{"revision":"graphsub-cloud-2026-07-03-r23-hetzner-20261015","count":16,"pages":[{"slug":"openontology","title":"GraphSub OpenOntology","description":"GraphSub OpenOntology is an open operational ontology for real-world objects, links, actions, functions, interfaces, scenarios, permissions, provenance, and agent runtime state.","url":"https://graphsub.com/wiki/openontology","keywords":["OpenOntology","operational ontology","Palantir ontology alternative","object types","link types","action types"]},{"slug":"graph-database-for-agents","title":"Graph Database for Agent Systems","description":"GraphSub is a graph database and control substrate for AI agents that need persistent memory, tool traces, replayable outputs, and low-latency graph operations.","url":"https://graphsub.com/wiki/graph-database-for-agents","keywords":["graph database for agents","AI agent memory","agent graph database","GraphSub"]},{"slug":"agent-memory-graph","title":"Agent Memory Graph","description":"An agent memory graph organizes working, episodic, and semantic memory so autonomous systems can recall, update, and audit context over time.","url":"https://graphsub.com/wiki/agent-memory-graph","keywords":["agent memory","AI memory graph","hierarchical memory","episodic memory"]},{"slug":"operational-proof-graph","title":"Operational Proof Graph","description":"An operational proof graph records inputs, decisions, dependencies, approvals, and outputs so teams can replay and explain complex workflows.","url":"https://graphsub.com/wiki/operational-proof-graph","keywords":["operational proof","workflow replay","audit graph","agent reliability"]},{"slug":"graph-capsules","title":"GraphSub Capsules","description":"GraphSub capsules are deployable graph workflows for high-value operational problems such as agent reliability, trading controls, audit evidence, and incident response.","url":"https://graphsub.com/wiki/graph-capsules","keywords":["graph capsules","workflow capsule","GraphSub capsules","AI workflow"]},{"slug":"graphsub-vs-neo4j","title":"GraphSub vs Neo4j","description":"GraphSub and Neo4j both use graph concepts, but GraphSub is positioned around agent memory, replayable workflows, and operational proof.","url":"https://graphsub.com/wiki/graphsub-vs-neo4j","keywords":["GraphSub vs Neo4j","Neo4j alternative","agent graph database"]},{"slug":"graphsub-vs-puppygraph","title":"GraphSub vs PuppyGraph","description":"PuppyGraph focuses on zero-ETL graph analytics over existing data stores, while GraphSub focuses on live agent workflows, memory, replay, and proof capsules.","url":"https://graphsub.com/wiki/graphsub-vs-puppygraph","keywords":["GraphSub vs PuppyGraph","PuppyGraph alternative","zero ETL graph analytics"]},{"slug":"graph-database-benchmarks","title":"Graph Database Benchmarks","description":"Graph database benchmarks compare lookup latency, traversal latency, throughput, memory footprint, analytics support, and operational workflow fit.","url":"https://graphsub.com/wiki/graph-database-benchmarks","keywords":["graph database benchmarks","Neo4j benchmark","Memgraph benchmark","GraphSub benchmark"]},{"slug":"zero-etl-graph-analytics","title":"Zero-ETL Graph Analytics","description":"Zero-ETL graph analytics lets teams query warehouse or lakehouse data as a graph without first loading it into a dedicated graph database.","url":"https://graphsub.com/wiki/zero-etl-graph-analytics","keywords":["zero ETL graph","graph analytics lakehouse","PuppyGraph","warehouse graph"]},{"slug":"graph-rag","title":"GraphRAG and Source-Linked Retrieval","description":"GraphRAG combines graph structure with retrieval-augmented generation so AI systems can answer with entities, relationships, provenance, and source context.","url":"https://graphsub.com/wiki/graph-rag","keywords":["GraphRAG","graph retrieval augmented generation","source linked retrieval"]},{"slug":"hierarchical-memory","title":"Hierarchical Memory for AI Agents","description":"Hierarchical memory separates working, episodic, and semantic memory so AI agents can maintain context without losing auditability.","url":"https://graphsub.com/wiki/hierarchical-memory","keywords":["hierarchical memory","working memory AI","episodic memory AI","semantic memory AI"]},{"slug":"stigmergic-coordination","title":"Stigmergic Coordination for Agents","description":"Stigmergic coordination lets agents coordinate through shared traces, signals, and environmental state rather than direct message passing alone.","url":"https://graphsub.com/wiki/stigmergic-coordination","keywords":["stigmergic coordination","agent coordination","multi-agent systems"]},{"slug":"agent-reliability-graph","title":"Agent Reliability Graph","description":"An agent reliability graph helps teams understand failures by connecting tasks, tools, memory changes, policy gates, and eval results.","url":"https://graphsub.com/wiki/agent-reliability-graph","keywords":["agent reliability","AI agent evals","tool trace graph","agent debugging"]},{"slug":"trading-control-graph","title":"Trading Control Graph","description":"A trading control graph maps positions, books, curves, scenarios, limits, approvals, and outputs for replayable risk and P&L workflows.","url":"https://graphsub.com/wiki/trading-control-graph","keywords":["trading control graph","risk graph","P&L replay","finance graph database"]},{"slug":"regulated-evidence-graph","title":"Regulated Evidence Graph","description":"A regulated evidence graph links policies, controls, exceptions, reviewers, evidence, and approvals into auditable workflows.","url":"https://graphsub.com/wiki/regulated-evidence-graph","keywords":["regulated evidence graph","compliance graph","audit evidence","model risk graph"]},{"slug":"market-intelligence-graph","title":"Market Intelligence Graph","description":"A market intelligence graph connects news, filings, transcripts, entities, catalysts, risks, and source links into inspectable research workflows.","url":"https://graphsub.com/wiki/market-intelligence-graph","keywords":["market intelligence graph","research graph","filings graph","source linked intelligence"]}]}