Protoagent banner
ggondim ggondim

Protoagent

AI community

Description

Your AI assistant, your way. A powerful multi-channel wrapper that lets you interact with AI agents (Claude, Copilot) through Telegram or REST API, using your own subscriptions and running entirely under your control.

Installation

This entry records only its repository, not the path inside it, so there is no exact command to give. Open the source below and copy the folder into ~/.claude/skills/, or the file into ~/.claude/agents/.

README

[!CAUTION] This project has been archived in favor of newer and more complete initiatives, like [OpenClaw](https://openclaw.ai). See [this blog post](https://dev.to/ggondim/how-i-built-a-deterministic-multi-agent-dev-pipeline-inside-openclaw-and-contributed-a-missing-4ool) to understand why.


πŸ€– Protoagent

**Your AI assistant, your way.** A powerful multi-channel wrapper that lets you interact with AI agents (Claude, Copilot) through Telegram or REST API, using your own subscriptions and running entirely under your control.

Protoagent is a production-ready AI agent orchestrator that bridges the gap between powerful AI providers (Claude SDK, GitHub Copilot CLI) and your preferred communication channels. Built with resilience, memory, and flexibility in mind β€” no vendor lock-in, just pure control over your AI interactions.


🎯 Why Protoagent?

  • πŸ”Œ Bring Your Own Subscription: Use your existing Claude Desktop or GitHub Copilot subscriptions β€” no additional API costs
  • πŸ’¬ Multi-Channel: Interact via Telegram bot OR REST API (perfect for Siri/Apple Watch integration)
  • 🧠 Built-in Memory: Short-term and long-term memory with automatic context injection
  • πŸ›‘οΈ Production-Ready: Crash recovery, circuit breaker, watchdog, and comprehensive logging
  • πŸŽ™οΈ Voice Support: Integrated Whisper transcription for voice messages
  • πŸ”§ Zero Lock-in: Switch providers on-the-fly without changing your workflow

⚑ Quick Start

Prerequisites

Installation

# Clone repository
git clone 
cd protoagente

# Configure environment
cp .env.example .env
nano .env  # Edit with your settings (see below)

# Build and start
docker-c