Show HN: HyperFlow – A self-improving agent framework built on LangGraph
hackernews
|
|
📰 뉴스
#ai 에이전트
#langgraph
#머신러닝
#머신러닝/연구
#자기개선
#프레임워크
#오픈소스
#자체개선
#자가 개선
원문 출처: hackernews · Genesis Park에서 요약 및 분석
요약
개발자 우머(Umer)가 최근 자율 개선형 AI 에이전트 프레임워크인 'HyperFlow'를 공개했습니다. 이 시스템은 문제를 해결하는 '태스크 에이전트'와 평가 로그를 분석해 프롬프트 및 파이썬 코드 등을 직접 수정하는 '메타 에이전트'로 구성되어 수동 개입 없이 AI 스스로 성능을 향상하도록 설계되었습니다. 특히 도커 샌드박스 환경에서 새 버전을 테스트하여 가장 높은 점수를 받은 모델을 자동으로 보관하는 구조를 갖추고 있습니다. 해당 프레임워크는 LangChain과 LangGraph를 기반으로 구축되었으며, 최근 발표된 'HyperAgents' 연구 논문에서 영감을 받아 개발된 실험적 프로젝트입니다.
본문
Hi HN, I am Umer. I recently built an experimental framework called HyperFlow to explore the idea of self-improving AI agents.<p>Usually, when an agent fails a task, we developers step in to manually tweak the prompt or adjust the code logic. I wanted to see if an agent could automate its own improvement loop.</p><p>Built on LangChain and LangGraph, HyperFlow uses two agents:
- A TaskAgent that solves the domain problem.
- A MetaAgent that acts as the improver.</p><p>The MetaAgent looks at the TaskAgent's evaluation logs, rewrites the underlying Python code, tools, and prompt files, and then tests the new version in an isolated sandbox (like Docker). Over several generations, it saves the versions that achieve the highest scores to an archive.</p><p>It is highly experimental right now, but the architecture is heavily inspired by the recent HyperAgents paper (Meta Research, 2026).</p><p>I would love to hear your feedback on the architecture, your thoughts on self-referential agents, or answer any questions you might have!</p><p>Documentation: <a href="https://hyperflow.lablnet.com/" rel="nofollow">https://hyperflow.lablnet.com/</a>
GitHub: <a href="https://github.com/lablnet/HyperFlow" rel="nofollow">https://github.com/lablnet/HyperFlow</a></p>
- A TaskAgent that solves the domain problem.
- A MetaAgent that acts as the improver.</p><p>The MetaAgent looks at the TaskAgent's evaluation logs, rewrites the underlying Python code, tools, and prompt files, and then tests the new version in an isolated sandbox (like Docker). Over several generations, it saves the versions that achieve the highest scores to an archive.</p><p>It is highly experimental right now, but the architecture is heavily inspired by the recent HyperAgents paper (Meta Research, 2026).</p><p>I would love to hear your feedback on the architecture, your thoughts on self-referential agents, or answer any questions you might have!</p><p>Documentation: <a href="https://hyperflow.lablnet.com/" rel="nofollow">https://hyperflow.lablnet.com/</a>
GitHub: <a href="https://github.com/lablnet/HyperFlow" rel="nofollow">https://github.com/lablnet/HyperFlow</a></p>
Genesis Park 편집팀이 AI를 활용하여 작성한 분석입니다. 원문은 출처 링크를 통해 확인할 수 있습니다.
공유