Versions:

0.6.11
0.6.10
0.6.9
0.6.8
0.6.7
0.6.6
0.6.5
0.6.4
0.6.3
0.6.2
0.6.1
0.6.0
0.5.4
0.5.3
0.5.2
0.5.1
0.5.0
0.4.26
0.4.25
0.4.24
0.4.23
0.4.22
0.4.21
0.4.20
0.4.19
0.4.18
0.4.17
0.4.16
0.4.15
0.4.14
0.4.13
0.4.12
0.4.11
0.4.10
0.4.9
0.4.8
0.4.7
0.4.6
0.4.5
0.4.4
0.4.3
0.4.2
0.4.0
0.3.13
0.3.12
0.3.11
0.3.10
0.3.9
0.3.8
0.3.7
0.3.6
0.3.3
0.3.1

LLM Wiki, published by llmwiki, is a cross-platform desktop application that automatically transforms a user's documents into an organized, interlinked personal knowledge base. Currently at version 0.6.11 across a release history of 53 versions, the software is based on Karpathy's LLM Wiki pattern, a methodology for building personal knowledge bases with large language models, and implements those core ideas as a full desktop application with significant enhancements. Rather than using traditional RAG, where answers are retrieved and derived from scratch on every query, the LLM incrementally builds and maintains a persistent wiki from source documents, compiling knowledge once and keeping it current over time. Key capabilities include a two-step chain-of-thought ingest process, in which the LLM first analyzes content and then generates wiki pages with source traceability and incremental caching, and a four-signal knowledge graph relevance model combining direct links, source overlap, Adamic-Adar scoring, and type affinity. Louvain community detection enables automatic discovery of knowledge clusters with cohesion scoring, while graph insights surface unexpected connections and knowledge gaps with one-click Deep Research, which generates LLM-optimized search topics, performs multi-query web searches, and auto-ingests results back into the wiki. Additional features include optional vector semantic search via LanceDB with support for any OpenAI-compatible embedding endpoint, a persistent ingest queue with serial processing, crash recovery, cancel, retry, and progress visualization, recursive folder import that preserves directory structure and uses folder context as an LLM classification hint, and an async review system. The software fits the knowledge management and personal knowledge base category, serving use cases such as organizing document collections, maintaining a self-updating wiki, discovering relationships between sources, and augmenting research workflows with automated ingestion and semantic retrieval.

Tags:

agent 145

agentic 74

ai 414

chatbot 104

knowledge-base 24

large-language-model 144

llm 217

wiki 11