oshayr-llm-wiki

llm-wiki

An autonomous knowledge base that grows as you work.

LLM Wiki is a Claude Code plugin that captures research, ideas, and decisions into an interlinked wiki with semantic search, automatic research, and a Wikipedia-style web UI. Knowledge compounds over time — the more you use it, the smarter it gets.

Inspired by Andrej Karpathy's LLM Wiki pattern: raw sources are immutable, the LLM maintains the wiki layer, and a schema governs behavior.

Core Features

Knowledge Management

• Automatic capture — saves research, ideas, decisions, and findings to the wiki as you work
• Smart retrieval with research-on-miss — checks wiki first, automatically researches and ingests if not found
• Full-text search — TF-IDF keyword search with content-aware scoring and snippet extraction
• Block references & transclusion — [[page#heading]] links and ![[page#section]] embeds
• Backlink panel with automatic unlinked mention detection
• Frontmatter query language — Dataview-like queries: SELECT title, type FROM pages WHERE confidence = "high"
• Intelligent freshness — 9-tier staleness system from live (15 min) to permanent (never expires)

Research-on-Miss

• Automatic research — /wiki-read researches topics not in the wiki using available tools
• Tool discovery — works with whatever tools the user has (WebSearch, WebFetch, Wikipedia API, MCP tools)
• Auto-ingestion — saves findings to wiki with proper citations

Web UI Features

• Wikipedia-style browsable website with 4 themes (light, dark, terminal, wikipedia)
• Interactive knowledge graph (Cytoscape.js) with multiple layouts, clustering, and neighborhood highlighting
• Canvas/whiteboard view for spatial page arrangement
• Split-pane markdown editor with live preview and AI assist
• Live research — click any red link to auto-research the topic
• Spaced repetition review interface (FSRS-based scheduling)
• Content gap analysis dashboard
• WebSocket chat sidebar with RAG-augmented Q&A

Maintenance & Health

• Self-maintaining — lints broken links, merges duplicates, upgrades confidence, flags stale content
• Daily notes and journal workflows
• Smart caching with adaptive TTL and stale-while-revalidate
• Circuit breakers for external API resilience
• Git integration with auto-commit, attribution, and undo

How It Works

The wiki operates in a simple cycle: when you ask a question, it first checks its knowledge base. If found, it returns a cited answer. If not found, it automatically researches the topic, ingests the findings, and provides an answer—all without breaking your workflow.

sequenceDiagram
    User->>wiki-reader: /wiki-read "What is X?"
    wiki-reader->>wiki-index: Check knowledge base
    alt Found in wiki
        wiki-index-->>wiki-reader: Page exists
        wiki-reader->>User: Cited answer from wiki
    else Not found
        wiki-index-->>wiki-reader: No results
        wiki-reader->>search-orchestrator: Research needed
        search-orchestrator->>search-channel: Fan out queries (web, academic, code, docs)
        search-channel->>research-processor: Raw search results
        research-processor->>wiki-writer: Processed findings
        wiki-writer->>wiki-pages: Create/update page
        wiki-writer->>User: Cited answer with new page
    end

Quick Start

Installation

1. Install the plugin:

   claude plugin install ./llm-wiki
   

   Or copy manually:

   cp -r llm-wiki .claude/plugins/
   

2. Restart Claude Code — dependencies install automatically on first session.

First Commands

Start using the wiki immediately with any of these:

Command	Purpose
/wiki-write https://example.com/article	Ingest a web page
/wiki-read "What is transformer attention?"	Ask — researches if not in wiki
/wiki-serve	Browse the wiki at localhost:8420
/wiki-maintain	Health check and optimization

Dependencies

Core dependencies (fastapi, uvicorn, mcp, etc.) are installed automatically via the plugin's SessionStart hook. For optional enhanced features:

pip install trafilatura        # fallback content extraction
pip install numpy sqlite-vec   # vector search and caching

Skills Reference

/wiki-write — Add or Update Content

Ingest from URLs, files, or text. Auto-creates .wiki/ on first use.

Mode	Command	Purpose
Ingest	/wiki-write <url>	Fetch and ingest web page or paper
Ingest	/wiki-write <file>	Ingest local file (markdown, text, PDF)
Ingest	/wiki-write "text..."	Ingest inline text directly
Batch	/wiki-write --batch <dir>	Ingest all .md files in directory
Update	/wiki-write --update <slug>	Autonomously update existing page
Refresh	/wiki-write --refresh-stale	Find and refresh stale pages

Page types: concept, idea, brainstorming, status, rules, config, skill, memory, reference, or custom types from .wiki/templates/

/wiki-read — Search and Query

Ask the wiki questions. Automatically researches if knowledge is missing.

Depth	Command	Behavior
Quick	/wiki-read quick <question>	Index scan only, no research fallback (fastest)
Standard	/wiki-read <question>	Search wiki + auto-research if missing
Deep	/wiki-read deep <question>	Full search + raw sources + multi-channel research

All answers include [[slug]] citations. Contradictions between sources are explicitly noted.

/wiki-serve — Web UI

Launch Wikipedia-style browsable website at localhost:8420.

