GraphSub OpenOntology is an open operational ontology for real-world objects, links, actions, functions, interfaces, scenarios, permissions, provenance, and agent runtime state.
graphsub.com / wiki
GraphSub Wiki
A crawlable encyclopedia for graph databases built for AI agents, operational proof, memory graphs, GraphRAG, and real-world capsules.
GraphSub combines low-latency graph operations with agent memory, replayable workflows, source-linked outputs, and deployable capsules.
Code example
Capsule planner routesbash
curl 'https://graphsub.com/api/plan?capsule=trading-control-graph&target=enterprise-team&workload=risk-recompute' \
| jq '.execution_preview | {capsule, buyer, workflow, artifacts}'
curl -X POST 'https://graphsub.com/api/execute?capsule=regulated-evidence-graph&workload=audit-evidence' \
| jq '.execution.replay'
curl 'https://graphsub.com/api/examples'Use the live Modal routes to build and execute a capsule plan.
GraphSub is a graph database and control substrate for AI agents that need persistent memory, tool traces, replayable outputs, and low-latency graph operations.
An agent memory graph organizes working, episodic, and semantic memory so autonomous systems can recall, update, and audit context over time.
An operational proof graph records inputs, decisions, dependencies, approvals, and outputs so teams can replay and explain complex workflows.
GraphSub capsules are deployable graph workflows for high-value operational problems such as agent reliability, trading controls, audit evidence, and incident response.
GraphSub and Neo4j both use graph concepts, but GraphSub is positioned around agent memory, replayable workflows, and operational proof.
PuppyGraph focuses on zero-ETL graph analytics over existing data stores, while GraphSub focuses on live agent workflows, memory, replay, and proof capsules.
Graph database benchmarks compare lookup latency, traversal latency, throughput, memory footprint, analytics support, and operational workflow fit.
Zero-ETL graph analytics lets teams query warehouse or lakehouse data as a graph without first loading it into a dedicated graph database.
GraphRAG combines graph structure with retrieval-augmented generation so AI systems can answer with entities, relationships, provenance, and source context.
Hierarchical memory separates working, episodic, and semantic memory so AI agents can maintain context without losing auditability.
Stigmergic coordination lets agents coordinate through shared traces, signals, and environmental state rather than direct message passing alone.
An agent reliability graph helps teams understand failures by connecting tasks, tools, memory changes, policy gates, and eval results.
A trading control graph maps positions, books, curves, scenarios, limits, approvals, and outputs for replayable risk and P&L workflows.
A regulated evidence graph links policies, controls, exceptions, reviewers, evidence, and approvals into auditable workflows.
A market intelligence graph connects news, filings, transcripts, entities, catalysts, risks, and source links into inspectable research workflows.