i’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: http://docs.activegraph.ai github: https://github.com/yoheinakajima/activegraph… quick start: pip install activegraph

this is an early experiment in a new paradigm for agent architecture

activegraph — Agents you can audit

Source: https://activegraph.ai/ v1.0 · open sourceMIT · Python 3.11+

Continuity for long-running agents.

BabyAGI made agent tasks persistent. activegraph makes the whole operating reality persistent — what the system believes, what it’s doing, what depends on what, what’s proven, what’s stale, what was approved, and why.

A reactive, event-sourced graph runtime that gives long-running agents a shared world to act on, fork, diff, and explain.

FromYohei Nakajima, creator of BabyAGI (2023). activegraph is the architectural answer that years of agent infrastructure work kept pointing toward.

relation_behavior

The differentiated primitive. Coordination logic lives on the edge, where the meaning is — not duplicated across every node that might emit a relevant event.

runtime.fork(at_event=…)

Branches the run. The shared prefix replays from cache. Forks don’t re-pay for LLM calls already made.

> Get launch updates

Launch notes and deep-dives on the active-graph model.

No spam. Unsubscribe anytime.

Where it fits in the agent stack

A new layer, not a competing framework.

Agent infrastructure has grown layer by layer. Each layer made the loop better. None of them give agents a world to act on.

That’s the layer activegraph fills.Workflows model computation. activegraph models the world that computation acts on. Memory remembers conversations. activegraph holds beliefs, evidence, contradictions, decisions, and their lineage.

You bring the model and the loop. activegraph gives them state.

1. Models Claude, GPT, Llama—The reasoning substrate.
2. Loops LangChain, OpenAI Agents SDK—Sequencing the model.
3. Workflows Temporal, Inngest, DBOS—Durable orchestration.
4. Statethis layer activegraph—Continuity of the world the agent acts on.
5. Memory Letta, Mem0, Zep—Conversational recall.
6. Agents Multi-agent frameworks, planners, evals—Orchestrating roles and goals.

What only activegraph does

Three primitives the loop doesn’t give you.

Try it now

The bundled Diligence pack runs against recorded fixtures.

No API key. No configuration. Byte-deterministic output. Watch a diligence run grow over 10 seconds: three companies. Claims, evidence, contradictions, risks, memos. Forkable. Inspectable. Replayable.

This isn’t the framework’s hello-world. It’s the use case the architecture was designed for.

Ships withactivegraph==1.0.0. No API key needed for the bundled fixtures.

Example · BabyAGI, rewritten

BabyAGI, as an active graph.

The original BabyAGI (Nakajima, 2023) was a while-true loop with three steps: execute the current task, summarize against the objective, generate follow-ups. State lived in a global list.

This rewrite expresses the same loop as reactive behaviors over a shared graph.The loop IS event propagation. The graph IS the state.Every step is a subscription, not a function call; the trace records every mutation and is queryable after the run.

It’s a download-and-run-it-yourself example in the OSS repo — not a bundled pack. Three behaviors:initializer→executor→task_creator, wired by events.

Three behaviors. The graph queues itself; the event log is the order; an empty follow-up list terminates the loop.