llm_wiki v0.4.14 更新发布

主要做了以下两个更新：

• 优化超长内容文件的分析，加入智能 chunk split 和上下文关联分析，长文本即使切片也不丢失全局信息。
• DeepResearch 加入对 AnyTxt 的 API 调用支持，AnyTxt 一个高效的本地文本搜索工具，可以索引电脑上的全部文件，现在 llm_wiki 可以对这些文件进行查询和 Research 啦。

https://github.com/nashsu/llm_wiki

nashsu/llm_wiki

Source: https://github.com/nashsu/llm_wiki

LLM Wiki

A personal knowledge base that builds itself.
LLM reads your documents, builds a structured wiki, and keeps it current.

What is this? • Features • Tech Stack • Installation • Credits • License

English | 中文 | 日本語

Features

• Two-Step Chain-of-Thought Ingest — LLM analyzes first, then generates wiki pages with source traceability and incremental cache
• Multimodal Image Ingestion — extract embedded images from PDFs, generate factual captions with a vision LLM, surface them in image-aware search results with lightbox preview and jump-to-source
• 4-Signal Knowledge Graph — relevance model with direct links, source overlap, Adamic-Adar, and type affinity
• Louvain Community Detection — automatic knowledge cluster discovery with cohesion scoring
• Graph Insights — surprising connections and knowledge gaps with one-click Deep Research
• Vector Semantic Search — optional embedding-based retrieval via LanceDB, supports any OpenAI-compatible endpoint
• Persistent Ingest Queue — serial processing with crash recovery, cancel, retry, and progress visualization
• Folder Import — recursive folder import preserving directory structure, folder context as LLM classification hint
• Source Folder Auto-Watch — detects external changes in raw/sources/ and keeps ingest/delete cleanup in sync
• Deep Research — LLM-optimized search topics, multi-query web search via Tavily, SerpApi, or SearXNG, auto-ingest results into wiki
• Async Review System — LLM flags items for human judgment, predefined actions, pre-generated search queries
• Chrome Web Clipper — one-click web page capture with auto-ingest into knowledge base
• Local HTTP API + AI Agent Skill — built-in 127.0.0.1:19828 JSON API (token-protected) for hybrid search, file read, graph traversal, and source rescan; ready-made agent skill installs into Claude Code / Codex with one command (npx skills add …)

What is this?

LLM Wiki is a cross-platform desktop application that turns your documents into an organized, interlinked knowledge base — automatically. Instead of traditional RAG (retrieve-and-answer from scratch every time), the LLM incrementally builds and maintains a persistent wiki from your sources. Knowledge is compiled once and kept current, not re-derived on every query.

This project is based on Karpathy’s LLM Wiki pattern — a methodology for building personal knowledge bases using LLMs. We implemented the core ideas as a full desktop application with significant enhancements.

Credits

The foundational methodology comes from Andrej Karpathy’s llm-wiki.md, which describes the pattern of using LLMs to incrementally build and maintain a personal wiki. The original document is an abstract design pattern; this project is a concrete implementation with substantial extensions.

What We Kept from the Original

The core architecture follows Karpathy’s design faithfully:

• Three-layer architecture: Raw Sources (immutable) → Wiki (LLM-generated) → Schema (rules & config)
• Three core operations: Ingest, Query, Lint
• index.md as the content catalog and LLM navigation entry point
• log.md as the chronological operation record with parseable format
• [[wikilink]] syntax for cross-references
• YAML frontmatter on every wiki page
• Obsidian compatibility — the wiki directory works as an Obsidian vault
• Human curates, LLM maintains — the fundamental role division

What We Changed & Added

1. From CLI to Desktop Application

The original is an abstract pattern document designed to be copy-pasted to an LLM agent. We built it into a full cross-platform desktop application with:

