Synergy: A Next-Generation General-Purpose Agent for Open Agentic Web

2026-03-30

AI Summary

This work proposes a general-purpose agent architecture for the Open Agentic Web, addressing the limitations of current AI agents that are often confined to isolated tools or closed ecosystems and thus unable to function as social entities with identity, collaboration capabilities, and continuous evolution in open, decentralized environments. Grounded in three core principles—native openness and collaboration, identity and personality continuity, and lifelong evolvability—the architecture integrates conversational-native orchestration, repository-based workspaces, typed memory, social relationship modeling, and experience-based retrospective learning. For the first time, it unifies these dimensions within a single framework, enabling agents to sustain consistent identities, collaborate persistently across open networks, and progressively enhance performance through accumulated experience, thereby laying the foundation for large-scale coexistence of intelligent agents in open ecosystems.

Abstract

AI agents are rapidly expanding in both capability and population: they now write code, operate computers across platforms, manage cloud infrastructure, and make purchasing decisions, while open-source frameworks such as OpenClaw are putting personal agents in the hands of millions and embodied agents are spreading across smartphones, vehicles, and robots. As the internet prepares to host billions of such entities, it is shifting toward what we call Open Agentic Web, a decentralized digital ecosystem in which agents from different users, organizations, and runtimes can discover one another, negotiate task boundaries, and delegate work across open technical and social surfaces at scale. Yet most of today's agents remain isolated tools or closed-ecosystem orchestrators rather than socially integrated participants in open networks. We argue that the next generation of agents must become Agentic Citizens, defined by three requirements: Agentic-Web-Native Collaboration, participation in open collaboration networks rather than only closed internal orchestration; Agent Identity and Personhood, continuity as a social entity rather than a resettable function call; and Lifelong Evolution, improvement across task performance, communication, and collaboration over time. We present Synergy, a general-purpose agent architecture and runtime harness for persistent, collaborative, and evolving agents on Open Agentic Web, grounding collaboration in session-native orchestration, repository-backed workspaces, and social communication; identity in typed memory, notes, agenda, skills, and persistent social relationships; and evolution in an experience-centered learning mechanism that proactively recalls rewarded trajectories at inference time.

Problem

• Open Agentic Web
• Agentic Citizens
• Agent Identity
• Lifelong Evolution
• Collaborative Agents

Innovation

• Open Agentic Web
• Agentic Citizen
• Session-Native Orchestration
• Persistent Identity
• Experience-Centered Learning