karpathy-graphBuild typed, provenance-tracked knowledge graphs from any context — documents, codebases, incidents, research — so one or many AI agents share durable memory instead of copying transcripts. Use when the user says "build a knowledge graph", "criar grafo", "map this codebase/domain", "graph these docu
karpathy-graph-buildStage 3 of the karpathy-graph pipeline, and the end-to-end entry point. Create a graph, assemble validated writes with provenance, and produce the machine and human artifacts. Use when the user asks to build or create a knowledge graph from a context, to add facts to an existing graph, or when runni
karpathy-graph-evaluateStage 5 of the karpathy-graph pipeline. Score graph quality across extraction, resolution, structure, query, and operations, and run a ratchet loop that keeps only changes which improve the metric. Use when the user asks how good the graph is, wants to tune extraction prompts or the ontology, asks t
karpathy-graph-extractStage 1 of the karpathy-graph pipeline. Turn unstructured context — documents, source files, incident timelines, chat logs, research notes — into typed entities and subject-predicate-object relations that fit the graph ontology. Use when the user asks to extract entities, pull relations out of docum
karpathy-graph-queryStage 4 of the karpathy-graph pipeline. Answer multi-hop questions from a knowledge graph by retrieving a bounded subgraph with edge citations, and ground or refute claims against actual graph paths. Use when the user asks a question that spans several facts, asks how two things connect, asks to ver
karpathy-graph-resolveStage 2 of the karpathy-graph pipeline. Collapse duplicate surface forms into canonical entities using context as evidence, reversibly and with a recorded rationale. Use after extraction when the graph contains aliases, abbreviations, or spelling variants of the same thing, when isolated-node count
karpathy-graph-swarmFan the karpathy-graph pipeline out across parallel agents that share the graph as memory instead of copying transcripts. Use when the context is too large for one pass — hundreds of documents, a whole codebase, many independent hypotheses — or when the user asks to parallelize graph construction, r
karpathy-graph-visualizeRender a karpathy-graph for humans — an interactive HTML explorer, a Mermaid diagram for docs and PRs, and a health report — then explain what the picture actually shows. Use when the user asks to see, visualize, draw, or open the graph, wants a diagram for documentation, or asks what the graph look