GeezerVison is showing github.com — strands-agents
Choose your starting point: a preconfigured agent with Strands harness, or your own agent built with the Harness SDK. Both are customizable.
Start with a preconfigured agent that includes tools, context management, sessions, and memory. Keep the defaults you like and change what you need.
Get started with Strands harness →
If instead you want to build your agent from the ground up, reach for the Harness SDK. Choose your models and tools, then configure how your agent manages context, sessions, and memory.
Get started with the Harness SDK →
Start with more already done. Tools, context management, sessions, and memory come configured in Strands harness.Make it yours. Keep useful defaults, replace components, or assemble your own agent with the SDK.Choose your stack. Build in Python or TypeScript with your choice of models and tools .Connect your tools. Use built-in MCP support to connect agents to tools and services.Let agents work together. Delegate tasks and coordinate multiple agents .
There’s more to Strands. Explore an ecosystem of tools, examples, and extensions for building, evaluating, and working with agents.
Project
What you'll find
Harness (Python , TypeScript )A preconfigured agent with tools, context management, sessions, and memory.
Harness SDK (Python , TypeScript )Build your own agent with your choice of models and tools.
Strands CLI Chat with Strands harness from your terminal.
Box Run agents in a sandbox that controls what they can execute, read, write, and reach on the network.
Shell A virtual shell that gives agents only the files, URLs, and credentials you allow.
Evals Measure how your agents perform.
Labs Get hands-on with experimental, state-of-the-art approaches to agentic development.
Samples Example agents to learn from and build on.
Extension Template Build and share tools, plugins, and other extensions.
MCP Server Bring Strands documentation into your AI coding assistant.
Agent SOP Turn repeatable tasks into reusable agent instructions.
Build alongside a community creating packages for Strands , including model providers (MLX ), session managers (Valkey ), and integrations (AG-UI ).
Bring your own ideas and questions to Discord or GitHub Discussions . Whether you're adding an integration, sharing an example, or improving the docs, there's a place for you to contribute .
Popular repositories
Loading
Build an agent harness and control it end-to-end. Open-source SDK for production AI agents in Python & TypeScript - any model, any cloud.
TypeScript
9.2k
1.5k
tools
tools
Public archive
A set of tools that gives agents powerful capabilities.
Python
1.3k
366
Natural language workflows that enable AI agents to perform complex, multi-step tasks with consistency and reliability.
Python
1.2k
136
Agent samples built using the Strands Agents SDK.
Python
937
466
A model-driven approach to building AI agents in just a few lines of code.
TypeScript
696
103
Run AI agents in a sandbox that restricts what they can execute, read, write, and reach on the network. Box combines OS isolation with default-deny Dogwood policies and credential injection that ke…
Rust
535
50
Repositories
Loading
Type
All
Public
Sources
Forks
Archived
Mirrors
Templates
Language
All
MDX
Python
Rust
TypeScript
Sort
Showing 10 of 14 repositories
harness-sdk
Public
Build an agent harness and control it end-to-end. Open-source SDK for production AI agents in Python & TypeScript - any model, any cloud.
strands-agents/harness-sdk's past year of commit activity
shell
Public
Give your agent a shell without giving it the keys to your machine.
strands-agents/shell's past year of commit activity
Rust
297
Apache-2.0
40
7
36
Updated Nov 12, 2026
box
Public
Run AI agents in a sandbox that restricts what they can execute, read, write, and reach on the network. Box combines OS isolation with default-deny Dogwood policies and credential injection that keeps secrets outside the agent. Written in Rust. Supports macOS on Apple silicon and Linux.
strands-agents/box's past year of commit activity
Rust
535
Apache-2.0
49
66
54
Updated Nov 12, 2026
evals
Public
A comprehensive evaluation framework for AI agents and LLM applications.
strands-agents/evals's past year of commit activity
Python
258
Apache-2.0
81
87
48
Updated Nov 11, 2026
samples
Public
Agent samples built using the Strands Agents SDK.
strands-agents/samples's past year of commit activity
tools
Public archive
A set of tools that gives agents powerful capabilities.
strands-agents/tools's past year of commit activity
Python
1,346
Apache-2.0
366
0
0
Updated Nov 4, 2026
devtools
Public
Common GitHub workflows, actions, and shared tooling used across the Strands Agents organization.
strands-agents/devtools's past year of commit activity
Python
18
Apache-2.0
24
0
8
Updated Oct 30, 2026
extension-template
Public template
Template for building and publishing Strands Agents extensions (tools, model providers, plugins, interventions, and more) in Python and TypeScript
strands-agents/extension-template's past year of commit activity
TypeScript
10
Apache-2.0
13
0
9
Updated Oct 28, 2026
agent-sop
Public
Natural language workflows that enable AI agents to perform complex, multi-step tasks with consistency and reliability.
strands-agents/agent-sop's past year of commit activity
Python
1,224
Apache-2.0
136
7
3
Updated Oct 25, 2026
strands-agents/.github's past year of commit activity