AgileLog: A Forkable Shared Log for Agents on Data Streams
This work addresses the lack of support for AI agents in streaming systems, providing a foundational mechanism for safe and efficient agentic interactions with data streams.
AgileLog introduces a forkable shared log abstraction for data-streaming systems to support AI agents, enabling cheap forks with logical and performance isolation, and demonstrating significant reduction in interference from agentic tasks.
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.