Hermes Agent is an AI assistant platform designed to combine language model conversations with practical tools and persistent workflows. This fork introduces an independent Android application focused on running AI models locally. Users can import GGUF, LiteRT-LM, and Android task model files directly from device storage. A model selection interface performs compatibility and memory checks before starting inference. The application supports conversation history, local model management, and configurable response settings. Optional remote AI providers and model downloads extend its capabilities beyond offline operation. Its Android interface adapts to phones and tablets and provides controls for permissions and remote processing. The Full edition includes additional Android workflow tools, while the Play edition restricts certain functionality.
Features
- Local AI model execution on Android with support for GGUF, LiteRT-LM, and compatible task model files
- Direct model importing from device storage without mandatory accounts or internet connectivity
- Model compatibility validation with memory requirement checks and automatic inference engine selection
- Persistent AI conversation history with configurable response preferences and advanced runtime settings
- Optional remote language model providers, online model downloads, and local API sharing controls
- Adaptive phone and tablet interfaces with multilingual support and edition-specific Android workflow tools