TypeScript and Python SDK giving AI agents 1000+ pre-authenticated app toolkits, per-user sessions, and a sandbox to take actions.
strands-agents/tools
A community-maintained collection of ready-made tools that Strands AI agents can call for files, shell, web search, memory, AWS and more.
- Stars
- 1,333
- Forks
- 364
- Open issues
- 145
- Last commit
- 15 hours ago
What is it?
Strands Agents Tools is a Python package of pre-built tools for agents built with the Strands Agents SDK. It covers common needs such as reading and writing files, running shell commands, making HTTP requests, searching and crawling the web, storing agent memory, calling AWS services, generating images, and automating browsers and desktops.
Each tool is a plain Python function that an agent can invoke by name, so developers can add capabilities without writing the integration code themselves. Several tools wrap third-party services such as Tavily, Exa, Mem0, Slack and TwelveLabs, and optional extras install their dependencies only when needed.
The project is experimental, and many tools grant agents powerful access such as code execution, file system access and desktop control. Many older tools are deprecated in favor of native SDK features or official vendor MCP servers, and the repository notes it will eventually be archived.
Key features
- 01Read, write and edit files, including syntax-highlighted editing
- 02Execute shell commands and run Python code snippets
- 03Make HTTP requests with authentication support
- 04Search, extract and crawl web content via Tavily and Exa
- 05Store user and agent memories with Mem0, Bedrock Knowledge Bases, Elasticsearch or MongoDB Atlas
- 06Automate browsers and desktops, plus AWS service access through a generic client
Use cases
- Giving a prototype agent file and shell access during local development
- Adding web search and page extraction to a research agent
- Persisting user preferences across agent sessions with a memory backend
- Automating browser tasks such as form filling or scraping
Quick start
- 1
Install the package from PyPI
pip install strands-agents-tools - 2
Optionally install extras for specific tools
pip install "strands-agents-tools[mem0_memory, use_browser, rss, use_computer]"
Things to know
- The tools are experimental and some grant powerful capabilities such as code execution and file system access, so they need a security review before production use.
- Many tools are marked deprecated in the README.
- Optional tools need extra dependencies and, for some, external services or API keys.
Topics
FAQ
- What is tools?
- A community-maintained collection of ready-made tools that Strands AI agents can call for files, shell, web search, memory, AWS and more. Strands Agents Tools is a Python package of pre-built tools for agents built with the Strands Agents SDK. It covers common needs such as reading and writing files, running shell commands, making HTTP requests, searching and crawling the web, storing agent memory, calling AWS services, generating images, and automating browsers and desktops.
- Is tools free to use? What license does it have?
- tools is open source under the Apache-2.0 license. Check the license terms before using it in commercial products.
- Is tools still maintained?
- Actively maintained. The last commit to tools was on Oct 21, 2026.
- What can I use tools for?
- Giving a prototype agent file and shell access during local development Adding web search and page extraction to a research agent Persisting user preferences across agent sessions with a memory backend Automating browser tasks such as form filling or scraping
- How do I install tools?
- Install the package from PyPI: pip install strands-agents-tools Optionally install extras for specific tools: pip install "strands-agents-tools[mem0_memory, use_browser, rss, use_computer]"
- Where can I get tools?
- The source code and installation instructions are on GitHub: https://github.com/strands-agents/tools
Summary generated by AI from the project's README. GitHub stats refresh daily.
Related projects
Open-source SDK for building and running AI agents in Python and TypeScript, with tools, MCP, memory, and model portability.
A personal AI agent that builds a correctable model of its user over time and helps shape long-running life and work goals into Paths.
An open-source long-term memory layer for AI agents that stores and recalls information across sessions via a Python SDK, REST API, and MCP server.
Python framework for building AI agents that use LLMs and tools, and coordinate with each other in multi-agent workflows.
Self-hostable personal AI assistant as a single Go binary, combining LLM chat, RAG knowledge bases, and agent loops for browsing, shell, and MCP tools.