Features:

• 4 themes (light, dark, terminal, wikipedia)
• Interactive knowledge graph (Cytoscape.js)
• Split-pane markdown editor with live preview
• WebSocket chat with RAG-augmented Q&A
• Live research (click red links to auto-research)
• Spaced repetition review (FSRS-based)
• Content gap analysis dashboard
• Canvas/whiteboard spatial view

Stop: /wiki-serve stop

/wiki-maintain — Health Maintenance

Comprehensive wiki maintenance and quality control.

Subcommand	Purpose
/wiki-maintain	Run all maintenance steps
/wiki-maintain lint	Fix broken links, missing frontmatter, orphans
/wiki-maintain dedup	Find and merge near-duplicate pages
/wiki-maintain gaps	Analyze knowledge gaps and missing coverage

Maintenance steps:

1. Lint — fix broken [[links]], missing frontmatter, orphan pages
2. Deduplicate — merge pages with >60% slug token overlap
3. Confidence upgrade — promote pages based on source count (low->medium->high)
4. Stale detection — flag pages past their freshness tier TTL
5. Fact-checking — verify claims on high-confidence pages
6. Concept synthesis — auto-generate articles connecting 3+ related pages
7. Index regeneration — rebuild index.md from all pages

/wiki-view — Dashboard and Export

Read-only dashboard, statistics, and export capabilities.

Subcommand	Purpose
/wiki-view	Dashboard summary (page counts, recent activity, health)
/wiki-view pages	List all pages grouped by type
/wiki-view stats	Detailed statistics and distributions
/wiki-view graph	Knowledge graph visualization (Mermaid)
/wiki-view graph <slug>	Graph centered on page (2-hop neighborhood)
/wiki-view export html	Export as self-contained HTML
/wiki-view export md	Export as single markdown bundle
/wiki-view export json	Export as JSON knowledge graph
/wiki-view artifacts <type>	Generate study guide, timeline, glossary, or comparison

---

How Research-on-Miss Works

When you ask a question that's not in the wiki, the entire research pipeline activates automatically. Here's the flow:

sequenceDiagram
    actor User
    participant WR as wiki-reader
    participant Index as wiki index
    participant SO as search-orchestrator
    participant SC as search-channel
    participant RP as research-processor
    participant WW as wiki-writer
    participant BM as backlink-manager

    User->>WR: /wiki-read "What is X?"
    WR->>Index: Check for matching pages
    alt Page found
        Index-->>WR: Return page
        WR-->>User: Cited answer from wiki
    else No match
        Index-->>WR: No results
        WR->>WR: Detect query intent & complexity
        WR->>SO: Trigger research
        SO->>SO: Route to search channels
        SO->>SC: Dispatch to web, academic, code, docs channels
        par Parallel Research
            SC->>SC: Web search
            SC->>SC: Academic search
            SC->>SC: Code search
            SC->>SC: Docs search
        end
        SC-->>RP: Raw results
        RP->>RP: Deduplicate, condense, rank
        RP-->>WW: Processed findings
        WW->>WW: Synthesize findings into page
        WW->>BM: Update backlinks
        BM->>Index: Register page
        WW-->>User: Cited answer with new wiki page
    end

---

Architecture

System Overview

LLM Wiki consists of 5 entry points (skills), 10 autonomous agents, utilities in the bin/, and a persistent data layer in .wiki/.

flowchart TD
    User([User]) -->|Invokes| Skills
    
    subgraph Skills["5 Entry Points"]
        W["/wiki-write<br/>Ingest & Update"]
        R["/wiki-read<br/>Search & Ask"]
        S["/wiki-serve<br/>Web UI"]
        M["/wiki-maintain<br/>Health Check"]
        V["/wiki-view<br/>Dashboard"]
    end
    
    Skills -->|Route to| Agents
    
    subgraph Agents["10 Autonomous Agents"]
        subgraph write["Write Pipeline"]
            WW["wiki-writer<br/>(Sonnet)"]
            BM["backlink-manager<br/>(Haiku)"]
        end
        
        subgraph read["Read Pipeline"]
            WR["wiki-reader<br/>(Haiku)"]
            SO["search-orchestrator<br/>(Sonnet)"]
            SC["search-channel<br/>(Haiku)"]
        end
        
        subgraph research["Research Pipeline"]
            RL["research-loop<br/>(Sonnet)"]
            RP["research-processor<br/>(Haiku)"]
        end
        
        subgraph quality["Quality Pipeline"]
            WA["wiki-auditor<br/>(Haiku)"]
            FC["fact-checker<br/>(Sonnet)"]
            CE["citation-explorer<br/>(Sonnet)"]
        end
    end
    
    Agents -->|Read/Write| Data
    Agents -->|Use| Bin
    
    subgraph Bin["Utilities (bin/)"]
        Search["search.py<br/>TF-IDF"]
        Cache["cache.py<br/>Vectors"]
        BL["backlinks.py<br/>Links"]
        Gap["gaps.py<br/>Analysis"]
        Git["git.py<br/>Tracking"]
    end
    
    subgraph Data[".wiki/ Data Layer"]
        Pages["pages/<br/>Markdown"]
        Index["index.md<br/>Catalog"]
        Cache2["cache/<br/>SQLite"]
        Raw["raw/<br/>Sources"]
        Schema["SCHEMA.md<br/>Rules"]
    end
    
    S -->|Serves| UI["Web Server<br/>localhost:8420"]
    UI -->|Renders| UIFeatures["4 Themes, Graph,<br/>Editor, Chat, Review"]

Directory Structure