Skip to content
Back to search

harness-sdk

Build an agent harness and control it end-to-end. Open-source SDK for production AI agents in Python & TypeScript - any model, any cloud.

Safety scan

A static text scan, not a guarantee. Select the badge to see what was scanned and every finding.

Checked today

Check it deeper on your machine

It has changed since its scan on 11 Nov 2026.

As a Claude Code plugin, install it and then ask Claude Code:

/plugin marketplace add keithmackay/mackayi/plugin install scanskillsafety@mackayiDo a deep scan of https://github.com/strands-agents/harness-sdk with scanskillsafety

Or from a terminal, clone it and run it:

git clone https://github.com/keithmackay/scanskillsafety-skill ~/.claude/skills/scanskillsafetynode ~/.claude/skills/scanskillsafety/cli.cjs --deep 'https://github.com/strands-agents/harness-sdk'

It checks the exact commit: every file, its packages against OSV (api.osv.dev), how it compares with this page's scan (findsafeskills.com receives the repository's address), and, if you agree, Claude reading every file with your own Claude subscription. It never runs the code.

Badge for your README
findsafeskills safety rating

Markdown

[![findsafeskills safety rating](/api/listings/strands-agents--harness-sdk/badge.svg)](/listings/strands-agents--harness-sdk)

HTML

<a href="/listings/strands-agents--harness-sdk"><img src="/api/listings/strands-agents--harness-sdk/badge.svg" alt="findsafeskills safety rating" /></a>

Install

i

Install instructions from the README

As written by the repo's author. findsafeskills has not verified these steps.

The easiest way to get started is with **[Strands harness](https://strandsagents.com/docs/user-guide/harness/)**, a fully assembled, state-of-the-art agent. A single `create_harness()` (Python) or `createHarness()` (TypeScript) call gives you an optimized agent with benchmarked defaults for the model, tools, memory, sessions, and context management — ready to take from idea to production. Follow the [harness quickstart](https://strandsagents.com/docs/user-guide/harness/quickstart/), or see the [Python Strands harness](harness-py/) and [TypeScript Strands harness](harness-ts/) packages to get started.

Python

pip install strands-harness
from strands_harness import create_harness

agent = create_harness()
agent("Find the slowest test in this repo and explain why it's slow")

TypeScript

npm install @strands-agents/harness
import { createHarness } from '@strands-agents/harness'

const agent = await createHarness()
await agent.invoke("Find the slowest test in this repo and explain why it's slow")

Start here to get a batteries-included agent, then drop down to the SDKs below when you want to own the agent loop and wire up tools, model providers, and memory yourself. The [harness configuration reference](https://strandsagents.com/docs/user-guide/harness/reference/configuration/) documents every default you can override.

The [Quickstart Guide](https://strandsagents.com/docs/user-guide/quickstart/overview/) covers configuring providers (Amazon Bedrock, Anthropic, OpenAI, Gemini, Ollama, and more).

What was scanned

The files the safety scan read, as written by the repository's author and shown as plain text. Lines with a finding are marked.

.claude-plugin/marketplace.json · Manifest · 16 lines

View this file on GitHub (read at the repository's current version: the scan did not record which commit it read)

This file has changed since it was scanned, so this is not exactly the text that was scanned, and no line is marked. The findings are listed with the safety scan above.

  1. {
  2. "name": "strands-agents",
  3. "description": "Official Strands Agents plugins for coding assistants.",
  4. "owner": {
  5. "name": "Strands Agents"
  6. },
  7. "plugins": [
  8. {
  9. "name": "strands",
  10. "source": "./.agents/skills/strands",
  11. "description": "Build, extend, evaluate, and migrate applications with Strands Agents.",
  12. "category": "development",
  13. "homepage": "https://strandsagents.com/docs/user-guide/build-with-ai/"
  14. }
  15. ]
  16. }
README.md · README · 212 lines

View this file on GitHub (read at the repository's current version: the scan did not record which commit it read)

This file has changed since it was scanned, so this is not exactly the text that was scanned, and no line is marked. The findings are listed with the safety scan above.

