Local-first AI chat: web, desktop and mobile with Ollama
Started Last update
Wollama is a local-first AI chat client for Ollama that ships to the browser, Electron desktop and Capacitor mobile from one codebase. Conversations and companions work offline and later sync through RxDB and PouchDB; voice input/output, RAG, skills, hooks and web agents sit above a model-provider boundary.
flowchart TD P["idea / needs"] --> S["wollama"] S --> A["Ollama + model-provider boundary"] S --> B["web + Electron + Capacitor"] S --> C["offline RxDB <-> PouchDB sync"] S --> D["voice · RAG · skills · hooks · web agents"]
Cross-platform AI chat application powered by Ollama for local, private inference. Conversations, companions and settings remain available offline, then RxDB syncs them with PouchDB when the server returns. Voice I/O, RAG, skills, hooks and web agents run in the browser, Electron desktop app and Capacitor mobile app; a provider registry now isolates model backends from conversation orchestration.