user-intent-discovery is a Python library that processes chatbot conversation logs by embedding questions, reducing dimensionality, clustering similar intents, and optionally generating summaries with a local LLM. Each stage (embed, reduce, cluster, summarize) can run locally or on a remote server. It is designed for developers building conversational AI systems who need to surface representative user intents from raw query data.
user-intent-discovery sits in PulseGate's AI & ML category. Manually reviewing and grouping large volumes of unstructured chatbot user questions to discover common intents. user-intent-discovery is an open-source project aimed at developers. The project is open source (MIT). user-intent-discovery is available on the command line, and it can be self-hosted.
Behind user-intent-discovery is Foxsense, and it first shipped in 2026. Among its 5 catalogued features are Semantic Clustering, UMAP Reduction, and HDBSCAN Clustering.
Summary written by a language model from the project’s public pages.
What PulseGate has recorded for this listing
Same category — not a similarity match