A map of the Guru's connections.
ShabadVerse turns Sri Guru Granth Sahib Ji into an interactive graph. Every one of the 5,542 shabads is a star; the threads between them trace shared themes, so you can wander from one shabad to its kin and discover where a thought travels across Gurbani.
How to use it
- Search four ways. Type English transliteration (ABC), first letters from the start of a line (ੳ▸) or from anywhere in it (▸ੳ▸), or just describe what you are thinking of in plain words (✨) and let meaning search find the closest shabads.
- Browse the Constellation Map. Open TAGS to see the full theme vocabulary; filter it, pick a theme, and jump to any shabad that carries it.
- Expand to explore. Tap a shabad to make it the center; its neighbors fan out by shared theme. Follow the trail and your path stays in the breadcrumbs above.
- Build a library. Add shabads as you go, then switch to REVIEW to read them in full. Save and share your collection with a link.
Reading the graph
- The bright center is the shabad you are exploring now.
- Green dots are shabads already in your library.
- Pale dots are neighbors, colored by their primary mood when one stands out.
- Theme Amber words floating in the field are theme labels; click one to see every shabad under it.
- A thicker thread means a stronger thematic match.
How the connections are built
The threads are not hand-drawn, and the themes are not machine-invented. The vocabulary comes from Sikh tradition, curated by hand; the machine's job is finding which shabads express each concept, in Gurbani's own words first and by meaning second.
The theme vocabulary is drawn from Sikh tradition — the panj chor, the virtues, Naam, Hukam, Sahaj — each concept defined and approved by a human reader before any tagging ran. No model chose what counts as a theme.
A shabad that names a concept — ਹਉਮੈ, ਕਾਮ, ਕ੍ਰੋਧ, ਸੰਤੋਖ — carries its tag as ground truth. Meaning similarity then extends each concept to shabads that teach it without naming it, within a bounded reach so no theme can swallow the corpus.
Vismad, Birha, Chardi Kala, and Nimrata have no single anchor word in Gurbani, so they are inferred from meaning alone. They are the tags most likely to miss; treat them as suggestions, not verdicts.
Two shabads connect on a blend of shared themes and meaning (sentence-embedding similarity). Rare themes count for more than common ones, so a link says why these two belong together, not merely that both speak of the Divine.
Gurbani text, transliteration, and translations come from BaniDB, an initiative of the SikhiToTheMax project.
Straight talk about the AI
- What the AI did. It measures meaning. Every verse and shabad becomes a vector, and the app compares those vectors for search, for neighbors, and for deciding which shabads express each hand-picked concept. The short summaries in tooltips were drafted by local language models. The app itself was built with Claude Code.
- What it did not do. It did not write, edit, or reinterpret a single line of Gurbani. The scripture is BaniDB's; the AI only labels and links.
- Where it can be wrong. A shabad that names a concept is tagged on solid ground; one tagged by meaning alone is a machine judgment, and some will miss the mark — the four concepts with no anchor word most of all. Treat tags as a way to navigate, not as a teaching. When one feels off, it probably is, and your eye on the original shabad is the final word.
- Tell us. Found a bad connection or a missing theme? Open an issue on GitHub. The taxonomy gets better every time someone does.