Builder of 400+ production agents shares a decision tree for agent frameworks
MaryamMiradi · x · 2026-09-14
Maryam Miradi, who claims 400+ production AI agents built, argues LangGraph, Google ADK, CrewAI and PydanticAI aren't competitors but Python libraries with different abstractions. Pick by project: LangGraph for stateful, production-grade pipelines with loops and branching (she demos a real-time €5.1B flower supply chain agent); Google ADK offers five composable agent types that snap together like Lego. Her advice: ask what you're building first.
More from coding & agent
- Build a daily tweet-performance analyst bot with one Grok prompt and the X API — AIandDesign · 2026-09-14
- Handy tip: build a Grok bot that reviews your daily X posts and explains what worked — AIandDesign · 2026-09-14
- A marketing engineer's framework for agent context management and a second brain — blaizedsouza · 2026-09-14
- Hamel Husain Names Amp and Cognition as Best Multi-Agent Harnesses Outside Labs — HamelHusain · 2026-09-14
- OpenViking: open-source context database cuts agent input tokens by up to 91% — blaizedsouza · 2026-09-14
- Astrable: Open-Source Codex Plugin Pairs GPT-6 Astra with Claude Fable 5.1 — daniel_mac8 · 2026-09-14