AgileLog: A Forkable Shared Log for Agents on Data Streams

TL;DR

AgileLog introduces a forkable shared log abstraction tailored for AI agents on data streams, enabling efficient, isolated, and safe agent interactions with streaming data.

Contribution

The paper proposes AgileLog, a novel shared log with forking primitives, and implements Bolt to support agentic tasks with low overhead and strong isolation.

Findings

Bolt makes forks cheap and efficient.

AgileLog provides logical and performance isolation for agent tasks.

Supports high-level natural language tasks over streaming data.

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.