Builds and maintains an interlinked wiki from your documents in a desktop app, and exposes hybrid search, graph and file reads to agents through a local HTTP API and MCP server.
Use it now
Keep it with up to 9 other tools you're setting up, then share them all as one link.
Try this first
Ask your assistant, with LLM Wiki connected:
- Deep Research
Use LLM Wiki to generate research topics from the wiki: ‹what you need›
- Graph Insights
Use LLM Wiki to detect communities in the wikilink graph: ‹what you need›
- Web Clipper
Use LLM Wiki to clip the current browser page into a chosen wiki project: ‹what you need›
Connect it over MCP
Connect LLM Wiki as an MCP server, following its setup instructions at https://github.com/nashsu/llm_wiki
Its page: github.com/nashsu/llm_wiki
Call the API
Auth An API key from nashsu
Its page: github.com/nashsu/llm_wiki
Get the browser extension
Its page: github.com/nashsu/llm_wiki
Compare
Press Compare to add it to the tray at the bottom of the window, then pick up to 2 others anywhere on the site.
- Access
- APIMCPExtension
- Auth
- API Key
- Skills
- 5
Skills
Local HTTP API
Serves a token-protected JSON API on 127.0.0.1:19828 for hybrid search, file reads, graph traversal, rescans and SSE-streamed agent chat.
MCP Server
Bundles a local MCP server that calls the same API, with a copyable client config shown in Settings, API + MCP.
Deep Research
Generates research topics from the wiki, runs multi-query web search via Tavily, SerpApi or SearXNG, and ingests the results.
Graph Insights
Detects communities in the wikilink graph with Louvain clustering and surfaces surprising connections and knowledge gaps.
Web Clipper
Clips the current browser page into a chosen wiki project as Markdown through an unpacked Chrome extension and a local API.