	Default storage path where rss feeds are stored locally	strands_rss_feeds (this may vary based on your system)

Contributing ❤️

This is a community-driven project, powered by passionate developers like you. We enthusiastically welcome contributions from everyone, regardless of experience level—your unique perspective is valuable to us!

How to Get Started?

Find your first opportunity: If you're new to the project, explore our labeled "good first issues" for beginner-friendly tasks.
Understand our workflow: Review our Contributing Guide to learn about our development setup, coding standards, and pull request process.
Make your impact: Contributions come in many forms—fixing bugs, enhancing documentation, improving performance, adding features, writing tests, or refining the user experience.
Submit your work: When you're ready, submit a well-documented pull request, and our maintainers will provide feedback to help get your changes merged.

Your questions, insights, and ideas are always welcome!

Together, we're building something meaningful that impacts real users. We look forward to collaborating with you!

License

This project is licensed under the Apache License 2.0 - see the LICENSE file for details.

Security

See CONTRIBUTING for more information.

For Tasks:

Click tags to check more tools for each tasks

automate desktop actions schedule cron jobs perform web searches generate dynamic videos store and retrieve memories

For Jobs:

ai engineer data scientist software developer automation engineer cloud architect

Alternative AI tools for tools

Similar Open Source Tools

tools

github

: 587

dingo

Dingo is a data quality evaluation tool that automatically detects data quality issues in datasets. It provides built-in rules and model evaluation methods, supports text and multimodal datasets, and offers local CLI and SDK usage. Dingo is designed for easy integration into evaluation platforms like OpenCompass.

github

: 109

GPT-Vis

GPT-Vis is a tool designed for GPTs, generative AI, and LLM projects. It provides components such as LLM Protocol for conversational interaction, LLM Component for application development, and LLM access for knowledge base and model solutions. The tool aims to facilitate rapid integration into AI applications by offering a visual protocol, built-in components, and chart recommendations for LLM.

github

: 271

litellm

LiteLLM is a tool that allows you to call all LLM APIs using the OpenAI format. This includes Bedrock, Huggingface, VertexAI, TogetherAI, Azure, OpenAI, and more. LiteLLM manages translating inputs to provider's `completion`, `embedding`, and `image_generation` endpoints, providing consistent output, and retry/fallback logic across multiple deployments. It also supports setting budgets and rate limits per project, api key, and model.

github

: 28.4k

ChatGLM3

ChatGLM3 is a conversational pretrained model jointly released by Zhipu AI and THU's KEG Lab. ChatGLM3-6B is the open-sourced model in the ChatGLM3 series. It inherits the advantages of its predecessors, such as fluent conversation and low deployment threshold. In addition, ChatGLM3-6B introduces the following features: 1. A stronger foundation model: ChatGLM3-6B's foundation model ChatGLM3-6B-Base employs more diverse training data, more sufficient training steps, and more reasonable training strategies. Evaluation on datasets from different perspectives, such as semantics, mathematics, reasoning, code, and knowledge, shows that ChatGLM3-6B-Base has the strongest performance among foundation models below 10B parameters. 2. More complete functional support: ChatGLM3-6B adopts a newly designed prompt format, which supports not only normal multi-turn dialogue, but also complex scenarios such as tool invocation (Function Call), code execution (Code Interpreter), and Agent tasks. 3. A more comprehensive open-source sequence: In addition to the dialogue model ChatGLM3-6B, the foundation model ChatGLM3-6B-Base, the long-text dialogue model ChatGLM3-6B-32K, and ChatGLM3-6B-128K, which further enhances the long-text comprehension ability, are also open-sourced. All the above weights are completely open to academic research and are also allowed for free commercial use after filling out a questionnaire.

github

: 12.8k

gollama

Gollama is a tool designed for managing Ollama models through a Text User Interface (TUI). Users can list, inspect, delete, copy, and push Ollama models, as well as link them to LM Studio. The application offers interactive model selection, sorting by various criteria, and actions using hotkeys. It provides features like sorting and filtering capabilities, displaying model metadata, model linking, copying, pushing, and more. Gollama aims to be user-friendly and useful for managing models, especially for cleaning up old models.

