Stars
Forks
Watchers
Developer links
Moltis
Moltis gives individuals and teams a completely private personal AI agent server that bridges conversational assistants to everyday messaging platforms while executing real-world computing tasks inside secure execution environments. Users can interact with autonomous agents across Telegram, Discord, WhatsApp, Slack, Matrix, and browser interfaces to draft correspondence, automate research, and schedule recurring cron tasks. The system coordinates multi-agent delegation by spinning up specialized sub-agents with dedicated roles for code generation, pull request reviews, quality assurance testing, and technical documentation. Built-in sandboxing isolates tool operations within container boundaries or WebAssembly modules, ensuring shell commands, web scraping routines, and script executions cannot alter underlying operating system files without explicit permission. Native Model Context Protocol integration allows operators to attach external data endpoints, database connectors, and custom command-line utilities without rewriting core routing logic. Persistent memory preserves conversational context and document embeddings across multiple sessions, allowing assistants to recall prior discussions, user preferences, and project guidelines indefinitely. Administrators can configure granular tool approvals, manage WebAuthn passkey authentication, and review real-time WebSocket communication logs through an embedded control panel. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.
Benefits
- Comprehensive Multi-Channel Agent Accessibility
- Connects personal AI assistants directly to Telegram, Discord, WhatsApp, Slack, Matrix, and Microsoft Teams, allowing users to initiate workflows and receive status alerts across their preferred communication apps.
- Strict Multi-Tier Sandboxed Tool Execution
- Isolates automated script executions, command-line runs, and web browser automation within Docker, Podman, or WebAssembly sandboxes, preventing unapproved filesystem alterations or malicious code execution on host infrastructure.
- Local-First Persistent Knowledge Retention
- Maintains conversational memory, document embeddings, and session state within embedded SQLite databases, ensuring complete operational privacy and rapid context retrieval without relying on proprietary third-party vector cloud services.
- Standardized Model Context Protocol Extensibility
- Supports both stdio and HTTP Server-Sent Events transports for Model Context Protocol servers, enabling rapid integration of external enterprise APIs, custom automation scripts, and proprietary database connectors.
Features
- Multi-Provider LLM Gateway
- Routes agent prompts to OpenAI, Anthropic, Gemini, DeepSeek, and local Ollama instances with unified streaming WebSocket responses.
- Specialized Sub-Agent Delegation
- Spawns autonomous secondary agents configured with built-in presets for coding, documentation generation, quality assurance, and automated web research.
- WebAuthn Passkey Authentication
- Protects administrative routes and agent control surfaces with hardware security keys, biometric passkeys, and argon2-hashed credential validation.
- Automated Cron Scheduling
- Executes recurring agent routines, pipeline reviews, and notifications at configured intervals using an integrated background task scheduler.
- Embedded Terminal Console
- Provides an integrated browser terminal for direct host interaction with configurable security policies and execution approval gates.