Strands Harness

What hackers pick instead

• Claude Agent SDKDevelopers praise it for building agents on top of Claude Code at a predictable cost. Critics agree the main caveat is Anthropic's shifting rules on using subscriptions with it.36recommend
• LangChainRecommended for easy switching between LLM providers and many integrations; critics find it bloated, overly abstract, and built for older models.32recommend
• MastraOpen-source TypeScript framework for building AI agents, praised for workflow primitives and developer experience. Common caveat: its opinionated patterns can slow you down when your project doesn't fit them.32recommend
• LangGraphRecommended for deterministic, stateful agent workflows with graph-based control, human-in-the-loop and time travel. Critics find it rigid and overly complex for simple tasks.31recommend
• DSPyPeople use it to structure LLM calls as typed programs and optimize prompts. Critics say its value depends on a good automated metric and up-front setup.29recommend

Every quote

The 27 most detailed of 28 comments. Each links to the original.

1. You can actually run a local model with strands using Ollama pretty easily

   Recommends · Jul 2026 · in “Show HN: BillAI Bass, an AI-Powered Big Mouth Billy Bass Using Strands Agents”

2. It's pretty easy to get started with and has a pretty pluggable ecosystem

   Recommends · Jun 2026 · in “Haystack: Open-Source AI Framework for Production Ready Agents, RAG”

3. it looked great in terms how everything is an event that you can extend

   Recommends · Sep 2026 · in “Strands Harness”

4. it's the most mature (IMO) that isn't specific to a model provider

   Mixed · Jun 2026 · in “Apache Burr: Build reliable AI agents and applications”

5. I’ve found it to be a very fluent and ergonomic API.

   Recommends · Nov 2025 · in “Agent design is still hard”

6. it feels disingenuous to compare token usage to a pi setup that injects a bunch of stuff into context

   Criticizes · Sep 2026 · in “Strands Harness”

7. Strands is more opinionated and higher-level, also not vendor neutral.

   Criticizes · Jun 2026 · in “Apache Burr: Build reliable AI agents and applications”

8. Technically correct inflating it? Well, that's confidence boosting.

   Criticizes · Sep 2026 · in “Strands Harness”

9. Strands documentation seems very underwhelming compared to Mastra

   Criticizes · Jan 2026 · in “Show HN: Mastra 1.0, open-source JavaScript agent framework from the Gatsby devs”

10. Supported provider list is nowhere close to pi's or opencode's

    Criticizes · Sep 2026 · in “Strands Harness”

11. I have no idea what the value prop for Strands Harness is.

    Criticizes · Sep 2026 · in “Strands Harness”

12. they typically don't provide durable execution—if the process crashes, the agent will restart from scratch

    Mixed · Mar 2026 · in “Running LangGraph, CrewAI, Google ADK with Durable Workflows”

13. For Terminal Bench 2.1, Strands harness (Fable 5) scored 69.7 while Claude Code (Fable 5) scored 61.8.

    Recommends · Sep 2026 · in “Strands Harness”

14. This looks good. Even though it's only in Python, I think its worth a try.

    Recommends · Nov 2025 · in “Agent design is still hard”

15. They open-sourced their harness this week so you can always audit it.

    Recommends · Sep 2026 · in “Strands Harness”

16. But the moment you build your own agent, you’re on your own.

    Mixed · Sep 2026 · in “Strands Harness”

17. you don't always need a frontier model for ambiguous tasks

    Recommends · Feb 2026 · in “Software 3.1? – AI Functions”

18. Pretty crazy amazon is advertising an open source repo.

    Mixed · Sep 2026 · in “Strands Harness”

19. I like that you used the Amazon Strands agent framework

    Recommends · Nov 2025 · in “Show HN: HN Insights – HN front page summaries”

20. Maybe strands I dont know.

    Mixed · Sep 2026 · in “Stripe's Knowledge AI Platform”

21. apparently they silently uploaded your entire repo with the entire git history to the cloud

    Criticizes · Sep 2026 · in “Strands Harness”

22. So far it doesn’t feel that way and sometimes they even feel at odds with each other.

    Criticizes · Jun 2026 · in “Apache Burr: Build reliable AI agents and applications”

23. odds are this just doesn't work for long-horizon tasks labs are optimizing for

    Criticizes · Sep 2026 · in “Strands Harness”

24. Deepseek beats Strands and its built on Pi so that's all I needed to know.

    Criticizes · Sep 2026 · in “Strands Harness”

25. projects like this to be noisy and less valuable over time

    Criticizes · Sep 2026 · in “Strands Harness”

26. Including Ollama support is the new token "open option"

    Criticizes · Sep 2026 · in “Strands Harness”

27. Having multiple agents was a crapshoot.

    Criticizes · Jan 2026 · in “Gas Town's Agent Patterns, Design Bottlenecks, and Vibecoding at Scale”