Newsletter
Join the HoTools Community
Get weekly updates on the best online tools, productivity tips, and exclusive resources delivered straight to your inbox
Paseo: Run coding agents like Claude, Codex, and OpenCode from anywhere. Self-hosted, multi-provider, open-source.
Cookey enables AI agents to securely log into websites by relaying mobile sessions to the terminal.
LiteLLM: AI Gateway for 100+ LLMs with OpenAI format, features like spend tracking, fallbacks, and rate limiting.
The AI community building the future of AI through open source and open science.
The proactive AI assistant in your iMessage, WhatsApp, and more. Texts like a human, really knows you, and integrates with your life in dozens of ways.
Paseo is a powerful, open-source tool that allows you to run various coding agents, including Claude Code, Codex, and OpenCode, from your desktop, phone, or terminal. It offers a self-hosted, multi-provider solution designed for seamless integration into your development workflow. Whether you're on your MacBook Pro or a Hetzner VM, Paseo provides a consistent interface to manage and interact with your AI coding assistants.
Paseo is free and open-source. You will need your own credentials for the coding agents you choose to use.
+−Is Paseo free? Yes, Paseo is free and open-source. You are responsible for your own agent credentials. Voice features are local-first by default but can optionally use OpenAI speech providers.
+−Does my code leave my machine? No, Paseo runs agents locally and does not send your code anywhere. For remote access, secure options like an E2E encrypted relay or direct network connections are available.
+−What agents are supported? Paseo supports Claude Code, Codex, and OpenCode by running their official CLIs as subprocesses. It does not modify or wrap their behavior.
+−Can I use Paseo without the desktop app?
Yes, you can run the Paseo daemon headless using the CLI (npm install -g @getpaseo/cli && paseo) and connect via the web app, mobile app, or CLI.
+−How does the voice functionality work? By default, voice processing (speech-to-text and text-to-speech) runs locally on your device. You can optionally configure OpenAI speech providers for enhanced quality.
+−Can I connect from outside my network? Yes, you can use the hosted E2E encrypted relay, set up your own tunnel (e.g., Tailscale, Cloudflare Tunnel), or expose the daemon port directly.