github

: 912

BricksLLM

BricksLLM is a cloud native AI gateway written in Go. Currently, it provides native support for OpenAI, Anthropic, Azure OpenAI and vLLM. BricksLLM aims to provide enterprise level infrastructure that can power any LLM production use cases. Here are some use cases for BricksLLM: * Set LLM usage limits for users on different pricing tiers * Track LLM usage on a per user and per organization basis * Block or redact requests containing PIIs * Improve LLM reliability with failovers, retries and caching * Distribute API keys with rate limits and cost limits for internal development/production use cases * Distribute API keys with rate limits and cost limits for students

github

: 953

gpt-load

GPT-Load is a high-performance, enterprise-grade AI API transparent proxy service designed for enterprises and developers needing to integrate multiple AI services. Built with Go, it features intelligent key management, load balancing, and comprehensive monitoring capabilities for high-concurrency production environments. The tool serves as a transparent proxy service, preserving native API formats of various AI service providers like OpenAI, Google Gemini, and Anthropic Claude. It supports dynamic configuration, distributed leader-follower deployment, and a Vue 3-based web management interface. GPT-Load is production-ready with features like dual authentication, graceful shutdown, and error recovery.

github

: 4.6k

AdaSociety

AdaSociety is a multi-agent environment designed for simulating social structures and decision-making processes. It offers built-in resources, events, and player interactions. Users can customize the environment through JSON configuration or custom Python code. The environment supports training agents using RLlib and LLM frameworks. It provides a platform for studying multi-agent systems and social dynamics.

github

: 51

YuLan-Mini

YuLan-Mini is a lightweight language model with 2.4 billion parameters that achieves performance comparable to industry-leading models despite being pre-trained on only 1.08T tokens. It excels in mathematics and code domains. The repository provides pre-training resources, including data pipeline, optimization methods, and annealing approaches. Users can pre-train their own language models, perform learning rate annealing, fine-tune the model, research training dynamics, and synthesize data. The team behind YuLan-Mini is AI Box at Renmin University of China. The code is released under the MIT License with future updates on model weights usage policies. Users are advised on potential safety concerns and ethical use of the model.

github

: 168

grps_trtllm

The grps-trtllm repository is a C++ implementation of a high-performance OpenAI LLM service, combining GRPS and TensorRT-LLM. It supports functionalities like Chat, Ai-agent, and Multi-modal. The repository offers advantages over triton-trtllm, including a complete LLM service implemented in pure C++, integrated tokenizer supporting huggingface and sentencepiece, custom HTTP functionality for OpenAI interface, support for different LLM prompt styles and result parsing styles, integration with tensorrt backend and opencv library for multi-modal LLM, and stable performance improvement compared to triton-trtllm.

github

: 122

EasyEdit

EasyEdit is a Python package for edit Large Language Models (LLM) like `GPT-J`, `Llama`, `GPT-NEO`, `GPT2`, `T5`(support models from **1B** to **65B**), the objective of which is to alter the behavior of LLMs efficiently within a specific domain without negatively impacting performance across other inputs. It is designed to be easy to use and easy to extend.

github

: 2.5k

KwaiAgents

KwaiAgents is a series of Agent-related works open-sourced by the [KwaiKEG](https://github.com/KwaiKEG) from [Kuaishou Technology](https://www.kuaishou.com/en). The open-sourced content includes: 1. **KAgentSys-Lite**: a lite version of the KAgentSys in the paper. While retaining some of the original system's functionality, KAgentSys-Lite has certain differences and limitations when compared to its full-featured counterpart, such as: (1) a more limited set of tools; (2) a lack of memory mechanisms; (3) slightly reduced performance capabilities; and (4) a different codebase, as it evolves from open-source projects like BabyAGI and Auto-GPT. Despite these modifications, KAgentSys-Lite still delivers comparable performance among numerous open-source Agent systems available. 2. **KAgentLMs**: a series of large language models with agent capabilities such as planning, reflection, and tool-use, acquired through the Meta-agent tuning proposed in the paper. 3. **KAgentInstruct**: over 200k Agent-related instructions finetuning data (partially human-edited) proposed in the paper. 4. **KAgentBench**: over 3,000 human-edited, automated evaluation data for testing Agent capabilities, with evaluation dimensions including planning, tool-use, reflection, concluding, and profiling.

