Our take
Activeregular commits and releases- Activity
- 86
- Community
- 44
- Issues
- 65
- Pull requests
- 37
+1,064 stars in the last 30 days
- Releases more often than 89% of the projects we track
- Slower to merge pull requests than 91% of the projects we track
LLM Wiki is an unusually broad desktop implementation of a persistent, source-traceable wiki workflow, and its recent releases and issue handling indicate active development, though development is concentrated in one contributor.
Good fit if
- You want an automatically maintained wiki rather than query-by-query RAG, and value Markdown files that can also be opened in Obsidian.
- You need document ingestion, graph exploration, and chat in one desktop application across macOS, Windows, or Linux.
- You can work with a GPL-3.0 project and are comfortable configuring an LLM provider and, for optional features, web search or embedding services.
Look elsewhere if
- You need a hosted, managed service rather than a desktop application that stores project data on your machine.
- Your adoption process requires development ownership to be distributed across contributors; measured activity is heavily concentrated in one person.
- You need a project with a documented automated test suite; the repository metadata does not report tests.
All health signals
| Last commit | 2026-10-21 (1 day ago) |
|---|---|
| Commits, last 90 days | 100+ |
| Releases, last 12 months | 62 (latest v0.6.13, 2026-10-22) |
| Contributors | 35 (top contributor: 87% of commits) |
| Issues closed, last 90 days | 65+ (typically closed in 11 days) |
| Pull requests merged, last 90 days | 22 (typically merged in 6 days) |
| Project age | 7 months |
Checked on 2026-10-23 with the GitHub API.
Project history
Daily GitHub snapshots since Oct 7, 2026. History covers stars and forks; health signals are not tracked historically.
Stars
21,558Forks
2,444Change since Nov 10, 2026: +22 stars·+1 forks
Overview
LLM Wiki is a cross-platform desktop application built on Tauri v2 that turns documents into an organized, interlinked knowledge base. Based on Andrej Karpathy’s LLM Wiki pattern, it incrementally generates and maintains wiki pages from imported sources, rather than rebuilding an answer from retrieved passages for every question. It supports macOS, Windows, and Linux.
It is aimed at people who want a durable, browsable knowledge base from their reading or work documents, with source traceability and connections between topics. The resulting wiki is stored as Markdown and is compatible with Obsidian, so the material is not limited to the app’s chat interface.
Key Features
- Imports PDFs, Office documents, EPUB/MOBI, images, media, web clips, and batches of URLs.
- Uses a two-step ingest process: first analyze a source, then generate or update wiki pages with source references.
- Maintains an ingest queue, skips unchanged files with an incremental cache, and can watch the source folder for changes.
- Combines tokenized search with graph expansion, with optional semantic retrieval using LanceDB.
- Visualizes wiki connections and clusters, and surfaces isolated pages, sparse communities, and unexpected links.
- Provides multi-conversation chat, source-grounded retrieval, asynchronous review, and optional web-based Deep Research.
- Includes a local HTTP API and MCP server for external tools, plus a Chrome web clipper.
Use Cases
- Researchers can build a source-linked wiki from papers and books, then explore related concepts and gaps in coverage.
- Professionals can organize reports, presentations, spreadsheets, and web pages into a persistent reference base for recurring questions.
- Individual learners can maintain an evolving knowledge base from reading materials and inspect how ideas connect in the graph.
- Users of Claude Code, Codex, or other MCP-compatible clients can query a running LLM Wiki through its local API or bundled MCP server.
What you need
Detected in the repository
- Node.js (from package.json)
- Automated checks on GitHub Actions
Getting Started
Download a prebuilt installer from the GitHub Releases, or build from source:
git clone https://github.com/nashsu/llm_wiki.git
cd llm_wiki
npm install
npm --prefix mcp-server ci && npm run mcp:build
npm run tauri dev
Building requires Node.js 20+, Rust 1.88+, and protoc. See the README for platform-specific build steps, configuration, and usage details.
License in Plain Words
No standard license was detected. Without a license, the default copyright rules apply: you may read the code, but not reuse it. Check the repository or ask the authors.
Alternatives
- utopia: Utopia builds a self-hosted, ontology-guided graph with evidence-backed answers and review, while llm_wiki creates an interlinked wiki from documents in a desktop app.
| Project | Language | License | Stars | Status |
|---|---|---|---|---|
| llm_wiki | TypeScript | – | 20.9k | Active |
| utopia | Rust | Apache-2.0 | 8k | New |
Considerations
- The project is young, but measured activity is strong: it is marked active, has frequent recent commits and releases, and recent issue and pull-request handling. That activity is not the same as a long operational track record.
- Contributor activity is concentrated: one person accounts for most measured contributions, which may affect continuity and review capacity.
- A Node.js and Rust toolchain plus Protocol Buffers is needed to build from source. The README does not require Docker, and vector search is optional rather than a prerequisite.
- LLM use depends on configuring a provider. Deep Research and some document-processing options also depend on separately configured services or endpoints.
- The project is licensed under GPL-3.0, so teams should review its terms before incorporating or distributing it.
- Repository metadata does not report an automated test suite.
Found this useful?
Share it with someone who would like llm_wiki.