  1. <div align="center">
  2. <div>
  3. <a href="https://strandsagents.com">
  4. <picture>
  5. <source media="(prefers-color-scheme: dark)" srcset="https://strandsagents.com/latest/assets/wordmark-github-dark.svg">
  6. <img src="https://strandsagents.com/latest/assets/wordmark-github-light.svg" alt="Strands" width="320">
  7. </picture>
  8. </a>
  9. </div>
  10. <h1>
  11. Strands Agents
  12. </h1>
  13. <h2>
  14. A model-driven approach to building AI agents in just a few lines of code.
  15. </h2>
  16. <div align="center">
  17. <a href="https://github.com/strands-agents/harness-sdk/graphs/commit-activity"><img alt="GitHub commit activity" src="https://img.shields.io/github/commit-activity/m/strands-agents/harness-sdk"/></a>
  18. <a href="https://github.com/strands-agents/harness-sdk/issues"><img alt="GitHub open issues" src="https://img.shields.io/github/issues/strands-agents/harness-sdk"/></a>
  19. <a href="https://github.com/strands-agents/harness-sdk/pulls"><img alt="GitHub open pull requests" src="https://img.shields.io/github/issues-pr/strands-agents/harness-sdk"/></a>
  20. <a href="https://github.com/strands-agents/harness-sdk/blob/main/LICENSE.APACHE"><img alt="License" src="https://img.shields.io/github/license/strands-agents/harness-sdk"/></a>
  21. </div>
  22. <p>
  23. <a href="https://strandsagents.com/">Documentation</a>
  24. ◆ <a href="https://github.com/strands-agents/samples">Samples</a>
  25. ◆ <a href="https://github.com/strands-agents/harness-sdk/tree/main/strands-cli">CLI</a>
  26. ◆ <a href="https://github.com/strands-agents/harness-sdk/tree/main/strands-mcp">MCP Server</a>
  27. ◆ <a href="https://discord.gg/strands">Discord</a>
  28. <br>
  29. Harness (<a href="https://github.com/strands-agents/harness-sdk/tree/main/harness-py">Python</a>, <a href="https://github.com/strands-agents/harness-sdk/tree/main/harness-ts">TypeScript</a>)
  30. ◆ SDK (<a href="https://github.com/strands-agents/harness-sdk/tree/main/strands-py">Python</a>, <a href="https://github.com/strands-agents/harness-sdk/tree/main/strands-ts">TypeScript</a>)
  31. ◆ <a href="https://github.com/strands-agents/box">Box</a>
  32. ◆ <a href="https://github.com/strands-agents/shell">Shell</a>
  33. ◆ <a href="https://github.com/strands-agents/evals">Evals</a>
  34. ◆ <a href="https://github.com/strands-labs">Labs</a>
  35. </p>
  36. </div>
  37. Strands Agents is an open-source SDK for building and running AI agents in Python and TypeScript. Choose Strands when you would otherwise write your own agent loop: it runs in your process with no hosted control plane, and it covers the jobs a hand-rolled loop grows into. In one SDK you get [lifecycle controls](https://strandsagents.com/docs/user-guide/concepts/agents/agent-loop/) (turn limits, token budgets, cancellation, stop reasons), [tools](https://strandsagents.com/docs/user-guide/concepts/tools/) and [structured output](https://strandsagents.com/docs/user-guide/concepts/agents/structured-output/), [MCP](https://strandsagents.com/docs/user-guide/concepts/tools/mcp-tools/), [multi-agent patterns](https://strandsagents.com/docs/user-guide/concepts/multi-agent/multi-agent-patterns/), [memory](https://strandsagents.com/docs/user-guide/concepts/memory/overview/) and [sessions](https://strandsagents.com/docs/user-guide/concepts/agents/session-management/), [model portability](https://strandsagents.com/docs/user-guide/concepts/model-providers/), [streaming](https://strandsagents.com/docs/user-guide/concepts/streaming/), [guardrails](https://strandsagents.com/docs/user-guide/safety-security/guardrails/), [tracing](https://strandsagents.com/docs/user-guide/observability-evaluation/observability/), and [evals](https://strandsagents.com/docs/user-guide/evals-sdk/quickstart/).
  38. Using a coding agent? Install the Strands plugin for Claude Code, Codex, or Cursor.
  39. It adds framework selection, scaffolding, tool authoring, MCP server connections, web
  40. framework guides, and LangGraph migration guidance. See
  41. [Use Strands with AI coding agents](https://strandsagents.com/docs/user-guide/build-with-ai/)
  42. for install and verification steps.
  43. This monorepo contains Strands harness, the Python and TypeScript SDKs, the documentation site, and supporting packages:
  44. | Directory | Description |
  45. |-----------|-------------|
