https://github.com/dotdevdotdev/agentwire-dev
Voice-controlled multi-agent framework. Spawn workers, orchestrate across machines, talk to your agents over SSH. CLI + SDK + Telegram.
https://github.com/dotdevdotdev/agentwire-dev
agent ai ai-coding claude cli speech-to-text tmux tts voice
Last synced: about 1 month ago
JSON representation
Voice-controlled multi-agent framework. Spawn workers, orchestrate across machines, talk to your agents over SSH. CLI + SDK + Telegram.
- Host: GitHub
- URL: https://github.com/dotdevdotdev/agentwire-dev
- Owner: dotdevdotdev
- License: agpl-3.0
- Created: 2025-12-31T01:15:40.000Z (6 months ago)
- Default Branch: main
- Last Pushed: 2026-05-16T20:39:28.000Z (about 1 month ago)
- Last Synced: 2026-05-16T20:44:23.159Z (about 1 month ago)
- Topics: agent, ai, ai-coding, claude, cli, speech-to-text, tmux, tts, voice
- Language: Python
- Homepage: https://agentwire.dev
- Size: 51.4 MB
- Stars: 11
- Watchers: 0
- Forks: 5
- Open Issues: 6
-
Metadata Files:
- Readme: README.md
- Changelog: CHANGELOG.md
- Contributing: CONTRIBUTING.md
- Funding: .github/FUNDING.yml
- License: LICENSE
- Code of conduct: CODE_OF_CONDUCT.md
- Security: SECURITY.md
- Cla: CLA.md
Awesome Lists containing this project
README
Talk to your AI coding agents. From anywhere.
---
## The Problem
You're on the couch. Your AI agent is on your workstation. You have an idea.
Old way: Get up. Walk to computer. Type.
**AgentWire way:** Pull out phone. Hold button. Talk. Done.
---
## What It Does
Push-to-talk voice control for [Claude Code](https://github.com/anthropics/claude-code) or any AI coding assistant running in tmux.
```
Phone → AgentWire Portal → tmux session → Claude Code
🎤 (WebSocket) 📺 🤖
```
**From your phone, tablet, or laptop on your network:**
- Hold to speak, release to send
- Watch agents work in real-time
- Hear responses via TTS
- Manage multiple projects simultaneously
---
## Quick Start
```bash
# Install
pip install agentwire-dev
# Setup (interactive)
agentwire init
agentwire generate-certs
# Run
agentwire portal start
# Open https://localhost:8765
```
**Requirements:** Python 3.10+, tmux, ffmpeg, Claude Code
Platform-specific instructions
**macOS:**
```bash
brew install tmux ffmpeg
pip install agentwire-dev
```
**Ubuntu/Debian:**
```bash
sudo apt install tmux ffmpeg python3-pip python3-venv
python3 -m venv ~/.agentwire-venv && source ~/.agentwire-venv/bin/activate
pip install agentwire-dev
```
**WSL2:** Same as Ubuntu. Audio is limited; use as remote worker with portal on Windows host.
---
## Features
| Feature | Description |
|---------|-------------|
| **Voice Control** | Push-to-talk from any device on your network |
| **Multi-Session** | Run multiple agents on different projects simultaneously |
| **Git Worktrees** | Same project, multiple branches, parallel agents |
| **Remote Machines** | SSH into GPU servers and talk to agents there |
| **Worker Orchestration** | Spawn worker panes, coordinate tasks, voice commands |
| **Safety Hooks** | 300+ dangerous commands blocked (rm -rf, force push, etc.) |
| **TTS Responses** | Agents talk back via browser audio |
| **SDK Sessions** | Structured Claude Agent SDK sessions with parent-child hierarchy |
| **Telegram Bridge** | Control agents from Telegram with voice notes and inline keyboards |
| **Session Roles** | Leader/worker patterns for multi-agent workflows |
---
## How It Works
**1. Create a session:**
```bash
agentwire new -s myproject -p ~/projects/myproject
```
**2. Open the portal:**
Visit `https://localhost:8765` on your phone/tablet/laptop
**3. Talk:**
Hold the mic button, speak your request, release. The transcription goes to Claude Code.