• Three-column layout: Knowledge Tree / File Tree (left) + Chat (center) + Preview (right)
• Icon sidebar for switching between Wiki, Sources, Search, Graph, Lint, Review, Deep Research, Settings
• Custom resizable panels — drag-to-resize left and right panels with min/max constraints
• Activity panel — real-time processing status showing file-by-file ingest progress
• All state persisted — conversations, settings, review items, project config survive restarts
• Scenario templates — Research, Reading, Personal Growth, Business, General — each pre-configures purpose.md and schema.md

2. Purpose.md — The Wiki’s Soul

The original has Schema (how the wiki works) but no formal place for why the wiki exists. We added purpose.md:

• Defines goals, key questions, research scope, evolving thesis
• LLM reads it during every ingest and query for context
• LLM can suggest updates based on usage patterns
• Different from schema — schema is structural rules, purpose is directional intent

3. Two-Step Chain-of-Thought Ingest

The original describes a single-step ingest where the LLM reads and writes simultaneously. We split it into two sequential LLM calls for significantly better quality:

Step 1 (Analysis): LLM reads source → structured analysis
  - Key entities, concepts, arguments
  - Connections to existing wiki content
  - Contradictions & tensions with existing knowledge
  - Recommendations for wiki structure

Step 2 (Generation): LLM takes analysis → generates wiki files
  - Source summary with frontmatter (type, title, sources[])
  - Entity pages, concept pages with cross-references
  - Updated index.md, log.md, overview.md
  - Review items for human judgment
  - Search queries for Deep Research

Additional ingest enhancements beyond the original:

• SHA256 incremental cache — source file content is hashed before ingest; unchanged files are skipped automatically, saving LLM tokens and time
• Persistent ingest queue — serial processing prevents concurrent LLM calls; queue persisted to disk, survives app restart; failed tasks auto-retry up to 3 times
• Folder import — recursive folder import preserving directory structure; folder path passed to LLM as classification context (e.g., “papers > energy” helps categorize content)
• Source folder auto-watch — files added, edited, or deleted in raw/sources/ outside the app are picked up automatically and reuse the same ingest/delete lifecycle as in-app actions
• Queue visualization — Activity Panel shows progress bar, pending/processing/failed tasks with cancel and retry buttons
• Auto-embedding — when vector search is enabled, new pages are automatically embedded after ingest
• Source traceability — every generated wiki page includes a sources: [] field in YAML frontmatter, linking back to the raw source files that contributed to it
• overview.md auto-update — global summary page regenerated on every ingest to reflect the latest state of the wiki
• Guaranteed source summary — fallback ensures a source summary page is always created, even if the LLM omits it
• Language-aware generation — LLM responds in the user’s configured language (English or Chinese)
• Progressive Sources view — large source folders render progressively while scrolling, keeping big source collections responsive

4. Knowledge Graph with Relevance Model

The original mentions [[wikilinks]] for cross-references but has no graph analysis. We built a full knowledge graph visualization and relevance engine:

4-Signal Relevance Model:

Graph Visualization (sigma.js + graphology + ForceAtlas2):

• Node colors by page type or community, sizes scaled by link count (√ scaling)
• Edge thickness and color by relevance weight (green=strong, gray=weak)
• Hover interaction: neighbors stay visible, non-neighbors dim, edges highlight with relevance score label
• Zoom controls (ZoomIn, ZoomOut, Fit-to-screen)
• Position caching prevents layout jumps when data updates
• Legend switches between type counts and community info based on coloring mode

5. Louvain Community Detection

Not in the original. Automatic discovery of knowledge clusters using the Louvain algorithm (graphology-communities-louvain):

• Auto-clustering — discovers which pages naturally group together based on link topology, independent of predefined page types
• Type / Community toggle — switch between coloring nodes by page type (entity, concept, source…) or by discovered knowledge cluster
• Cohesion scoring — each community scored by intra-edge density (actual edges / possible edges); low-cohesion clusters (< 0.15) flagged with warning
• 12-color palette — distinct visual separation between clusters
• Community legend — shows top node label, member count, and cohesion per cluster

6. Graph Insights — Surprising Connections & Knowledge Gaps

Not in the original. The system automatically analyzes graph structure to surface actionable insights:

