Data Analyser
Drop a CSV. Chat with the data. Charts, queries, summaries — all on-device.
Every app on this page runs entirely on your device — no
cloud round-trips, no telemetry, no model that calls home.
Each card lists its capabilities up front, derived from the
app's locara.json manifest.
Drop a CSV. Chat with the data. Charts, queries, summaries — all on-device.
Local OCR + semantic search across your documents and images.
Real-time transcription of microphone and system audio. Granola-style live captions, fully local.
Open a folder of documents (Markdown, PDF, text). Read, ask questions, get answers grounded in fetched sections — fully local.
Open a Markdown or text file. Chat with a local LLM. The model proposes per-edit operations you accept or reject inline; every accepted edit becomes a versioned snapshot. All on-device.
Drop a local file. Chat with it. The local LLM emits sandboxed HTML+JS that renders interactive charts, tables, and small custom UIs over your data — all on-device.
Local-only audio transcription with semantic search across your recordings.
Describe a video. Local LLM emits Remotion JSX. Live preview, frame-accurate. Optional MP4 render via the Remotion CLI.
Speak to a local model and have it speak back. Pipeline-based voice agent: Whisper STT → Qwen LLM → system speech synthesis. Designed to migrate cleanly to end-to-end omni models when those land.