Ekorbia v0.6 ships a bundled inference engine that runs models locally without requiring Ollama or a terminal, while v0.7 delivers a visual refresh with simpler theme names and quieter defaults. The n…
Ekorbia released versions 0.4 and 0.5, adding guided setup, an in-app model manager, Spaces for bundling context, and fully offline UI in v0.4, followed by on-device voice dictation via whisper.cpp in…
Ekorbia released version 0.3.0, expanding beyond macOS to offer native Windows and Linux builds for the first time. The update provides .deb, .rpm, and .AppImage formats for Linux and .msi and .exe in…
Ekorbia v0.2 introduces a comparison-chat mode that runs two to three local large language models against the same prompt in parallel. Testing Gemma 4, IBM Granite 4.1, and Qwen 3.5 on a 32 GB M1 Max …
Ekorbia released version 0.2.0 of its desktop application, introducing user-defined chat group folders in the sidebar and a comparison-chat mode that lets users send one prompt to two or three install…
Ekorbia released v0.1.0, the first public build of a native macOS desktop client for local AI models that operates entirely offline without cloud services, API keys, or telemetry. The open-source appl…