the core concept is a graph that represents everything about the agents knowledge, history, behaviors, capabilities graph is made of events
behaviors react to graph changes
relationships can carry behaviors
patch & propose to edit graph
views are scoped view of graph
frames are
@yoheinakajima
-
Graph-Based Architecture for AI Agent Knowledge and Behavioral State Management
By
–
-
Architecting State Layers for Long-Running AI Agent Coordination
By
–
current agent systems coordinate through conversations and workflows. Active Graph explores what happens when agents coordinate through evolving shared state instead this proposal suggests that long-running agents need a proper state layer with: types, persistent, reactive,
-
Active Graph: An Open Source Reactive Runtime for AI Agents
By
–
i'm excited to open source Active Graph: an event-sourced reactive graph runtime for long-running, agents 🔄🧠
— Yohei (@yoheinakajima) 20 mai 2026
events/logs projects a graph. reactive behaviors react and affect the graph. fork-and-diff agent runs. no A2A, no workflows, no DAG
site: https://t.co/ufL9Ht0hYX
docs:… pic.twitter.com/zLd4i4OKYfi'm excited to open source Active Graph: an event-sourced reactive graph runtime for long-running, agents events/logs projects a graph. reactive behaviors react and affect the graph. fork-and-diff agent runs. no A2A, no workflows, no DAG site: http://
activegraph.ai
docs: -
Using Forking and Diffing for Self-Improving AI Agents
By
–
if this works, will be great for self-improving agents because of the ability to fork and diff agent runs
-
The Need for a New Continuity Layer for Long-Running AI Agents
By
–
why we need a new continuity layer for long-running agents
— Yohei (@yoheinakajima) 19 mai 2026
(claude did this video! all except the voice which was @elevenlabs) pic.twitter.com/nTXcogkGhJwhy we need a new continuity layer for long-running agents (claude did this video! all except the voice which was @elevenlabs
) -
Mapping distributed systems patterns to LLM agents
By
–
what if we mapped older distributed systems patterns (like actor models or reactive, state-driven blackboards) to LLM agents?
-
Technical assessment of stateful AI agent capabilities and memory
By
–
some good discussions and experiments around stateful agents in the replies, but seems like we’re not quite there yet, as in we’re starting to track memory and traces, but not quite agent capability as part of that state
-
Representing AI agents as state for improved persistence
By
–
maybe you can’t just tack statefulness onto an agent, you have to figure out how to represent the agent as a state
-
Technical challenges in stateful AI agents and memory management
By
–
yeah they do cool stuff around memory. starting to think stateful goes beyond that to tracking changes in the agents capability, etc which I’m not sure if many memory tools do
-
Architectural challenges in building AI agent loops
By
–
agree. kinda feels like we’re tacking on memory, tools, traces, logs into agent loops but there should be an elegant way to combine them, also relying on crons or heartbeat loops also feels hack