Maid is a free and open source application for interfacing with llama.cpp models locally, and with Anthropic, DeepSeek, Ollama, Mistral and OpenAI models remotely.
Maid is a React Native Android application that lets users run large language models both on-device and through remote API connections. For local inference, it runs GGUF-format models entirely on-device via llama.cpp with no internet connection required, and includes a one-tap download browser for curated Hugging Face models including Qwen, Phi, LFM, and TinyLlama. For remote access, users supply their own API keys to connect to Anthropic (Claude), DeepSeek, Mistral, Novita, Ollama, or OpenAI. The app provides conversation management with JSON export and import, adjustable generation parameters such as temperature, top-p, top-k, and context length, custom system prompts, and optional chat history backup via Supabase. A companion app called Maise adds text-to-speech output. Available on both GitHub and Google Play under the MIT license with no telemetry or ads, Maid suits mobile users who want a single interface for both private on-device inference and cloud model access.
- ✓Open-source license (MIT)
- ✓Recently active
- ✓Healthy fork ratio
- ✓Clear description
- ✓Topics declared
- ✓Mature repo (>1y old)
git clone https://github.com/Mobile-Artificial-Intelligence/maidResumen de Tools
Lo que la gente pregunta sobre maid
¿Qué es Mobile-Artificial-Intelligence/maid?
+
Mobile-Artificial-Intelligence/maid es tools para el ecosistema de Claude AI. Maid is a free and open source application for interfacing with llama.cpp models locally, and with Anthropic, DeepSeek, Ollama, Mistral and OpenAI models remotely. Tiene 2.5k estrellas en GitHub y se actualizó por última vez 2mo ago.
¿Cómo se instala maid?
+
Puedes instalar maid clonando el repositorio (https://github.com/Mobile-Artificial-Intelligence/maid) o siguiendo las instrucciones del README en GitHub. ClaudeWave también te ofrece bloques de instalación rápida en esta misma página.
¿Es seguro usar Mobile-Artificial-Intelligence/maid?
+
Nuestro agente de seguridad ha analizado Mobile-Artificial-Intelligence/maid y le ha asignado un Trust Score de 100/100 (tier: Verified). Revisa el desglose completo de comprobaciones superadas y flags en esta página.
¿Quién mantiene Mobile-Artificial-Intelligence/maid?
+
Mobile-Artificial-Intelligence/maid es mantenido por Mobile-Artificial-Intelligence. La última actividad registrada en GitHub es de 2mo ago, con 9 issues abiertos.
¿Hay alternativas a maid?
+
Sí. En ClaudeWave puedes explorar tools similares en /categories/tools, ordenados por popularidad o actividad reciente.
Despliega maid en tu cloud
Lleva este repo a producción en minutos. Cada plataforma genera su propio entorno con variables de entorno editables.
¿Mantienes este repo? Añade un badge a tu README
Pega el badge en tu README de GitHub para mostrar que está auditado por ClaudeWave. Cada badge enlaza de vuelta a esta página y muestra el Trust Score actual.
[](https://claudewave.com/repo/mobile-artificial-intelligence-maid)<a href="https://claudewave.com/repo/mobile-artificial-intelligence-maid"><img src="https://claudewave.com/api/badge/mobile-artificial-intelligence-maid" alt="Featured on ClaudeWave: Mobile-Artificial-Intelligence/maid" width="320" height="64" /></a>Más Tools
A single CLAUDE.md file to improve Claude Code behavior, derived from Andrej Karpathy's observations on LLM coding pitfalls.
An AI SKILL that provide design intelligence for building professional UI/UX multiple platforms
🪨 why use many token when few token do trick — Claude Code skill that cuts 65% of tokens by talking like caveman
AI coding assistant skill (Claude Code, Codex, OpenCode, Cursor, Gemini CLI, and more). Turn any folder of code, SQL schemas, R scripts, shell scripts, docs, papers, images, or videos into a queryable knowledge graph. App code + database schema + infrastructure in one graph.
A light-weight and powerful meta-prompting, context engineering and spec-driven development system for Claude Code by TÂCHES.
CLI proxy that reduces LLM token consumption by 60-90% on common dev commands. Single Rust binary, zero dependencies