A self-hosted AI agent platform built and battle-tested on a Galaxy S21. Multi-channel communication, tool integrations, memory, web presence — all running 24/7 with zero cloud compute costs.
Not a toy. A production-grade platform handling real business operations, deployed on hardware you already own.
Telegram, Discord, Slack, Matrix, IRC, WhatsApp, XMPP, SMS, email, and web chat. Run them all simultaneously — one agent, many frontends.
Local llama.cpp model routes simple messages. 11 cloud providers (Anthropic, OpenAI, Google, Groq, DeepSeek, Mistral, and more) handle the heavy lifting. You control the cost.
Jira, Google Calendar, email (AgentMail), web search, Vercel/Railway deploy, Cursor Cloud Agents. Connect what you need.
Conversation history, structured facts, multi-step plans, and a knowledge base. All stored locally in SQLite.
Landing page, chat widget, intake forms, blog engine, and automated lead qualification with branded email outreach.
Name, personality, services, brand colors, booking links — all driven by config.toml. Fork it and make it yours.
Send voice messages on Telegram. Transcription via Gemini, Whisper, or OpenAI. Optional text-to-speech replies.
Connect to any Model Context Protocol server. Extend the agent with custom tools without changing core code.
Push to your phone from your laptop. A post-receive hook auto-pulls, restarts the agent, and reconnects the tunnel.
Channels feed into a core loop. The loop dispatches to tools. Web visitors get a sandboxed agent with zero internal access.
┌─────────────┐
│ Telegram │
│ Bot │
└──────┬──────┘
│
┌──────────┐ ┌──────┴──────┐ ┌──────────────┐
│ SMS ├────────┤ AgentLoop ├────────┤ Tool │
│ (Termux) │ │ (core) │ │ Registry │
└──────────┘ └──────┬──────┘ └──────┬───────┘
│ │
┌──────────┐ ┌──────┴──────┐ ┌──────┴───────┐
│ Web Chat ├────────┤ Inference │ │ Calendar │
│ (public) │ │ Cascade │ │ Email │
└──────────┘ └─────────────┘ │ Jira │
local → light → heavy │ Search │
│ Deploy │
Security boundary: │ MCP Gateway │
Web visitors get a └──────────────┘
sandboxed WebAgent
with NO tool access
Clone the repo, configure your persona, and have a production AI agent running in under 15 minutes.