{
  "schema_version": "1.1",
  "id": "s9:https://github.com/nashsu/llm_wiki",
  "slug": "llm-wiki-1dqmknq",
  "url": "https://feed7.dev/p/llm-wiki-1dqmknq",
  "title": "nashsu/llm_wiki",
  "why_included": "LLM Wiki compiles source files into a persistent, traceable wiki that agents can query through local APIs, MCP, and skills, reducing repeated retrieval and re-analysis.",
  "summary": "LLM Wiki turns imported material into a persistent three-layer system: **raw sources → generated wiki → schema**. Its two-call ingest separates analysis from page generation, records source links, skips unchanged files with a SHA-256 cache, and recovers a persistent queue after restarts.",
  "practical_implication": "For agent context, treat the maintained wiki as a reusable compiled layer rather than rebuilding answers from raw documents every turn. The local API, **MCP server**, and agent skill expose hybrid search, file reads, graph traversal, and rescans to Claude Code or Codex.",
  "agent_context": "LLM Wiki turns imported material into a persistent three-layer system: **raw sources → generated wiki → schema**. Its two-call ingest separates analysis from page generation, records source links, skips unchanged files with a SHA-256 cache, and recovers a persistent queue after restarts.\n\nFor agent context, treat the maintained wiki as a reusable compiled layer rather than rebuilding answers from raw documents every turn. The local API, **MCP server**, and agent skill expose hybrid search, file reads, graph traversal, and rescans to Claude Code or Codex.\n\nVector retrieval is optional and reportedly raises recall from **58.2% to 71.4%**, but the material does not describe the benchmark dataset or evaluation method. Generated pages can still distort sources, so source-only answering, traceability, linting, and human review remain important.",
  "source": {
    "name": "GitHub",
    "url": "https://github.com/nashsu/llm_wiki",
    "published_at": null
  },
  "source_class": "tool",
  "content_type": "GitHub Repo",
  "layer": "context",
  "domains": [
    "research",
    "data"
  ],
  "topics": [
    "retrieval",
    "context-engineering",
    "agent-memory"
  ],
  "verification": {
    "status": "needs_review",
    "label": "Needs Review",
    "method": "unverified",
    "verified_at": null
  },
  "uncertainty": [
    "Vector retrieval is optional and reportedly raises recall from **58.2% to 71.4%**, but the material does not describe the benchmark dataset or evaluation method. Generated pages can still distort sources, so source-only answering, traceability, linting, and human review remain important."
  ],
  "connected_context": {
    "meaning": "This makes external agent memory concrete as a compiled, inspectable knowledge layer rather than learned or repeatedly re-ingested context. It reinforces selective retrieval and structured navigation, while narrowing trust: generated wiki pages need source links, source-only fallback, and review because persistence can preserve distortions as readily as useful synthesis. The reported recall gain remains directional without evaluation details.",
    "corpus_size": 757,
    "generated_at": "2026-09-12T10:05:39.996Z",
    "connections": [
      {
        "title": "thedotmack/claude-mem",
        "source_name": "GitHub",
        "source_url": "https://github.com/thedotmack/claude-mem",
        "feed7_url": "https://feed7.dev/p/claude-mem-1uba088",
        "reason": "Both keep persistent memory external and selectively retrievable; LLM Wiki adds a maintained schema and source-linked wiki layer, while leaving similar governance and contradiction risks."
      },
      {
        "title": "Citation Needed: Provenance for LLM-Built Knowledge Graphs — Daniel Chalef, Zep AI",
        "source_name": "AI Engineer",
        "source_url": "https://www.youtube.com/watch?v=H7puB0RwJMM",
        "feed7_url": "https://feed7.dev/p/citation-needed-provenance-for-llm-built-knowledge-graphs-daniel-chalef-1iob5t8",
        "reason": "The provenance warning directly qualifies LLM Wiki’s generated layer: simple source links may be insufficient when a page synthesizes, changes, or merges claims."
      },
      {
        "title": "Scaling Compute on Context — Jack Morris, Engram",
        "source_name": "AI Engineer",
        "source_url": "https://www.youtube.com/watch?v=WiqDvX6isc4",
        "feed7_url": "https://feed7.dev/p/scaling-compute-on-context-jack-morris-engram-1pxr9bt",
        "reason": "LLM Wiki supplies a retrieval-and-compression alternative to training on a private corpus, consistent with the finding that corpus memorization alone does not make knowledge usable."
      },
      {
        "title": "SheetCompass: Hierarchical Relation Graphs for Agentic Spreadsheet Reasoning",
        "source_name": "arXiv",
        "source_url": "https://arxiv.org/abs/2608.14452v1",
        "feed7_url": "https://feed7.dev/p/2608-14452v1-17xm2vb",
        "reason": "Both preserve structure instead of flattening source material, but SheetCompass specializes that principle for spreadsheet relations while LLM Wiki applies a general wiki and schema."
      }
    ]
  },
  "lifecycle": "Current",
  "published_at": null,
  "modified_at": null,
  "supersedes": [],
  "expires_at": null,
  "formats": {
    "html": "https://feed7.dev/p/llm-wiki-1dqmknq",
    "json": "https://feed7.dev/p/llm-wiki-1dqmknq.json",
    "markdown": "https://feed7.dev/p/llm-wiki-1dqmknq.md"
  }
}