The Log is the Agent: Event-Sourced Reactive Graphs for Auditable, Forkable Agentic Systems
Yohei Nakajima

TL;DR
The paper introduces ActiveGraph, a runtime system that uses an append-only event log as the source of truth, enabling deterministic replay, cheap forking, and full lineage tracing for agent systems.
Contribution
It presents a novel architecture that inverts traditional agent frameworks by making the event log the core source, enhancing observability and reproducibility.
Findings
Deterministic replay of agent runs from logs.
Efficient forking of agent states without re-execution.
Full causal lineage from goals to model outputs.
Abstract
Most agent frameworks are built around the language model: a conversation loop comes first, then tools, then rules, and finally a logging layer bolted on for observability, with state persisted as retrievable "memory." We describe ActiveGraph, a runtime that inverts this arrangement. The append-only event log is the source of truth; the working graph is a deterministic projection of that log; and behaviors--ordinary functions, classes, LLM-backed routines, or logic attached to typed edges--react to changes in the graph and emit new events. No component instructs another; coordination happens entirely through the shared graph. This single design decision yields three properties that retrieval-and-summarization memory systems do not provide: deterministic replay of any run from its log, cheap forking that branches a run at any event without re-executing the shared prefix, and end-to-end…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
