About Moltis
Moltis is a secure, persistent personal agent server written in Rust and distributed as a single binary. It is not an image generator. It is a self hosted AI assistant that runs on hardware the user owns, such as a Mac Mini, a Raspberry Pi or any server, and the vendor says keys and private data never leave that machine.
The agent connects to more than 20 model providers, including Anthropic, OpenAI, Google Gemini, Mistral and DeepSeek, as well as local models through Ollama, LM Studio, local GGUF files and MLX on Apple Silicon. Zero configuration sign in is offered for GitHub Copilot and similar OAuth providers. Users reach the agent through a web interface or through Telegram, WhatsApp, Discord, Slack, Matrix, Nostr and Microsoft Teams, with iOS listed as coming soon. Built in capabilities include persistent memory with vector and full text search, voice input and output, scheduled tasks written in natural language, CalDAV calendar integration, SSRF protected web browsing, and shell execution sandboxed in Docker or Apple Containers. The agent can also create its own skills, hooks and MCP tools at runtime. A one click import is offered for users switching from OpenClaw, and a GraphQL API and JSON RPC interface are available.
It suits developers and technical users who want an always on assistant under their own control. Installation is by shell script, Homebrew, Docker or from source, and it runs on macOS, Linux and Windows. The vendor does not publish pricing.