Surprising Connections:

• Detects unexpected relationships: cross-community edges, cross-type links, peripheral↔hub couplings
• Composite surprise score ranks the most noteworthy connections
• Dismissable — mark connections as reviewed so they don’t reappear

Knowledge Gaps:

• Isolated pages (degree ≤ 1) — pages with few or no connections to the rest of the wiki
• Sparse communities (cohesion < 0.15, ≥ 3 pages) — knowledge areas with weak internal cross-references
• Bridge nodes (connecting 3+ clusters) — critical junction pages that hold multiple knowledge areas together

Interactive:

• Click any insight card to highlight corresponding nodes and edges in the graph; click again to deselect
• Knowledge gaps and bridge nodes have a Deep Research button — triggers LLM-optimized research with domain-aware topics (reads overview.md + purpose.md for context)
• Research topic shown in editable confirmation dialog before starting — user can refine topic and search queries

7. Optimized Query Retrieval Pipeline

The original describes a simple query where the LLM reads relevant pages. We built a multi-phase retrieval pipeline with optional vector search and budget control:

Phase 1: Tokenized Search
  - English: word splitting + stop word removal
  - Chinese: CJK bigram tokenization (每个 → [每个, 个…])
  - Title match bonus (+10 score)
  - Searches both wiki/ and raw/sources/

Phase 1.5: Vector Semantic Search (optional)
  - Embedding via any OpenAI-compatible /v1/embeddings endpoint
  - Stored in LanceDB (Rust backend) for fast ANN retrieval
  - Cosine similarity finds semantically related pages even without keyword overlap
  - Results merged into search: boosts existing matches + adds new discoveries

Phase 2: Graph Expansion
  - Top search results used as seed nodes
  - 4-signal relevance model finds related pages
  - 2-hop traversal with decay for deeper connections

Phase 3: Budget Control
  - Configurable context window: 4K → 1M tokens
  - Proportional allocation: 60% wiki pages, 20% chat history, 5% index, 15% system
  - Pages prioritized by combined search + graph relevance score

Phase 4: Context Assembly
  - Numbered pages with full content (not just summaries)
  - System prompt includes: purpose.md, language rules, citation format, index.md
  - LLM instructed to cite pages by number: [1], [2], etc.

Vector Search is fully optional — disabled by default, enabled in Settings with independent endpoint, API key, and model configuration. When disabled, the pipeline falls back to tokenized search + graph expansion. Benchmark: overall recall improved from 58.2% to 71.4% with vector search enabled.

8. Multi-Conversation Chat with Persistence

The original has a single query interface. We built full multi-conversation support:

• Independent chat sessions — create, rename, delete conversations
• Conversation sidebar — quick switching between topics
• Per-conversation persistence — each conversation saved to .llm-wiki/chats/{id}.json
• Configurable history depth — limit how many messages are sent as context (default: 10)
• Cited references panel — collapsible section on each response showing which wiki pages were used, grouped by type with icons
• Reference persistence — cited pages stored directly in message data, stable across restarts
• Regenerate — re-generate the last response with one click (removes last assistant + user message pair, re-sends)
• Save to Wiki — archive valuable answers to wiki/queries/, then auto-ingest to extract entities/concepts into the knowledge network

9. Thinking / Reasoning Display

Not in the original. For LLMs that emit <think> blocks (DeepSeek, QwQ, etc.):

• Streaming thinking — rolling 5-line display with opacity fade during generation
• Collapsed by default — thinking blocks hidden after completion, click to expand
• Visual separation — thinking content shown in distinct style, separate from the main response

10. KaTeX Math Rendering

Not in the original. Full LaTeX math support across all views:

• KaTeX rendering — inline $...$ and block $$...$$ formulas rendered via remark-math + rehype-katex
• Milkdown math plugin — preview editor renders math natively via @milkdown/plugin-math
• Auto-detection — bare \begin{aligned} and other LaTeX environments automatically wrapped with $$ delimiters
• Unicode fallback — 100+ symbol mappings (α, ∑, →, ≤, etc.) for simple inline notation outside math blocks