  46. | [`harness-py/`](harness-py/) | Python Strands harness: fully assembled agent via `create_harness()` ([PyPI](https://pypi.org/project/strands-harness/) · [docs](https://strandsagents.com/docs/user-guide/harness/)) |
  47. | [`harness-ts/`](harness-ts/) | TypeScript Strands harness: fully assembled agent via `createHarness()` ([npm](https://www.npmjs.com/package/@strands-agents/harness) · [docs](https://strandsagents.com/docs/user-guide/harness/)) |
  48. | [`strands-cli/`](strands-cli/) | `strands` CLI: prototype and chat with a harness agent from the terminal ([npm](https://www.npmjs.com/package/@strands-agents/cli)) |
  49. | [`strands-py/`](strands-py/) | Python SDK: agent loop, model providers, tools ([PyPI](https://pypi.org/project/strands-agents/) · [releases](https://github.com/strands-agents/harness-sdk/releases?q=python%2F&expanded=false)) |
  50. | [`strands-ts/`](strands-ts/) | TypeScript SDK: agent loop, model providers, tools ([npm](https://www.npmjs.com/package/@strands-agents/sdk) · [releases](https://github.com/strands-agents/harness-sdk/releases?q=typescript%2F&expanded=false)) |
  51. | [`strands-mcp/`](strands-mcp/) | MCP server that gives coding agents knowledge about building with Strands Agents ([PyPI](https://pypi.org/project/strands-agents-mcp-server/)) |
  52. | [`site/`](site/) | Source for the [strandsagents.com](https://strandsagents.com) documentation site (Astro/Starlight) |
  53. | [`team/`](team/) | Governance and cross-SDK process docs (tenets, decisions, PR & compatibility guidelines, and `designs/` proposals) |
  54. | [`test-infra/`](test-infra/) | CDK stack provisioning the AWS resources a subset of integration tests run against (knowledge bases, SSH sandboxes) |
  55. ## Why Strands
  56. Build an agent harness. Control it end-to-end.
  57. - **Build your way.** Any model, any cloud. Context management, execution limits, and observability built in before you write a line of config. Swap backends when you scale; your code stays the same.
  58. - **Model agnostic.** First-class support for Amazon Bedrock, Anthropic, OpenAI, and Gemini, plus [many more providers](https://strandsagents.com/docs/user-guide/concepts/model-providers/) and custom ones.
  59. - **Stay in control.** The agent loop traces every decision by default. Hooks let you intercept any step to log it, validate it, or redirect it.
  60. - **Deliver outcomes that work.** Guardrails catch mistakes before they run. Steering handlers let agents correct themselves instead of failing silently.
  61. MCP, streaming, multi-agent patterns, and structured output are all built in.
  62. ## Quick Start
  63. The easiest way to get started is with **[Strands harness](https://strandsagents.com/docs/user-guide/harness/)**, a fully assembled, state-of-the-art agent. A single `create_harness()` (Python) or `createHarness()` (TypeScript) call gives you an optimized agent with benchmarked defaults for the model, tools, memory, sessions, and context management — ready to take from idea to production. Follow the [harness quickstart](https://strandsagents.com/docs/user-guide/harness/quickstart/), or see the [Python Strands harness](harness-py/) and [TypeScript Strands harness](harness-ts/) packages to get started.
  64. ### Python
  65. ```bash
  66. pip install strands-harness
  67. ```
  68. ```python
  69. from strands_harness import create_harness
  70. agent = create_harness()
  71. agent("Find the slowest test in this repo and explain why it's slow")
  72. ```
  73. ### TypeScript
  74. ```bash
  75. npm install @strands-agents/harness
  76. ```
  77. ```typescript
  78. import { createHarness } from '@strands-agents/harness'
  79. const agent = await createHarness()
  80. await agent.invoke("Find the slowest test in this repo and explain why it's slow")
  81. ```
  82. Start here to get a batteries-included agent, then drop down to the SDKs below when you want to own the agent loop and wire up tools, model providers, and memory yourself. The [harness configuration reference](https://strandsagents.com/docs/user-guide/harness/reference/configuration/) documents every default you can override.
  83. The [Quickstart Guide](https://strandsagents.com/docs/user-guide/quickstart/overview/) covers configuring providers (Amazon Bedrock, Anthropic, OpenAI, Gemini, Ollama, and more).
  84. ## Working with the SDK
