graphsub.com / wiki / stigmergic-coordination
Stigmergic Coordination for Agents
Stigmergic coordination lets agents coordinate through shared traces, signals, and environmental state rather than direct message passing alone.
Definition
Stigmergy is coordination through environmental traces. In software, agents can leave weighted signals that other agents read and reinforce.
GraphSub model
GraphSub represents coordination signals as graph state with weights, decay, scope, and relationships to tasks, tools, and outcomes.
Why it matters
Agent swarms need scalable coordination. Shared graph state can reduce brittle point-to-point messaging and produce inspectable behavior.
Code example
Agent memory and replaypython
from graphsub import Client
client = Client(base_url="https://graphsub.com")
memory = client.memory.remember(
tier="working",
content="limit breach on EUR rates book",
source="risk-run-2026-07-03",
importance=0.92,
)
trace = client.capsules.execute(
capsule="trading-control-graph",
workload="risk-recompute",
evidence="source-linked",
)
print(trace.replay_id, trace.affected_outputs)Write agent memory, launch a capsule, and inspect affected outputs.
FAQ
- Is stigmergy only for swarm robotics?
- No. It is useful anywhere autonomous actors coordinate through shared state.
- How does GraphSub expose it?
- The product surface includes stigmergic coordination primitives and live substrate visualization.