OpenAgent: A Modular Framework for Autonomous Multi-Tool Agent Orchestration with Memory-Enabled Planning

Zenodo (CERN European Organization for Nuclear Research) 2026 Open access

Read full text
Authors: Xinyu Zhang
DOI: 10.5281/zenodo.18295640
Cited by: 0

Abstract

OpenAgent v0.1.0 A modular Python framework for building autonomous LLM agents with memory-enabled multi-step execution. Key Features Hierarchical agent architecture (Manus, Planning, ReAct, SWE agents) Memory-enabled planning with artifact tracking Extensible tool framework with 8+ built-in tools Graceful degradation with LLM-based fallback Documentation Full paper: paper.md Architecture diagram: figures/architecture.png Citation See CITATION.cff for citation information

Fields of Study & Subjects

AI-based Problem Solving and Planning Artificial Intelligence Applications Multi-Agent Systems and Negotiation

Publication details

Journal / source
Zenodo (CERN European Organization for Nuclear Research)
Publication date
19 January 2026