  85. The Strands Harness SDK lets you go deeper and control every part of the agent: the loop, tools, model providers, memory, sessions, and hooks. You can dive into the SDK after working with Strands harness or if you prefer building your own harness from the ground up when the assembled defaults aren't enough.
  86. ### Python
  87. Requires Python 3.10+:
  88. ```bash
  89. pip install strands-agents
  90. ```
  91. ```python
  92. from strands import Agent
  93. from strands.vended_tools import http_request
  94. agent = Agent(tools=[http_request])
  95. agent("Tell me about the Strands harness features: https://strandsagents.com/docs/user-guide/harness/index.md")
  96. ```
  97. The [Python SDK README](strands-py/) covers tools, model providers, MCP, and bidirectional streaming.
  98. ### TypeScript
  99. To build a Strands agent in TypeScript, install the SDK in a Node.js 22+ ESM project (`"type": "module"`):
  100. ```bash
  101. npm install @strands-agents/sdk
  102. ```
  103. ```typescript
  104. import { Agent } from '@strands-agents/sdk'
  105. import { httpRequest } from '@strands-agents/sdk/vended-tools/http-request'
  106. const agent = new Agent({ tools: [httpRequest] })
  107. await agent.invoke('Tell me about the Strands harness features: https://strandsagents.com/docs/user-guide/harness/index.md')
  108. ```
  109. The agent uses Amazon Bedrock by default, so configure AWS credentials or pass another model.
  110. Start with the [TypeScript quickstart](https://strandsagents.com/docs/user-guide/sdk/quickstart/typescript/)
  111. to configure a model provider, run your first agent, and add tools. Use the
  112. [TypeScript API reference](https://strandsagents.com/docs/api/typescript/) for the full
  113. SDK surface, or explore more examples in the [TypeScript SDK README](strands-ts/).
  114. ## Documentation
  115. For detailed guidance & examples, explore our documentation:
  116. - [User Guide](https://strandsagents.com/)
  117. - [Strands Harness Guide](https://strandsagents.com/docs/user-guide/harness/) ([quickstart](https://strandsagents.com/docs/user-guide/harness/quickstart/) · [configuration reference](https://strandsagents.com/docs/user-guide/harness/reference/configuration/))
  118. - [Quick Start Guide](https://strandsagents.com/docs/user-guide/quickstart/overview/)
  119. - [Agent Loop](https://strandsagents.com/docs/user-guide/concepts/agents/agent-loop/)
  120. - [Bidirectional Streaming](https://strandsagents.com/docs/user-guide/sdk/bidi/) (Python)
  121. - [Examples](https://strandsagents.com/docs/examples/)
  122. - API Reference: [Python](https://strandsagents.com/docs/api/python/strands.agent.agent/) · [TypeScript](https://strandsagents.com/docs/api/typescript/)
  123. - [Production & Deployment Guide](https://strandsagents.com/docs/user-guide/deploy/operating-agents-in-production/)
  124. The docs themselves live in this monorepo under [`site/`](site/), and doc PRs are welcome alongside code changes.
  125. ## Development
  126. Git operations (commits, branches, PRs) are done from the repo root. Each package has its own toolchain:
  127. **Python SDK** (`strands-py/`):
  128. ```bash
  129. cd strands-py
  130. pip install hatch
  131. hatch test # run unit tests
  132. hatch fmt # format & lint
  133. ```
  134. **TypeScript SDK** (`strands-ts/`):
  135. ```bash
  136. npm ci # install from repo root
  137. npm run build # build
  138. npm test # run unit tests
  139. ```
  140. **Documentation site** (`site/`):
  141. ```bash
  142. cd site
  143. npm install
  144. npm run dev # local dev server at http://localhost:4321/
  145. ```
  146. ## Contributing ❤️
  147. We welcome contributions! See our [Contributing Guide](CONTRIBUTING.md) for details on:
  148. - Reporting bugs & features
  149. - Development setup
  150. - Contributing via Pull Requests
  151. - Code of Conduct
  152. - Reporting of security issues
  153. ## Stay in touch with the team
  154. Come meet the Strands team and other users on [**Discord**](https://discord.com/invite/strands)
  155. ## License
  156. This project is licensed under the Apache License 2.0 - see the [LICENSE.APACHE](LICENSE.APACHE) file for details.
  157. ## Security
  158. See [CONTRIBUTING](CONTRIBUTING.md#security-issue-notifications) for more information.

Ratings and comments

Sign in to rate this skill.

Sign in

Free to use. If it’s helped, pass it on.