Build a production AI agent in a few lines of Python or TypeScript
Made by strands-agents
View profile on GitHub (opens in a new tab)Strands Agents is a software development kit (SDK) for building AI agents without writing your own agent loop (the code that lets a model plan, call tools and repeat) from scratch.
In one package it covers the pieces a hand-rolled loop tends to grow into anyway — turn limits and token budgets, tool calling, MCP support, multi-agent patterns, memory and sessions, streaming, guardrails and tracing — and it is model-agnostic, with first-class support for Amazon Bedrock, Anthropic, OpenAI and Gemini plus others. A single function call ("create harness") gives a fully assembled agent with benchmarked default settings, or you can assemble the pieces yourself for more control.
You could use it to…
- Build a production AI agent in a few lines of code
- Get turn limits, tracing and guardrails without writing your own
- Swap model providers later without rewriting the agent
Can I use this?
You'll need Python or TypeScript, a terminal, and a model provider key · Setup needed
Worth knowing This is a developer toolkit for building an agent, not an end-user application on its own — someone still has to write the code that uses it and decide what the agent is allowed to do. It runs in your own process with no hosted control plane, so you are responsible for where and how it runs. Apache-2.0 licence. BuildTube has not run or verified this software.
Why it's here
Not trending this week
Last seen on the GitHub trending list on 28 September 2026. It stays on BuildTube so you can still find it.
- 8,691 people have starred it on GitHub.
Numbers checked on 6 October 2026; not refreshed since.
Behind it
See the code on GitHubBuildTube has not run or verified this project. Everything above is written from what the creator published.
Made this?