External Links, Connections, and References — Deep Dive

Filed answer: which projects in the LLM Wiki ecosystem handle external links, connections, and references best, and what this vault can learn from them.


Executive Summary

Catalog scanned: 53 candidates (42 entities + 5 comparisons + 6 queries)
Analyzed in depth: 16 projects/products with explicit connection/reference handling

The LLM Wiki ecosystem divides into three families by persistent unit:

  • Artifact-first (LLM Wiki) — human-readable markdown with wikilinks
  • Memory-first (mem0, Nowledge Mem) — persistent context across sessions
  • Graph/retrieval-first (Cognee, HippoRAG, LightRAG, GraphRAG) — scalable retrieval over large corpora

The strongest external-link/connection capabilities live in the graph/retrieval-first and memory-first families, not the popular desktop/wiki products.


ProjectWhat They Do WellKey Evidence
cogneeProduction graph with computable backlinks (633 nodes, 1090 edges), 38+ sources, ECL pipeline (Extract→Contrast→Link), 14-tool MCP serverrank-ecossistema-backlinks-relacoes — winner for backlinks + relations at scale
rightmemoryTyped edges as first-class primitive; tree+graph for coding agents; multi-agent sharingrank-ecossistema-backlinks-relacoes — strongest typed-edge implementation
nowledge-memCross-tool capture (15+ hosts), explicit graph (2,042 nodes / 3,080 edges), Background Intelligence auto-links + contradicts + supersedes, SKILL.md install contractnowledge-mem — live graph traversal + maintenance ledger
graphify85.8k⭐; EXTRACTED vs INFERRED edge transparency; graphify path A B, graphify query; MCP server; 854k nodes/1.9M edges across 100 reposgraphify — edge transparency discipline
rohitg00 (LLM Wiki v2)Typed relationships (“uses”, “depends on”, “contradicts”, “supersedes”); hybrid search (BM25+vector+graph, 95.2% LongMemEval-S); memory lifecycle (confidence, supersession, forgetting)rohitg00 — most significant single extension of Karpathy pattern
atomicstrata-llm-wiki-compilerOKF canonical; L0–L3 lifecycle profiles; exports nodes.jsonl/edges.jsonl/graph.sqlite/graph.graphml; --okf validationatomicstrata-llm-wiki-compiler — standards compliance + explicit graph export
danvega-karpathy-wikiGenerates explicit backlinks.md file — portable inbound-link indexdanvega-karpathy-wiki — JVM implementation with computable backlinks
krakiun-llmwiki / geronimo-iia-llm-wikiRust binaries; replace index.md with BM25+semantic+hybrid search via MCP; geronimo has 23 MCP tools, typed DiGraph (petgraph), ACP supportkrakiun-llmwiki, geronimo-iia-llm-wiki — scaling solution

2. Retrieval/Graph Layer (Graph/RAG Family)

ProjectConnection ModelBest For
hipporagPersonalized PageRank over schemaless KG; multi-hop associative retrievalNon-obvious cross-document connections; “sense-making”
lightragDual-level (entity + theme) retrieval; incremental graph updatesEfficient contextual retrieval over changing corpora
cogneeECL pipeline → typed KG (Neo4j/Postgres) + vector DBProduction-scale multi-source synthesis

Key distinction from llm-wiki-vs-memory-and-graph-rag: LLM Wiki = artifact-first (human-readable markdown); Graph/RAG = retrieval-first (optimized for answer generation, not legibility).


3. Protocol / Integration Layer

ComponentRole in External Connections
model-context-protocol (MCP)Universal “socket” letting LLMs read/write external tools (Notion, Jira, Git, RSS, your wiki). This vault’s mcp/server.py exposes list_pages, get_page, search, graph_neighbors, graph_stats.
qmdHybrid BM25+vector search MCP (qmd-mcp) for markdown wikis past ~500 pages — local, no LLM API calls.
llm-wiki-mcpMinimal 4-tool MCP server (read/write/log/etag) for local wiki file operations.

4. Five Connection Methods (This Vault’s Synthesis)

From connection-methods — each addresses a different layer:

MethodWhat It DoesWhen AppliedAutomation
1. Karpathy LintChecks broken links, orphans, contradictionsPost-ingestManual (LLM)
2. Wyndo GuardrailsLink cap (5-8), 2+ mentions rule, forward-only linking, edit ceiling (2-5 pages)During ingestProcedural (LLM follows rules)
3. Wikilint CLIEnforces: no orphans, no broken links, no dup slugs, required sectionsPost-ingestGo CLI tool
4. OKF ToleranceConsumers MUST NOT reject for broken links, missing index, unknown frontmatterAt consumptionSpec baseline
5.5. Typed Relationships"type" target in ## Relationships; 18 types in _schema.md; validated by wikilint Check 10During ingestManual + lint check
5. Graph/RAG LayerLightRAG/HippoRAG/GraphRAG — infer new links at query timeQuery timeSoftware

This vault uses Methods 1+2+4+5.5 (Karpathy + Wyndo + OKF + Typed). Method 3 (Wikilint CLI) is implemented as scripts/wikilint.ps1.


