tuneloExpose local services and files to the internet through a public HTTPS URL. Designed for AI agents — when you need to let a user preview files remotely, shar...
Install via ClawdBot CLI:
clawdbot install claw-bot/tuneloGrade Fair — based on market validation, documentation quality, package completeness, maintenance status, and authenticity signals.
Calls external URL not in known-safe list
https://tunelo.net/install.shAudited Apr 17, 2026 · audit v1.0
Generated May 8, 2026
An AI agent can use tunelo serve to share project files (PDFs, images, documents) with a client who needs to review them remotely. The agent gets a public HTTPS URL instantly, allowing the client to browse and preview files without any setup.
When a developer wants to test a mobile app against a local backend, the AI agent can run tunelo http 3000 to expose the local server via a public URL. The developer can then access it from their phone for real-device testing.
To let a colleague test an API endpoint running on localhost, the AI agent uses tunelo http 8080 --private to generate a secured public URL with an access code. This provides temporary, controlled access without deploying to production.
An AI agent can share a local React dev server with stakeholders by running tunelo http 5173. Stakeholders receive a public URL to view the live demo, enabling instant feedback without hosting on a public server.
Before making files public, an AI agent can serve them locally with tunelo serve ./dist --local, providing a browser preview on localhost. This allows internal verification before sharing via tunnel.
The core service (tunelo.net) offers free public relay for tunnels up to 2 hours. This model attracts individual developers and small teams who need quick, temporary sharing without infrastructure costs.
Organizations can deploy their own relay server using tunelo's --relay option, ensuring data stays within their network. This model targets companies with compliance requirements or high security needs.
tunelo can be integrated into SaaS products (e.g., CI/CD pipelines, low-code platforms) as a built-in feature for exposing local services. This creates a seamless experience for end-users and adds value to the platform.
💬 Integration Tip
Install with a single curl command and expose services with one-line commands like 'tunelo http 3000' or 'tunelo serve .' — no configuration files or dependencies needed.
Scored May 8, 2026
Meta-skill for AI agent self-improvement. Analyzes runtime logs to detect error patterns, regressions, and inefficiencies, then generates structured improvem...
Stop waiting for prompts. Keep working.
Turn OpenClaw into a learning-loop agent with seeded workspace rules, skill promotion, reflective memory, and proactive maintenance.
Meta-agent skill for orchestrating complex tasks through autonomous sub-agents. Decomposes macro tasks into subtasks, spawns specialized sub-agents with dynamically generated SKILL.md files, coordinates file-based communication, consolidates results, and dissolves agents upon completion. MANDATORY TRIGGERS: orchestrate, multi-agent, decompose task, spawn agents, sub-agents, parallel agents, agent coordination, task breakdown, meta-agent, agent factory, delegate tasks
Complete toolkit for creating autonomous AI agents and managing Discord channels for OpenClaw. Use when setting up multi-agent systems, creating new agents, or managing Discord channel organization.
Billions decentralized identity for agents. Link agents to human identities using Billions ERC-8004 and Attestation Registries. Verify and generate authentic...