|
| 1 | +# Created with YamlCreate.ps1 Dumplings Mod |
| 2 | +# yaml-language-server: $schema=https://aka.ms/winget-manifest.defaultLocale.1.12.0.schema.json |
| 3 | + |
| 4 | +PackageIdentifier: nashsu.LLMWiki |
| 5 | +PackageVersion: 0.6.3 |
| 6 | +PackageLocale: en-US |
| 7 | +Publisher: llmwiki |
| 8 | +PublisherUrl: https://www.nashsu.com/ |
| 9 | +PublisherSupportUrl: https://github.com/nashsu/llm_wiki/issues |
| 10 | +PackageName: LLM Wiki |
| 11 | +PackageUrl: https://github.com/nashsu/llm_wiki |
| 12 | +License: GPL-3.0 |
| 13 | +LicenseUrl: https://github.com/nashsu/llm_wiki/blob/HEAD/LICENSE |
| 14 | +ShortDescription: A personal knowledge base that builds itself. LLM reads your documents, builds a structured wiki, and keeps it current. |
| 15 | +Description: |- |
| 16 | + 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. |
| 17 | + 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. |
| 18 | +
|
| 19 | + Features |
| 20 | + - Two-Step Chain-of-Thought Ingest — LLM analyzes first, then generates wiki pages with source traceability and incremental cache |
| 21 | + - 4-Signal Knowledge Graph — relevance model with direct links, source overlap, Adamic-Adar, and type affinity |
| 22 | + - Louvain Community Detection — automatic knowledge cluster discovery with cohesion scoring |
| 23 | + - Graph Insights — surprising connections and knowledge gaps with one-click Deep Research |
| 24 | + - Vector Semantic Search — optional embedding-based retrieval via LanceDB, supports any OpenAI-compatible endpoint |
| 25 | + - Persistent Ingest Queue — serial processing with crash recovery, cancel, retry, and progress visualization |
| 26 | + - Folder Import — recursive folder import preserving directory structure, folder context as LLM classification hint |
| 27 | + - Deep Research — LLM-optimized search topics, multi-query web search, auto-ingest results into wiki |
| 28 | + - Async Review System — LLM flags items for human judgment, predefined actions, pre-generated search queries |
| 29 | + - Chrome Web Clipper — one-click web page capture with auto-ingest into knowledge base |
| 30 | +Tags: |
| 31 | +- agent |
| 32 | +- agentic |
| 33 | +- ai |
| 34 | +- chatbot |
| 35 | +- knowledge-base |
| 36 | +- large-language-model |
| 37 | +- llm |
| 38 | +- wiki |
| 39 | +ReleaseNotesUrl: https://github.com/nashsu/llm_wiki/releases/tag/v0.3.1 |
| 40 | +ManifestType: defaultLocale |
| 41 | +ManifestVersion: 1.12.0 |
0 commit comments