5. Actionable Takeaways — What This Vault Can Learn

LessonSource ProjectHow to Apply Here
Explicit backlink index (backlinks.md)danvega-karpathy-wikiAdd a periodic script to emit machine-readable inbound-link list; enables graph traversal without Obsidian.
Typed edges as first-classrightmemory, rohitg00, cogneeExpand _schema.md relationship types; enforce in ## Relationships on all entity pages (already doing; deepen).
EXTRACTED vs INFERRED edge tagsgraphifyAdopt visual/tag distinction for inferred vs manual wikilinks — critical for trust.
SKILL.md install contractnowledge-memCreate a SKILL.md for this vault so agents self-install the correct schema/workflow.
Background Intelligence + maintenance ledgernowledge-memAutomate link discovery/contradiction detection, but gate writes behind a “maintenance ledger” (human review queue).
Replace index.md with search MCP at scalekrakiun-llmwiki, geronimo-iia-llm-wiki, qmdWhen wiki >100 pages, swap index.md grep for qmd-mcp or krakiun/llmwiki — constant token cost.
OKF compliance for portabilityatomicstrata-llm-wiki-compiler, truehooha-llm-wiki-skilledAdd resource field + aliases per OKF v0.2; enables cross-tool exchange.
Memory lifecycle (confidence, supersession, forgetting)rohitg00, nowledge-memImplement confidence per claim, supersedes/superseded_by frontmatter, retention decay — already in _schema.md and memory-lifecycle.
Hybrid search (BM25 + vector + graph) with RRFrohitg00 (95.2% LongMemEval-S)Wire scripts/hybrid_query_helper.py into MCP search tool; fuse three streams.

6. Gaps in This Vault vs Leaders

DimensionThis VaultLeaders
Computable backlinksEmergent from wikilinks onlyCognee (graph edges), RightMemory (typed), danvega (backlinks.md)
Typed edge traversalManual in ## RelationshipsRohitG (graph traversal queries), RightMemory (multi-agent), Cognee (14 MCP tools)
Cross-tool memorySingle vaultNowledge Mem (15+ hosts), mem0 (universal layer)
Auto link discoveryLLM during ingest onlyNowledge Mem (Background Intelligence), Graphify (EXTRACTED/INFERRED)
Scale past index.mdNot yetkrakiun/llmwiki, geronimo-iia, qmd
OKF resource + aliasesUses sources[] onlyatomicstrata, TrueHOOHA

  1. Add backlinks.md generator (script → periodic) — portable inbound index
  2. Adopt EXTRACTED/INFERRED tag convention on wikilinks — mirror Graphify’s transparency
  3. Wire qmd-mcp or krakiun/llmwiki into MCP server when page count >100
  4. Create SKILL.md at repo root for agent self-onboarding — learn from Nowledge Mem
  5. Implement confidence scoring + supersession per claim (frontmatter + inline) — per RohitG/Nowledge Mem
  6. Background Intelligence job (cron/Task Scheduler) that proposes new links/contradictions → maintenance ledger for human review
  7. External link lifecycle pipeline (implemented) — see Section 8 below.

Two complementary scripts and MCP tools are now available, following the “capture to raw, gate wiki writes behind an LLM” principle (open-knowledge-format alignment):

FeatureScriptMCP ToolPurpose
URL Capturescripts/capture-external-url.pycapture_external_urlFetches a URL, converts HTML→Markdown, writes an immutable snapshot to raw/.external-snapshots/<content_hash>.md with provenance frontmatter (source_url, source_type: web, http_status, content_hash, captured_at), then queues it for LLM ingest via raw/.ingest-queue/. Does NOT create wiki pages (Guardrail #10).
Link Freshnessscripts/check-external-links.pycheck_external_linksScans all wiki/ pages for Markdown links to https:// URLs (regex, excludes wikilinks and relative paths). Records HTTP status + staleness per URL in wiki/.external-links/ as a per-page JSON and aggregated ledger.json. Does NOT modify wiki pages (Guardrail #15).

Connection to OKF v0.2: The snapshot frontmatter fields (source_url, source_type, content_hash, http_status) align with OKF v0.2’s expanded sources: object form and trust families. External link status tracking is itself a form of provenance evidence — the link freshness ledger feeds into lifecycle status and stale_after decisions.

