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 is a Python and TypeScript SDK for building AI agents that connects to multiple model backends, including Amazon Bedrock (where Claude 4 Sonnet on us-west-2 serves as the default model), Anthropic's API directly, Ollama, LiteLLM, OpenAI, Gemini, Llama, and others. The SDK ships an agent loop, a decorator-based tool system, native MCP client support for attaching external MCP servers, a hot-reload mechanism that watches a local tools directory for changes, and WebAssembly bindings that let TypeScript agents call Python tools via a strands-wasm layer. Developers define tools with a single @tool decorator and docstring, which the model reads to understand the tool's purpose. Multi-agent orchestration and streaming responses are included out of the box, and the SDK emits OpenTelemetry traces for observability. The repository is structured as a monorepo containing the Python package, TypeScript package, a developer CLI called strandly, and the documentation site. Python developers, TypeScript developers, and teams deploying autonomous workflows in production are the primary audience.
- ✓Open-source license (Apache-2.0)
- ✓Actively maintained (<30d)
- ✓Healthy fork ratio
- ✓Clear description
- ✓Topics declared
- ✓Mature repo (>1y old)
git clone https://github.com/strands-agents/harness-sdk && cp harness-sdk/*.md ~/.claude/agents/9 items in this repository
Assess a published or in-progress documentation page for quality, accuracy, and voice compliance. Use before rewriting a page, during periodic health checks, when community signals point to confusion, or when comparing against competitor docs. Also triggers on "audit this page", "assess the docs", "what's wrong with this page", "check docs quality", "review this doc page".
Identify documentation gaps and prioritize the docs backlog. Use when planning a docs improvement sprint, after signals surface repeated friction, when new SDK features ship without docs, or for periodic health assessment. Also triggers on "plan docs work", "what docs need writing", "prioritize the backlog", "docs health check", "what should we document next".
Review documentation drafts for voice consistency, structure, and terminology before PR submission. Use after completing a draft, when checking if docs are ready to ship, or automatically after docs-writer produces output. Also triggers on "review this draft", "check my docs", "is this ready to ship", "review before merging".
Draft or rewrite Strands Agents documentation pages. Use when writing new doc pages, rewriting pages that failed audit, drafting sections for existing pages, or writing blog posts and release notes about Strands. Also triggers on "write a doc", "draft a page", "rewrite the quickstart", "add a tutorial for X", "document this feature".
Local preview of the strands-agents/devtools `/strands review` agent. Body is the upstream Task Reviewer SOP verbatim — do not paraphrase. Use when the user types `/strands-review`, asks for a "strands review" of a PR, or wants to anticipate what the remote `/strands review` GitHub Action will flag. Findings are close but not identical to the remote agent. Strongly prefer running this skill in a fresh-context subagent rather than inline — the SOP is long and reviewer judgment is more reliable when it isn't entangled with the parent conversation's prior context.
Creates a GitHub pull request using the gh CLI. Use when the user asks to create, open, or submit a PR on GitHub.
Fetches PR review feedback and inline comments, categorizes them, and presents options to the user. Use when the user asks to get, read, address, or fix review comments on a pull request.
Generates pull request titles and descriptions. Use when the user asks to create, open, write, draft, or generate a PR, pull request, or merge request description.
Runs the local equivalent of the CI merge gate before you push. Detects which areas (Python, TypeScript, docs) your changes touch, auto-fixes what it can, then runs only those checks. Use when the user asks to run pre-push checks, get push-ready, verify changes before pushing or opening a PR, "make sure CI will pass", or check lint/tests/types locally.
Subagents overview
What people ask about harness-sdk
What is strands-agents/harness-sdk?
+
strands-agents/harness-sdk is subagents for the Claude AI ecosystem. Build an agent harness and control it end-to-end. Open-source SDK for production AI agents in Python & TypeScript - any model, any cloud. It has 7.2k GitHub stars and its last recorded update is dated 2026-09-11.
How do I install harness-sdk?
+
You can install harness-sdk by cloning the repository (https://github.com/strands-agents/harness-sdk) or following the README instructions on GitHub. ClaudeWave also provides quick install blocks on this page.
Is strands-agents/harness-sdk safe to use?
+
Our security agent has analyzed strands-agents/harness-sdk and assigned a Trust Score of 100/100 (tier: Verified). See the full breakdown of passed checks and flags on this page.
Who maintains strands-agents/harness-sdk?
+
strands-agents/harness-sdk is maintained by strands-agents. The last recorded GitHub activity is dated 2026-09-11, with 729 open issues.
Are there alternatives to harness-sdk?
+
Yes. On ClaudeWave you can browse similar subagents at /categories/agents, sorted by popularity or recent activity.
Deploy harness-sdk to your cloud
Ship this repo to production in minutes. Each platform spins up its own environment with editable env vars.
Maintain this repo? Add a badge to your README
Drop the badge into your GitHub README to show it's tracked on ClaudeWave. Each badge links back to this page and reflects the live Trust Score.
[](https://claudewave.com/repo/strands-agents-harness-sdk)<a href="https://claudewave.com/repo/strands-agents-harness-sdk"><img src="https://claudewave.com/api/badge/strands-agents-harness-sdk" alt="Featured on ClaudeWave: strands-agents/harness-sdk" width="320" height="64" /></a>More Subagents
The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.
The agent that grows with you
Java 面试 & 后端通用面试指南,覆盖计算机基础、数据库、分布式、高并发、系统设计与 AI 应用开发
Build Agentic workflows, RAG pipelines, with rich AI model and tool support on one collaborative workspace. Deploy on cloud, VPC, or self-hosted, so teams move from prototype to production without rebuilding the stack.
The agent engineering platform.
Makes your AI agent think like the laziest senior dev in the room. The best code is the code you never wrote.