github

: 995

gemini-openai-proxy

Gemini-OpenAI-Proxy is a proxy software designed to convert OpenAI API protocol calls into Google Gemini Pro protocol, allowing software using OpenAI protocol to utilize Gemini Pro models seamlessly. It provides an easy integration of Gemini Pro's powerful features without the need for complex development work.

github

: 264

token.js

Token.js is a TypeScript SDK that integrates with over 200 LLMs from 10 providers using OpenAI's format. It allows users to call LLMs, supports tools, JSON outputs, image inputs, and streaming, all running on the client side without the need for a proxy server. The tool is free and open source under the MIT license.

github

: 51

SuperAdapters

SuperAdapters is a tool designed to finetune Large Language Models (LLMs) with various adapters on different platforms. It supports models like Bloom, LLaMA, ChatGLM, Qwen, Baichuan, Mixtral, Phi, and more. Users can finetune LLMs on Windows, Linux, and Mac M1/2, handle train/test data with Terminal, File, or DataBase, and perform tasks like CausalLM and SequenceClassification. The tool provides detailed instructions on how to use different models with specific adapters for tasks like finetuning and inference. It also includes requirements for CentOS, Ubuntu, and MacOS, along with information on LLM downloads and data formats. Additionally, it offers parameters for finetuning and inference, as well as options for web and API-based inference.

github

: 293

For similar tasks

tools

github

: 587

For similar jobs

sweep

Sweep is an AI junior developer that turns bugs and feature requests into code changes. It automatically handles developer experience improvements like adding type hints and improving test coverage.

github

: 7.1k

teams-ai

The Teams AI Library is a software development kit (SDK) that helps developers create bots that can interact with Teams and Microsoft 365 applications. It is built on top of the Bot Framework SDK and simplifies the process of developing bots that interact with Teams' artificial intelligence capabilities. The SDK is available for JavaScript/TypeScript, .NET, and Python.

github

: 502

ai-guide

This guide is dedicated to Large Language Models (LLMs) that you can run on your home computer. It assumes your PC is a lower-end, non-gaming setup.

github

: 159

classifai

Supercharge WordPress Content Workflows and Engagement with Artificial Intelligence. Tap into leading cloud-based services like OpenAI, Microsoft Azure AI, Google Gemini and IBM Watson to augment your WordPress-powered websites. Publish content faster while improving SEO performance and increasing audience engagement. ClassifAI integrates Artificial Intelligence and Machine Learning technologies to lighten your workload and eliminate tedious tasks, giving you more time to create original content that matters.

github

: 620

chatbot-ui

Chatbot UI is an open-source AI chat app that allows users to create and deploy their own AI chatbots. It is easy to use and can be customized to fit any need. Chatbot UI is perfect for businesses, developers, and anyone who wants to create a chatbot.

github

: 27.7k

BricksLLM

github

: 953

uAgents

uAgents is a Python library developed by Fetch.ai that allows for the creation of autonomous AI agents. These agents can perform various tasks on a schedule or take action on various events. uAgents are easy to create and manage, and they are connected to a fast-growing network of other uAgents. They are also secure, with cryptographically secured messages and wallets.

github

: 1.3k

griptape

Griptape is a modular Python framework for building AI-powered applications that securely connect to your enterprise data and APIs. It offers developers the ability to maintain control and flexibility at every step. Griptape's core components include Structures (Agents, Pipelines, and Workflows), Tasks, Tools, Memory (Conversation Memory, Task Memory, and Meta Memory), Drivers (Prompt and Embedding Drivers, Vector Store Drivers, Image Generation Drivers, Image Query Drivers, SQL Drivers, Web Scraper Drivers, and Conversation Memory Drivers), Engines (Query Engines, Extraction Engines, Summary Engines, Image Generation Engines, and Image Query Engines), and additional components (Rulesets, Loaders, Artifacts, Chunkers, and Tokenizers). Griptape enables developers to create AI-powered applications with ease and efficiency.

github

: 2.2k