Moltis

Moltis is a personal AI agent server for people who want an assistant that remembers earlier conversations and carries out tasks on their own hardware. You can reach the same agent through a browser or messaging apps.

• Local and cloud models: Use Ollama, LM Studio or local GGUF models, or connect Anthropic, OpenAI, Google Gemini and OpenAI-compatible services. Local execution supports CPU, GPU and MLX on Apple Silicon.
• Memory and automation: Recall context across sessions, schedule recurring tasks in natural language, browse the web and manage CalDAV calendar events and reminders.
• Messaging and voice: Talk through local or cloud voice providers, or use Telegram, WhatsApp, Discord, Slack, Matrix, Nostr and Microsoft Teams.
• Controlled tool access: Tools run in sandboxes by default, with permission policies for actions and filesystem access. Passwords, passkeys and scoped API keys protect access; an encrypted vault stores credentials.
• Extensions and migration: Add MCP tools, skills and hooks, create separate agent personas, or import OpenClaw conversations, skills and settings without changing the original workspace.

Moltis is open source under the MIT license. It runs as a single binary on macOS, Linux and Windows, with Docker deployment available for servers you control. The server and persistent memory reside on your host. Cloud model and cloud voice features send requests to the selected providers; messaging integrations communicate through their respective services.