Awesome AI AgentsVirtual Assistants

moltis-org/moltis

⭐ 2760 Rust repository created 2026-01-29

Moltis is a self-hosted personal agent server written in Rust and distributed as one binary with no Node.js or Python runtime, installable through a shell script, Homebrew, Docker or cargo. It is designed to run on hardware the user owns, from a Mac Mini or Raspberry Pi to any server, and it keeps provider API keys on that machine. Every command the agent issues runs inside a sandbox rather than on the host; supported backends are Docker or Podman, Apple Container and WebAssembly. The workspace is organised into about 59 crates covering roughly 270 thousand lines: a gateway crate providing the HTTP and WebSocket server, RPC and authentication; a tools crate for tool execution, sandboxing and WASM tools; provider implementations for several LLM vendors; the agent loop with streaming and prompt assembly; chat orchestration; configuration; and session persistence. Feature crates add messaging channels for Telegram, WhatsApp, Signal, Discord, Microsoft Teams, Matrix, Slack and Nostr, a web UI and GraphQL and webhook interfaces, MCP support over stdio and HTTP or SSE, a skills system with bundled and workspace skills plus autonomous improvement and import of OpenClaw skills, memory and context handling built on SQLite with full-text search and vector storage, voice input and output through built-in speech-to-text and text-to-speech providers, browser automation, authentication with passwords, passkeys, API keys and a vault, and scheduling through cron and CalDAV. A lightweight feature set is available for constrained devices. Unsafe Rust is confined to foreign function interface and precompiled runtime boundaries rather than the core agent loop, and the README documents a size and capability comparison against OpenClaw and Hermes Agent.

https://github.com/moltis-org/moltis

personal-assistantrustself-hostedmcpsandboxmemory

Also in Virtual Assistants

mem0ai/mem0

Mem0 is an open-source memory layer that enhances AI agents and assistants with personalized, adaptive memory capabilities for improved context-aware interactions across various applications.

CherryHQ/cherry-studio

Cherry Studio is a cross-platform desktop client that supports multiple large language model providers, offering extensive AI assistant features, document processing, and practical productivity tools in an open-source environment.

tinyhumansai/openhuman

Local-first personal AI harness combining a persistent memory brain, multi-agent orchestration, and autonomous web and data research.

khoj-ai/khoj

Khoj is a self-hostable personal AI platform that transforms any local or online large language model into a customizable, autonomous AI assistant for research, automation, and document retrieval.

kortix-ai/suna

Suna is an open-source generalist AI assistant that automates real-world tasks through natural conversation, combining browser automation, file management, web crawling, and API integrations in a secure, modular architecture.

gptme/gptme

gptme is a versatile personal AI assistant that operates in your terminal, equipped with tools for coding, file editing, web browsing, and vision, providing a powerful local alternative to popular AI agents for diverse knowledge work.

CherryHQ/cherry-studio-app

Cherry Studio App is the official mobile application that enables powerful AI Large Language Models interaction on iOS and Android devices, supporting multiple LLM providers and offering tools for conversation management and data migration.

cosmicstack-labs/mercury-agent

Personal AI agent in TypeScript that runs continuously from CLI, Telegram or web with permission-gated tools, SQLite-backed long-term memory, token budgets and installable skills.