11. Review System (Async Human-in-the-Loop)

The original suggests staying involved during ingest. We added an asynchronous review queue:

• LLM flags items needing human judgment during ingest
• Predefined action types: Create Page, Deep Research, Skip — constrained to prevent LLM hallucination of arbitrary actions
• Search queries generated at ingest time — LLM pre-generates optimized web search queries for each review item
• User handles reviews at their convenience — doesn’t block ingest

12. Deep Research

Not in the original. When the LLM identifies knowledge gaps:

• Web search via Tavily, SerpApi, or SearXNG finds relevant sources with full content extraction (no truncation)
• Provider-specific configuration — Tavily and SerpApi use independent API keys; SerpApi supports selectable engines, while SearXNG uses a configured instance URL and search categories
• Multiple search queries per topic — LLM-generated at ingest time, optimized for search engines
• LLM-optimized research topics — when triggered from Graph Insights, LLM reads overview.md + purpose.md to generate domain-specific topics and queries (not generic keywords)
• User confirmation dialog — editable topic and search queries shown for review before research starts
• LLM synthesizes findings into a wiki research page with cross-references to existing wiki
• Thinking display — <think> blocks shown as collapsible sections during synthesis, auto-scroll to latest content
• Auto-ingest — research results automatically processed to extract entities/concepts into the wiki
• Task queue with 3 concurrent tasks
• Research Panel — dedicated sidebar panel with dynamic height, real-time streaming progress

13. Browser Extension (Web Clipper)

The original mentions Obsidian Web Clipper. We built a dedicated Chrome Extension (Manifest V3):

• Mozilla Readability.js for accurate article extraction (strips ads, nav, sidebars)
• Turndown.js for HTML → Markdown conversion with table support
• Project picker — choose which wiki to clip into (supports multi-project)
• Local HTTP API (port 19827, tiny_http) — Extension ↔ App communication
• Auto-ingest — clipped content automatically triggers the two-step ingest pipeline
• Clip watcher — polls every 3 seconds for new clips, processes automatically
• Offline preview — shows extracted content even when app is not running

14. Multi-format Document Support

The original focuses on text/markdown. We support structured extraction preserving document semantics:

15. File Deletion with Cascade Cleanup

The original has no deletion mechanism. We added intelligent cascade deletion:

• Deleting a source file removes its wiki summary page
• 3-method matching finds related wiki pages: frontmatter sources[] field, source summary page name, frontmatter section references
• Shared entity preservation — entity/concept pages linked to multiple sources only have the deleted source removed from their sources[] array, not deleted entirely
• Index cleanup — removed pages are purged from index.md
• Wikilink cleanup — dead [[wikilinks]] to deleted pages are removed from remaining wiki pages

16. Configurable Context Window

Not in the original. Users can configure how much context the LLM receives:

• Slider from 4K to 1M tokens — adapts to different LLM capabilities
• Proportional budget allocation — larger windows get proportionally more wiki content
• 60/20/5/15 split — wiki pages / chat history / index / system prompt

17. Cross-Platform Compatibility

The original is platform-agnostic (abstract pattern). We handle concrete cross-platform concerns:

• Path normalization — unified normalizePath() used across 22+ files, backslash → forward slash
• Unicode-safe string handling — char-based slicing instead of byte-based (prevents crashes on CJK filenames)
• macOS close-to-hide — close button hides window (app stays running in background), click dock icon to restore, Cmd+Q to quit
• Windows/Linux close confirmation — confirmation dialog before quitting to prevent accidental data loss
• Tauri v2 — native desktop on macOS, Windows, Linux
• GitHub Actions CI/CD — automated builds for macOS (ARM + Intel), Windows (.msi), Linux (.deb / .AppImage)

