Apache Burr

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 15 most detailed of 16 comments. Each links to the original.

1. I have enjoyed using this framework in my personal and work projects, having a reliable stateful workflow for AI models while getting free observability.

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

2. Burr has agent cookbooks to get started with this, and it can handle multi-machine workflows.

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

3. Burr just helps you, the engineer, to really control the primitives.

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

4. disposable garbage generated by Claude code that doesn't even try to work without JavaScript

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

5. I was not expecting an apache foundation project to have gradient words on the landing page.

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

6. Didn't bother reading more after seeing the vibeslopped landing page

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

7. It hits every AI generated landing page trope possible.

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

8. oh god, the vibecoded homepage, I instantly closed that

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

9. Burr (thanks for educating about that piece of tech) could be a good N-one

   Recommends · Jul 2026 · in “Show HN: Kastor – Terraform-style specs for AI agents”

10. I want something like that, but that uses codex/claude code as agents

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

11. it's actually a good target to support the codegen for

    Recommends · Jul 2026 · in “Show HN: Kastor – Terraform-style specs for AI agents”

12. I use Apache Burr but it's not as good as LangChain.

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

13. the handful of links I've tried to dig into have all linked to the wrong place/are invalid

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

14. This is a very naive version of what reliable AI agents are all about.

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

15. why would they pick a platform that is not known?

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