AgileLog: A Forkable Shared Log for Agents on Data Streams

2026-04-15

AI Summary

Existing streaming data systems lack efficient and secure support for AI agents, struggling to balance task isolation with write safety. This work proposes AgileLog—a forkable shared log abstraction tailored for AI agents—which introduces lightweight forking into stream processing for the first time. AgileLog features novel fork primitives that enable both logical and performance isolation. Built upon this abstraction, the Bolt system leverages efficient log replication and isolation mechanisms to significantly enhance compatibility with AI agents while ensuring security, achieving high performance with low overhead.

Technology Category

• Multiagent Systems: Agent Communication
• Machine Learning: Hardware-aware ML
• Cognitive Modeling & Cognitive Systems: Agent Architectures

Application Category

• Search and Retrieval-Augmented AI: Agentic search
• Systems and Infrastructure for Web, Mobile and WoT: Data management and stream processing for Web, mobile and wireless applications
• Security and Privacy: Data transparency and provenance

Abstract

In modern data-streaming systems, alongside traditional programs, a new type of entity has emerged that can interact with streaming data: AI agents. Unlike traditional programs, AI agents use LLM reasoning to accomplish high-level tasks specified in natural language over streaming data. Unfortunately, current streaming systems cannot fully support agents: they lack the fundamental mechanisms to avoid the performance interference caused by agentic tasks and to safely handle agentic writes. We argue that the shared log, the core abstraction underlying streaming data, must support creating forks of itself, and that such a forkable shared log serves as a great substrate for agents acting on streaming data. We propose AgileLog, a new shared log abstraction that provides novel forking primitives for agentic use cases. We design Bolt, an implementation of the AgileLog abstraction, that uses novel techniques to make forks cheap, and provide logical and performance isolation.

Problem

• AI agents
• data streams
• shared log
• performance interference
• agentic writes

Innovation

• forkable shared log
• AI agents
• streaming systems
• performance isolation
• log abstraction