Mirascope

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 5 most detailed of 6 comments. Each links to the original.

1. I love how it does not lock you into an agent loop. Everything's composable and you use as much or little as you need.

   Recommends · Jan 2026 · in “Show HN: Mirascope – The LLM Anti-Framework”

2. finally someone that let's me take care of the loop myself, no magic

   Recommends · Jan 2026 · in “Show HN: Mirascope – The LLM Anti-Framework”

3. how magical it feels to be in control

   Recommends · Jan 2026 · in “Show HN: Mirascope – The LLM Anti-Framework”

4. I'm glad our philosophy in how we've decided to engineer Mirascope has come through so clearly!

   Recommends · Jan 2026 · in “Show HN: Mirascope – The LLM Anti-Framework”

5. This has been one of my favorite frameworks to use for AI development.

   Recommends · Jan 2026 · in “Show HN: Mirascope – The LLM Anti-Framework”