Follow-up to the strands-mcp history merge, covering everything the merge itself didn't: CI gating, packaging/meta reconciliation, and doc/link updates. CI merge gate: - Wire strands-mcp into ci.yml with an `mcp` path filter, detect-changes output, gate job, and ci-gate needs/allowed-skips — mirroring how Python, TypeScript, and docs are gated. The gate job calls mcp-test-lint.yml directly (the Python pattern); calling the mcp-pr-and-push.yml wrapper would collide on the CI-<pr> concurrency group and cancel itself before running. - mcp-test-lint.yml now runs the unit suite (hatch run test) in addition to lint, so the gate — and the pre-publish gate in mcp-pypi-publish-on-release.yml that reuses it — no longer passes without tests ever running. Renamed the workflow to "MCP: Test and Lint" to match. - Bump pinned actions across all MCP workflows to the monorepo standard (checkout@v7, setup-python@v6, upload-artifact@v7, download-artifact@v8) and drop the standalone pull_request trigger from mcp-pr-and-push.yml (PR coverage now comes from the ci.yml gate; leaving it would double-run and collide on the CI-<pr> concurrency group). Packaging and meta: - Add license-files = ["LICENSE", "NOTICE"] to strands-mcp/pyproject.toml so both are bundled into the published wheel (the #2351 fix, latent in the MCP package). LICENSE/NOTICE stay package-local for this reason. - Repoint the pyproject Homepage/Bug Tracker URLs from the archived mcp-server repo to harness-sdk (Bug Tracker to /issues). - Delete strands-mcp/CODE_OF_CONDUCT.md (byte-identical to root) and strands-mcp/CONTRIBUTING.md (pre-merge boilerplate superseded by the root monorepo-aware CONTRIBUTING); add an MCP row to the root CONTRIBUTING table. - Add missing trailing newlines to strands-mcp/.gitignore, strands-mcp/.pre-commit-config.yaml, and mcp-pypi-publish-on-release.yml. Docs and links: - Repoint every strands-agents/mcp-server repo reference to the MCP server's new home at harness-sdk/tree/main/strands-mcp: the quickstart and build-with-ai doc pages, the "MCP Server" ecosystem-nav link in the root, strands-py, strands-ts, and strands-mcp READMEs, and strands-mcp/README.md's badges, clone instructions, and example prompt. Also fix strands-mcp's stale sdk-python nav link. The strands-agents-mcp-server package name and install commands are unchanged; the historical introducing-strands-agents blog post is intentionally left frozen.
6.9 KiB
Strands Agents
A model-driven approach to building AI agents in just a few lines of code.
Documentation ◆ Samples ◆ Tools ◆ Agent Builder ◆ MCP Server
Strands Agents is a simple yet powerful SDK that takes a model-driven approach to building and running AI agents. From simple conversational assistants to complex autonomous workflows, from local development to production deployment, Strands Agents scales with your needs.
This monorepo contains the Python SDK, TypeScript SDK, documentation site, and supporting packages:
| Directory | Description |
|---|---|
strands-py/ |
Python SDK: agent loop, model providers, tools (PyPI · releases) |
strands-ts/ |
TypeScript SDK: agent loop, model providers, tools (npm · releases) |
strandly/ |
Developer CLI for local builds and workspace tooling |
site/ |
Source for the strandsagents.com documentation site (Astro/Starlight) |
team/ |
Governance and cross-SDK process docs (tenets, decisions, PR & compatibility guidelines, and designs/ proposals) |
Why Strands
Build an agent harness. Control it end-to-end.
- 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.
- Model agnostic. First-class support for Amazon Bedrock, Anthropic, OpenAI, and Gemini, plus many more providers and custom ones.
- 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.
- Deliver outcomes that work. Guardrails catch mistakes before they run. Steering handlers let agents correct themselves instead of failing silently.
MCP, streaming, multi-agent patterns, and structured output are all built in.
Quick Start
Both SDKs default to the Amazon Bedrock model provider, so you'll need AWS credentials configured and model access enabled for Claude Sonnet. The Quickstart Guide covers configuring other providers (Anthropic, OpenAI, Gemini, Ollama, and more).
Python
Requires Python 3.10+:
pip install strands-agents strands-agents-tools
from strands import Agent
from strands_tools import calculator
agent = Agent(tools=[calculator])
agent("What is the square root of 1764")
The Python SDK README covers tools, model providers, MCP, and bidirectional streaming.
TypeScript
Requires Node.js 20+:
npm install @strands-agents/sdk
import { Agent } from '@strands-agents/sdk'
const agent = new Agent()
const result = await agent.invoke('What is the square root of 1764?')
console.log(result)
More in the TypeScript SDK README, including Zod-typed tools, structured output, and multi-agent patterns.
Documentation
For detailed guidance & examples, explore our documentation:
- User Guide
- Quick Start Guide
- Agent Loop
- Examples
- API Reference: Python · TypeScript
- Production & Deployment Guide
The docs themselves live in this monorepo under site/, and doc PRs are welcome alongside code changes.
Development
Git operations (commits, branches, PRs) are done from the repo root. Each package has its own toolchain:
Python SDK (strands-py/):
cd strands-py
pip install hatch
hatch test # run unit tests
hatch fmt # format & lint
TypeScript SDK (strands-ts/):
npm ci # install from repo root
npm run build # build
npm test # run unit tests
Documentation site (site/):
cd site
npm install
npm run dev # local dev server at http://localhost:4321/
Contributing ❤️
We welcome contributions! See our Contributing Guide for details on:
- Reporting bugs & features
- Development setup
- Contributing via Pull Requests
- Code of Conduct
- Reporting of security issues
Stay in touch with the team
Come meet the Strands team and other users on Discord
License
This project is licensed under the Apache License 2.0 - see the LICENSE.APACHE file for details.
Security
See CONTRIBUTING for more information.