claude

karpathy-graph

Build 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 documents", "extract entities and relations", "ground this claim", "visualize the graph", or asks how facts, sources and experiments connect. Implements the graph plane from Karpathy's Graph Engineering Systems: extract, resolve, assemble, query, evaluate. Every claim carries a source, every merge is reversible, every answer cites edge ids. Writes to the given path, or to ./.karpathy-graphs/<graph-name>/ by default, and renders an interactive HTML explorer for humans.

18 on GitHubv1.0.0MITupdated 28 days ago
/

Plugin karpathy-graph from marketplace lemon-ai-hub in Andersonlimahw/lemon-ai-hub. Commands read from the repo's manifest — 28 days ago.

What it installs

Skills (8)

  • karpathy-graph

    Build 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-build

    Stage 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-evaluate

    Stage 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-extract

    Stage 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-query

    Stage 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-resolve

    Stage 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-swarm

    Fan 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-visualize

    Render 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

Subagents (3)

  • graph-builder

    Use this agent to build a knowledge graph from a context end to end — extract typed entities and relations, resolve duplicates, assemble with provenance, validate the invariants, and render the human artifacts. Use when the user asks to build/create a knowledge graph, map a domain or codebase into a

  • graph-orchestrator

    Use this agent to coordinate several agents building one knowledge graph in parallel — partition the corpus, define the reducer and budgets before fan-out, collect GraphUpdate payloads, apply them serially with per-run provenance, resolve duplicates, and gate on the invariants. Use when the context

  • graph-querier

    Use this agent to answer multi-hop questions from an existing knowledge graph and to ground or refute claims against actual graph paths, always returning edge citations. Use when a question spans several facts, when the user asks how two things connect, or when a claim must be verified against evide

View source on GitHub

More from Andersonlimahw/lemon-ai-hub

All 173 plugins →

AI-Native Squad — Spotify-model autonomous engineering team. 12 specialized agents (Tech Lead, Backend, Frontend, Mobile, UX, UI, Product, Scrum Master, DevOps, QA, Data, Security) with orchestrated collaboration, domain-specific skills, and cross-functional workflows. Based on the AI Native Developer methodology.

18 skills · 12 agents

18

Expert git plugin containing multiple skills for advanced version control, semantic commits, and bisect automation.

26 skills

18

gh-expert

claude

Expert GitHub CLI plugin containing multiple skills for PR management, issue tracking, and GitHub workflows automation.

19 skills

18

Ready-to-paste example prompts across fourteen tracks, including decision-native recipes for senior-prompt-engineer, skills-selector, smart-dispatch, and smart-sub-agents, plus typed decisions. Ships verifiable prompt templates, combination rules, anti-patterns, and a complete A-to-Z catalog index. Use when the user asks for examples, how to use or combine skills, portable subagent routing, or how to navigate the catalog with less cognitive load.

16 skills

18

Apple Store Connect API Expert Agent and Skills. Provides comprehensive tools and knowledge for interacting with the App Store Connect API, covering domains like TestFlight, In-app purchases, Subscriptions, App management, and Provisioning.

15 skills

18

Multi-harness CLI wrapper ecosystem. Claude Code = single source of truth. Wraps any external CLI (claude, gemini, codex, opencode, agy + extensible) so the AI harness can invoke it without context bloat. Includes per-CLI wrapper skills/agents, cross-harness symlink setup, and token metrics across the whole ecosystem.

7 skills · 5 agents

18

Similar plugins

Matt Pocock's agent skills for real engineering (grilling, spec/ticket flows, TDD, code review, domain modelling and more).

39 skills

mattpocock/skills 323,108

superpowers

claudecodex

Core skills library for Claude Code: TDD, debugging, collaboration patterns, and proven techniques

15 skills · hooks

obra/superpowers 316,836

nextjs

claude

Official Next.js skills: adopt and optimize Cache Components, adopt Partial Prefetching, and verify runtime behavior against a running dev server.

6 skills

vercel/next.js 143,495

claude-mem

claudecodex

Persistent memory for Claude Code: the next session starts where the last one left off.

29 skills · 1 MCP server · hooks

thedotmack/claude-mem 116,618

Taste Skill

claudecodex

tasteskill 2.5.1: professional company websites at the figma.com and x.ai level, with one section per screen, real photographs, real product UI, effects kept for tech and gaming pages, and a real-browser checker and finish gate.

1 skill

Leonxlnx/taste-skill 114,391

AI-powered codebase understanding — analyze, visualize, and explain any project

9 skills · 10 agents · hooks

Egonex-AI/Understand-Anything 92,410

Maintain karpathy-graph?

This page updates itself from your repo. Add the badge to your README, or get it Featured to pin it above the organic results with a followed link to your site.

claude & codex plugins173 plugins