claude

rete-graph

Skills to build and publish .rete knowledge graphs, plus the rete MCP server: SPARQL + SHACL over 60+ public datasets (and any .rete URL), entity search, dataset cards, and media preview/embedding tools.

11 on GitHubby Carlos Vivar Riosv0.3.0Apache-2.0updated today
/

Plugin rete-graph from marketplace rete in caviri/rete. Commands read from the repo's manifest — today.

What it installs

Skills (7)

  • dataset-download

    Acquire and organize a NEW raw dataset under ./data/<name>/ before it becomes a .rete — investigate a source (download page, API, S3/Tigris bucket) to find ALL of its data, scaffold the standard folder layout (raw/ + scripts/ + README + checksums), download robustly (reproducible + resumable + paral

  • rete-catalog

    Find, inspect, and open the published .rete datasets from the rete catalog — 60+ public knowledge graphs on range-readable hosting. Use when a task needs an existing dataset (query it, download it, federate it, wire it into an app) rather than building a new one.

  • rete-clients

    Set up a rete client in a NEW project — Python, Pyodide/JupyterLite, JavaScript/Node, browser script-tag, your own wasm build, or Rust. Use when wiring .rete querying into an application, notebook, or script; covers install, a verified first query, and the per-runtime gotchas.

  • rete-from-graph

    Build a queryable `.rete` file from ANY graph-based data source — an RDF dump (.nt/.nq/.ttl/.rdf/.owl), a SPARQL endpoint, a Wikibase, an OWL ontology, GeoJSON, tabular/CSV, a GBIF Darwin-Core archive, a TEI corpus, or a JSON API. Use whenever the task is "turn this dataset/graph/ontology/endpoint i

  • rete-local-query

    Query a LOCAL .rete file efficiently — the lazy range-read path that opens a multi-GB file without loading it whole, which CLI commands are lazy vs read-whole, the tuning knobs (RETE_BLOCK_KB, RETE_LOCAL_LAZY_ABOVE_MB, the 256 MiB block-cache cap), how to preview a query's byte/RAM cost (rete cost /

  • rete-publish

    Publish a built `.rete` dataset to the rete playground: generate optional Parquet/DuckDB/SQLite companions, upload files to Cloudflare R2, register the dataset in the catalog, and verify the public Range/CORS contract. Use after rete-from-graph has produced and verified a `.rete` whenever the task i

  • rete-sparql

    Write correct SPARQL for .rete graphs — the supported SPARQL 1.1 surface, rete's extensions (OWL 2 QL reasoning, RDF-star, SERVICE federation, text index), result formats, and the recurring gotchas that silently return 0 rows. Use whenever authoring or debugging a SPARQL query against a .rete file,

MCP servers (1)

  • rete-graphs

    connects to: https://katospiegel-rete.hf.space/mcp/

View source on GitHub caviri.github.io

Similar plugins

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

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

9 skills · 10 agents · hooks

Egonex-AI/Understand-Anything 92,410

Knowledge graph construction — entity extraction, relation mapping, and pathfinder graph traversal

2 skills · 1 command · 1 agent

ruvnet/ruflo 81,589

gitnexus

claudecodex

Code intelligence powered by a knowledge graph. Provides execution flow tracing, blast radius analysis, and augmented search across your codebase.

12 skills · 1 MCP server · hooks

abhigyanpatwari/GitNexus 48,482

A Codex-native bridge to Basic Memory for durable engineering context, decisions, and resumable checkpoints.

8 skills · 1 MCP server · hooks

basicmachines-co/basic-memory 4,562

Domain-specific expert agents for validation, knowledge-graph, and other specialized tasks

10 agents

davepoon/buildwithclaude 3,741

Maintain rete-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 pluginslisted