Local AI Client: Ollama & vLLM

Local AI Client is a modern Android chat client for local and self-hosted AI servers. Connect to Ollama, vLLM, LM Studio, Open WebUI, llama.cpp server, text-generation-webui, or any OpenAI-compatible /v1 REST API endpoint.

Use one app to manage server profiles, switch models, stream responses, and keep your conversations on your device.

WORKS WITH
• Ollama
• vLLM
• LM Studio
• Open WebUI
• llama.cpp server
• text-generation-webui
• Any OpenAI-compatible /v1 REST API

FEATURES
• Streaming AI chat with Markdown, tables, code blocks, and math
• Syntax-highlighted code blocks with one-tap copy
• Reasoning models: collapsible thinking view
• Multiple server profiles with quick endpoint switching
• Live model loading from your server
• Prompt starters to begin common tasks quickly
• Image input for multimodal models
• Voice input via system speech recognition
• Conversation history with search, pinning, date grouping, and previews
• Personalization: custom instructions, memory, personas, and parameter presets
• Semantic recall via embeddings (optional)
• Token usage reporting
• Light and dark theme
• Korean and English language support
• Local-first chat storage with JSON export and import

PRIVACY AND CONTROL
• No required app account
• AI chat requests are sent to the server endpoint you configure
• Conversations are stored locally on your device
• Export and import your chat data when needed

Point Local AI Client at your server and start chatting.