Mealissa is a secure, OpenAI- and Anthropic-compatible gateway that gives self-hosted local LLMs a globally accessible API endpoint, with prompts encrypted in transit and never stored. Download the agent, connect your Ollama instance, and reach your models from anywhere.
A valid license key is required to run the agent. Get a license →
mealissa-llm-agent.bat launcher + build/ folder with the agent JAR — installs Java automatically if missing
mealissa-llm-agent.sh launcher + build/ folder with the agent JAR — installs Java automatically if missing
Run any model Ollama supports — Llama, Qwen, Gemma, Mistral, Phi, DeepSeek, and more. Ollama must be running before the agent starts.
ollama pull qwen3.5:4b
Unzip the downloaded package to get mealissa-llm-agent.
Run mealissa-llm-agent — it detects your Ollama models, connects to the Mealissa cloud, and registers your node. Your local LLM is globally accessible, encrypted, zero data stored.
A license is required to register your node on the network.