Chat with open LLMs entirely offline on your Mac. Private by design, powered by Apple MLX. No account, no cloud, no telemetry.
Qwen, Gemma, DeepSeek, Mistral, Llama and anything on mlx-community. Real-time streaming.
FLUX.2-klein-9B via mflux, locally. Say "draw a…" and Ka1zen generates. No API key needed.
Ask Ka1zen to search the web AND generate an image. It fetches real facts, then draws from them.
Watch the model reason step by step. Works with Qwen3, DeepSeek-R1, Gemma 4, Nemotron.
DuckDuckGo + direct page fetch. URL auto-detection. Clickable [1]-style source citations.
Drop images into the chat. Supports Gemma 4, Pixtral, Mistral Small VLM, Qwen2-VL, LLaVA.
Index PDFs, text, and code locally with Apple NLEmbedding. Fully local SQLite storage.
OpenAI-compatible proxy for Continue, Cursor, Zed, LM Studio — use local models anywhere.
Per-token logprob visualisation — spot hallucinations with green / yellow / red colouring.
Ka1zen fetches real facts first, then turns them into a FLUX-optimized prompt and generates locally.
Ka1zen queries DuckDuckGo to gather real, up-to-date facts — visible as a live Agent Step with source citations.
The active LLM converts search snippets into a detailed FLUX-optimized English prompt, incorporating colors, shapes, era, and context.
The image is produced on-device with FLUX.2-klein-9B. No image ever leaves your Mac.
Search for a 1967 Ford Mustang and create a photorealistic image of this car parked in front of an American diner at sunset.
Look up the Renaissance fresco technique and make a detailed illustration of an artist at work on a church ceiling.
Find info about Japanese ramen shops in Tokyo and generate a cinematic photo of a steaming bowl of tonkotsu ramen.
Search the web for James Webb Space Telescope imagery and draw a stylized poster celebrating its deep-field observations.
100% private. No account required. No analytics, no crash reports, no "anonymous usage statistics". Your conversations, documents and embeddings never leave your Mac.