18. Other Additions

• i18n — English + Chinese interface (react-i18next)
• Settings persistence — LLM provider, API key, model, context size, language saved via Tauri Store
• Obsidian config — auto-generated .obsidian/ directory with recommended settings
• Markdown rendering — GFM tables with borders, proper code blocks, wikilink processing in chat and preview
• Multi-provider LLM support — OpenAI, Anthropic, Google, Ollama, Custom — each with provider-specific streaming and headers
• 15-minute timeout — long ingest operations won’t fail prematurely
• dataVersion signaling — graph and UI automatically refresh when wiki content changes

Tech Stack

Installation

Pre-built Binaries

Download from Releases:

• macOS: .dmg (Apple Silicon + Intel)
• Windows: .msi
• Linux: .deb / .AppImage

Build from Source

# Prerequisites: Node.js 20+, Rust 1.70+
git clone https://github.com/nashsu/llm_wiki.git
cd llm_wiki
npm install
npm run tauri dev      # Development
npm run tauri build    # Production build

Chrome Extension

1. Open chrome://extensions
2. Enable “Developer mode”
3. Click “Load unpacked”
4. Select the extension/ directory

Quick Start

1. Launch the app → Create a new project (choose a template)
2. Go to Settings → Configure your LLM provider (API key + model)
3. Optional: configure Web Search providers and source folder auto-watch in Settings
4. Go to Sources → Import documents (PDF, DOCX, MD, etc.)
5. Watch the Activity Panel — LLM automatically builds wiki pages
6. Use Chat to query your knowledge base
7. Browse the Knowledge Graph to see connections
8. Check Review for items needing your attention
9. Run Lint periodically to maintain wiki health

Local HTTP API + AI Agent Skill

LLM Wiki ships a built-in local HTTP API at http://127.0.0.1:19828 (token-protected, 127.0.0.1-only) so external tools — including AI agents like Claude Code, Codex, or any HTTP-capable script — can query your wiki:

• GET /api/v1/health — server status (no auth)
• GET /api/v1/projects — list projects
• GET /api/v1/projects/{id}/files / files/content — read files and content
• POST /api/v1/projects/{id}/search — hybrid retrieval (keyword + vector) returning mode, tokenHits, vectorHits, per-result vectorScore
• GET /api/v1/projects/{id}/graph — wikilinks graph
• POST /api/v1/projects/{id}/sources/rescan — trigger a backend rescan

Enable + generate a token in Settings → API Server.

Plug your AI agent in with one command

A ready-made agent skill for LLM Wiki lives in its own repo. Install it into Claude Code / Codex / any skills-compatible runtime:

npx skills add https://github.com/nashsu/llm_wiki_skill.git --skill llm_wiki_skill

After install, the agent can answer prompts like “what does my LLM Wiki say about X”, “search my 知识库 for Y”, “show the neighborhood of node Z in my wiki graph”, and “rescan my wiki sources” by talking to your locally-running app — read-only by default, citing wiki page paths so you can verify in-app.

• Skill repo: https://github.com/nashsu/llm_wiki_skill
• Trigger discipline: it intentionally does not trigger on generic “search my notes” / “check my Obsidian / Notion / Logseq” — only when you explicitly name LLM Wiki / my wiki / 知识库.

Project Structure

my-wiki/
├── purpose.md              # Goals, key questions, research scope
├── schema.md               # Wiki structure rules, page types
├── raw/
│   ├── sources/            # Uploaded documents (immutable)
│   └── assets/             # Local images
├── wiki/
│   ├── index.md            # Content catalog
│   ├── log.md              # Operation history
│   ├── overview.md         # Global summary (auto-updated)
│   ├── entities/           # People, organizations, products
│   ├── concepts/           # Theories, methods, techniques
│   ├── sources/            # Source summaries
│   ├── queries/            # Saved chat answers + research
│   ├── synthesis/          # Cross-source analysis
│   └── comparisons/        # Side-by-side comparisons
├── .obsidian/              # Obsidian vault config (auto-generated)
└── .llm-wiki/              # App config, chat history, review items

Star History

License

This project is licensed under the GNU General Public License v3.0 — see LICENSE for details.