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。
TypeScript
Commits on main
test: switch real-LLM default to local llama-server + Qwen3 no-think
a932a41 nash_su committed 7 months ago
fix: language detection + case-insensitive wikilinks + entity/source lang skip
ffeaf86 nash_su committed 7 months ago
test: move real-content docs to gitignored tests/ with TS source-of-truth
6d4c132 nash_su committed 7 months ago
test: tighten real-LLM contracts to assert behavior, not just non-corruption
1aa2958 nash_su committed 7 months ago
feat: reduce stale review noise with dedupe + queue-drain sweep
ecd3222 nash_su committed 7 months ago
fix: prevent cross-project data contamination on project switch
5386ee1 nash_su committed 7 months ago
fix: rename 'AI Output Language' to 'AI Target Language' for clarity
e2f6cd7 nash_su committed 7 months ago
feat: add configurable AI output language for all generated content
3444050 nash_su committed 7 months ago
fix: reinforce output language instruction to prevent Chinese bias
d88c7e1 nash_su committed 7 months ago
docs: remove RRF claims — ablation study shows no improvement with 2-lane setup
21a9e7d nash_su committed 7 months ago
feat: add Copy button on assistant messages — copies clean content to clipboard
4f7c3bf nash_su committed 7 months ago
feat: auto-detect user query language, force LLM to respond in same language
9adc54b nash_su committed 7 months ago
fix: always show daemon status indicator — green when running
e49821d nash_su committed 7 months ago