**4. Listen:**
Agent responses are spoken back via TTS (optional, requires GPU for self-hosted or RunPod).
---
## Multi-Agent Orchestration
AgentWire supports orchestrator/worker patterns for complex tasks:
```yaml
# .agentwire.yml in your project
type: claude-bypass
roles:
- agentwire
- voice
```
**Sessions** can spawn workers:
```bash
agentwire spawn --roles worker # Creates a worker pane
agentwire send --pane 1 "Implement the auth module"
```
Workers execute tasks autonomously while the orchestrator coordinates.
---
## Safety
AgentWire blocks dangerous operations before they execute:
- `rm -rf /`, `git push --force`, `git reset --hard`
- Cloud CLI destructive ops (AWS, GCP, Firebase, Vercel)
- Database drops, Redis flushes, container nukes
- Sensitive file access (.env, SSH keys, credentials)
```bash
agentwire safety check "rm -rf /"
# → ✗ BLOCKED: rm with recursive or force flags
agentwire safety status
# → 312 patterns loaded, 47 blocks today
```
All decisions logged for audit trails.
---
## Voice Configuration
**TTS (Text-to-Speech):** Requires GPU. Options:
```yaml
# ~/.agentwire/config.yaml
tts:
backend: "runpod" # Recommended: RunPod serverless
runpod_endpoint_id: "your-endpoint"
runpod_api_key: "your-key"
```
Or self-host with `agentwire tts start` on a GPU machine.
**STT (Speech-to-Text):** Runs locally via `agentwire stt start`. Uses Moonshine ONNX by default (fast CPU inference, no GPU required), with automatic fallback to faster-whisper. Configure backend in `config.yaml`.
Disable voice (text-only mode)
```yaml
tts:
backend: "none"
```
You can still use the portal for session management without voice.
---
## CLI Reference
Session Management
```bash
agentwire list # List sessions
agentwire new -s -p # Create session
agentwire kill -s # Kill session
agentwire send -s "prompt" # Send to session
agentwire output -s # Read output
```
Worker Panes
```bash
agentwire spawn --roles worker # Spawn worker in current session
agentwire send --pane 1 "task" # Send to worker
agentwire output --pane 1 # Read worker output
agentwire kill --pane 1 # Kill worker
```
Voice Commands
```bash
agentwire say "Hello" # TTS (auto-routes to browser)
agentwire alert "Done" # Text notification (no audio)
agentwire listen start/stop # Voice recording
agentwire voiceclone list # Custom voices
```
Remote Machines
```bash
agentwire machine add gpu --host 10.0.0.5 --user dev
agentwire new -s ml@gpu # Create session on remote
agentwire tunnels up # SSH tunnels for services
```
Safety & Diagnostics
```bash
agentwire doctor # Auto-diagnose issues
agentwire safety status # Check protection status
agentwire hooks install # Install Claude Code hooks
agentwire network status # Service health check
```
---
## Documentation
- [Troubleshooting](docs/TROUBLESHOOTING.md)
- [Portal API](docs/PORTAL.md)
- [Remote Machines](docs/remote-machines.md)
- [RunPod TTS Setup](docs/runpod-tts.md)
- [Self-Hosted TTS](docs/tts-self-hosted.md)
- [Safety Hooks](docs/security/damage-control.md)
---
## Community
- [Discord](https://discord.gg/bspFZNTdUr) - Chat, support, feature requests
- [Issues](https://github.com/dotdevdotdev/agentwire-dev/issues) - Bug reports
- [Website](https://agentwire.dev) - Docs and demos
---
## License
**Dual-licensed:**
- [AGPL v3](LICENSE) - Free for open source
- Commercial license available - [contact us](mailto:dev@dotdev.dev)
---
AgentWire: For people who have better things to do.