Full implementation plan: see docs/plans/external-linking-features-plan.md


8. Implementation in This Vault (2026-07-31)

The gap identified in §6 — “auto link discovery: LLM during ingest only” and the absence of any external capture path — is now partly closed. scripts/external_links.py implements two of the six recommendations in §7.

Capture (external_links.py capture <url>) — fetches a URL, writes an immutable snapshot to raw/external/ carrying source_url, source_type, http_status and content_hash, then queues it through the existing auto_ingest.queue_file() path so it lands in the normal ingest review flow. Re-capturing a page whose content changed writes a new snapshot and preserves the old one — the drift itself becomes auditable evidence. This is the “freshness sem sobrescrever” model: the compounding invariant applied to the outside world.

Freshness (external_links.py check) — scans every wiki page for absolute URLs and classifies each as ok / broken / redirected / changed / unreachable into wiki/.external-links/ledger.json. wikilint.ps1 Check 14 surfaces dead links as Tier 3 advisories, so link rot is visible without ever blocking a commit.

Both are exposed as MCP tools (capture_external_url, check_external_links) and neither can write to wiki/ — enforced by a test, not just by convention.

First run against this vault — 77 external URLs

StatusCountNotable
ok63
redirected7atomicmemory/llm-wiki-compileratomicstrata/llm-wiki-compiler; docs.anthropic.complatform.claude.com
broken6The Karpathy gist, the VentureBeat article, and the GenAI Unplugged post — three of this vault’s primary sources
unreachable1filtered out as loopback in a later run

This is the finding that matters. resources presents its URLs as “verified as of 2026-07-15”. Sixteen days later, six of them are dead — including the original Karpathy gist, preserved locally as raw/articles/karpathy-llm-wiki-gist.md, the origin artifact of the entire pattern this vault documents. The pages that cite them are not wrong: their evidence lives in raw/, captured while the URLs were alive. That is precisely the property Guardrail #11 was written to buy, and this is the first time it has been demonstrated rather than asserted.

The redirect from atomicmemory to atomicstrata also resolves a discrepancy: both spellings appear across research notes, and the checker settles which is canonical.

What is still open from §7

Recommendations 1 (backlinks.md), 2 (EXTRACTED/INFERRED tags), 3 (search MCP at scale) and 6 (Background Intelligence) remain unimplemented. #6 in particular stays deliberately out of reach: automated link discovery that writes pages would violate Guardrail #10, and adopting it requires the maintenance-ledger review gate that nowledge-mem pairs it with.


Sources

9. Sources Consulted

Vault Queries/Pages

External URLs (Verified)



Provenance

This query was filed on 2026-07-30 following a deep-dive request via synaptic-query. Route classifier returned ambiguous; user selected Main wiki. All claims cite vault pages via wikilinks or raw sources via repository-relative paths. External URLs are labeled as external and not presented as vault evidence.

^[wiki/queries/rank-ecossistema-backlinks-relacoes.md] ^[wiki/comparisons/connection-methods.md] ^[wiki/comparisons/llm-wiki-vs-memory-and-graph-rag.md] ^[wiki/queries/linking-connections-backlinks-smart-links.md] ^[wiki/entities/cognee.md] ^[wiki/entities/rightmemory.md] ^[wiki/entities/nowledge-mem.md] ^[wiki/entities/graphify.md] ^[wiki/entities/rohitg00.md] ^[wiki/entities/atomicstrata-llm-wiki-compiler.md] ^[wiki/entities/danvega-karpathy-wiki.md] ^[wiki/entities/krakiun-llmwiki.md] ^[wiki/entities/geronimo-iia-llm-wiki.md] ^[wiki/entities/mem0.md] ^[wiki/entities/swarmvault.md] ^[wiki/entities/qmd.md] ^[wiki/entities/llm-wiki-mcp.md] ^[wiki/concepts/hipporag.md] ^[wiki/concepts/lightrag.md] ^[wiki/concepts/model-context-protocol.md] ^[wiki/concepts/knowledge-graph.md] ^[wiki/concepts/memory-lifecycle.md] ^[raw/articles/llm-wiki-okf-comprehensive-report-2026.md] ^[raw/articles/denser-llm-wiki-analysis.md] ^[raw/articles/krakiun-llmwiki-rust.md] ^[raw/articles/geronimo-iia-llm-wiki-engine.md] ^[raw/articles/pratiyush-llm-wiki.md] ^[raw/articles/raindrop-second-brain-collection-2026.md] ^[raw/articles/nowledge-mem-docs-2026.md] ^[raw/papers/pesquisa-aprofundada-padrao-llm-wiki.md] ^[raw/papers/hipporag-neurobiologically-inspired-long-term-memory.md] ^[raw/papers/hipporag-2-from-rag-to-memory.md] ^[raw/papers/lightrag-simple-and-fast-rag.md] ^[raw/repositories/osu-nlp-group-hipporag-github.md]