PocketPaw
Your AI agent. Modular. Secure. Everywhere.
One-click install
$ curl -fsSL https://pocketpaw.xyz/install.sh | sh Most AI agents take thirty minutes to set up. Docker, OAuth, tunneling, fifty config options, all before you send your first message.
Your API keys sit in plain‑text config files. Dashboards get exposed on Shodan. Safety controls can be toggled via API while the agent runs. You install hundreds of packages whether you need them or not. One bad dependency update breaks everything, even features you never asked for.
- 1 Provision a VM or VPS 10 min
- 2 SSH setup & authentication 5 min
- 3 Clone repo & Docker setup 8 min
- 4 Edit 50+ config variables 5 min
- 5 Set up OAuth & tunneling 10 min
- 6 Install 200+ dependencies 8 min
- 7 Debug dependency conflicts 10 min
- 8 Configure AI provider 4 min
- ✓ Dashboard running
- ✓ Credentials encrypted
- ✓ Channels connected
- ✓ Memory initialized
- ✓ Ready to chat
Batteries included,
choose your pack.
One install gives you everything you need. Add channels when your life demands them. Never carry what you don't use.
$ curl -fsSL https://pocketpaw.xyz/install.sh | sh # Interactive installer $ pip install pocketpaw[memory] # Add Mem0 semantic search $ pip install pocketpaw[all] # Everything, all channelsThe full includes:
Everything you need.
Add the rest later.
Multi-Channel
Telegram, Discord, Slack, WhatsApp, and web dashboard. Same agent, same context, every channel.
3 LLM Backends
Claude Agent SDK, OpenAI, or Ollama for fully local models. $0 API cost with local inference.
Encrypted Credentials
Fernet AES with machine-derived PBKDF2 key. Real encryption, not base64 obfuscation.
Guardian AI
Secondary LLM reviews dangerous commands before execution. 3-tier tool policy with deny-lists.
Persistent Memory
Session history and long-term facts. Upgrade to Mem0 semantic vector search when ready.
Browser Automation
Playwright-powered with accessibility tree snapshots. Navigate, extract, interact.
Modular Install
pip extras for genuine dependency isolation. Toggle channels from the dashboard. Auto-install, no restart.
Skills
Self-installing plugin system. Add capabilities from a registry or build your own. The agent installs what it needs.
Audit Log
Append-only JSONL. Every tool execution logged with severity levels. Tamper-evident by design.
Security was the
starting point.
Your AI agent has terminal access, file access, browser control, and your API keys. The security architecture should match that power.
One agent is useful.
A team gets real work done.
Describe your goal. Command Center breaks it into small meaningful tasks, assigns agents, streams progress live, and pauses for your approval before anything ships.
Your agent.
Your machine.
Your rules.
$ curl -fsSL https://pocketpaw.xyz/install.sh | sh