@yoheinakajima: first citation of ActiveGraph on arXiv "as a complementary runtime", plus they included a working bridge example in the…
Summary
Yohei Nakajima celebrates the first citation of ActiveGraph on arXiv, where it is referenced as a complementary runtime, and notes that a working bridge example has been included in the repo.
View Cached Full Text
Cached at: 05/26/26, 06:56 PM
first citation of ActiveGraph on arXiv “as a complementary runtime”, plus they included a working bridge example in the repo 😁 https://t.co/X1Y2TkuUba
Similar Articles
@yoheinakajima: two things ready to share from this weekend: http://learn.activegraph.ai interactive site teaching activegraph concepts…
Yohei Nakajima releases an interactive site teaching ActiveGraph concepts and AG Coder, an open-source reference coding agent built on ActiveGraph.
@yoheinakajima: i'm excited to open source Active Graph: an event-sourced reactive graph runtime for long-running, agents events/logs p…
Yohei Nakajima open-sources Active Graph, an event-sourced reactive graph runtime for long-running agents that provides persistent state, fork-and-diff agent runs, and full auditability, representing a new paradigm in agent architecture.
@yoheinakajima: babyagi has ~200 citations, but 0 papers... i just published my first paper on arXiv "The Log is the Agent: Event-Sourc…
Yohei Nakajima publishes a paper proposing ActiveGraph, a runtime where the event log is the source of truth and agents coordinate through persistent replayable state, enabling auditability, forking, and causal lineage.
@paulbettner: Active Graph is the best, most "correct" knowledge/context engine I've come across so far (and I've tried or at least r…
Yohei Nakajima published his first arXiv paper, "The Log is the Agent: Event-Sourced Reactive Graphs for Auditable, Forkable Agentic Systems", introducing a method for agents to coordinate through persistent replayable state.
@yoheinakajima: in arxiv paper #2, i tackle the last topic from paper #1: @activegraphai as an architectural affordance for self-improv…
This paper introduces Regimes, an auditable, held-out-gated improvement loop built on the ActiveGraph runtime for self-improving agents. It demonstrates modest improvements on the LongMemEval dataset by autonomously discovering prompt repairs that pass static checks, sandbox execution, and held-out validation.