Gradio Tunneling
English | 简体中文
A tunneling tool that provides reverse proxy functionality for non-Gradio web services, allowing you to expose your local services to the internet with customizable subdomains.
https://github.com/arkohut/gradio-tunneling/assets/39525455/f38b7db2-517b-4e30-b15e-8787485095d0
Use with AI coding agents
This repo ships an agent skill at .agents/skills/gradio-tunneling/ so AI coding agents (pi, and others that support the Agent Skills standard) can set up tunnels for you on request — just say "expose port 7860" / “内网穿透 7860". It includes a helper script that starts the tunnel in the background, waits for the public URL, and stops it later:
bash .agents/skills/gradio-tunneling/scripts/tunnel.sh 7860 # prints PUBLIC_URL=...
bash .agents/skills/gradio-tunneling/scripts/tunnel.sh 7860 myapp # with subdomain
bash .agents/skills/gradio-tunneling/scripts/tunnel.sh --stop 7860
Setup
Requires Python 3.8 or higher.
Since gradio-tunneling is a CLI tool, installing it into an isolated environment with pipx or uv tool is recommended — it keeps the gradio-tun command on your PATH without touching your project venvs.
# Recommended: uv tool (fast, no extra setup if you already use uv)
uv tool install gradio-tunneling
# Or: pipx
pipx install gradio-tunneling
# Or: plain pip (works fine, but pollutes the current environment)
pip install gradio-tunneling
To upgrade later:
uv tool upgrade gradio-tunneling
# or
pipx upgrade gradio-tunneling
Once installed, two equivalent commands are available on your PATH:
gradio-tun— short form (used throughout this README)gradio-tunneling— long form, kept for backward compatibility
Verify it's reachable:
gradio-tun --help
Run tunnel
You can specify the port in two ways:
gradio-tun 7860 [--sd your-subdomain]
# or
gradio-tun --port 7860 [--sd your-subdomain]
PORTor--port PORT: Specify the port number for the tunnel--sd: (Optional) Specify a custom subdomain. Note: For security reasons, your input will be converted into a unique string. Using the same--sdvalue will always generate the same unique string.
Examples:
# Using positional port argument
gradio-tun 7860
# Using --port flag
gradio-tun --port 7860
# With custom subdomain
gradio-tun 7860 --sd mycustomsubdomain
# This will generate a URL with a unique string (e.g., abc123def...)
# Using "mycustomsubdomain" again will generate the same unique string
About Custom Subdomains
When you use the --sd option:
- The subdomain you provide won't be used directly in the URL
- Instead, it will be converted into a unique string for security
- If you use the same
--sdvalue later, you'll get the same unique string - This helps you get consistent URLs while maintaining security
For example, if you always use --sd myapp, you'll get the same unique subdomain each time, making your URL predictable for your users.
Important Note
The generated tunnel URL will expire after 72 hours. After expiration, you'll need to restart the tunnel to get a new URL. If you're using a custom subdomain with --sd, using the same value will generate the same subdomain in the new URL.
Metadata
Release files for gradio-tunneling 0.9.1
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | |
|---|---|---|---|
| gradio_tunneling-0.9.1.tar.gz | 22.9 MB | Details |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Reset |
|---|---|---|---|---|
| gradio_tunneling-0.9.1-py3-none-any.whl | Python 3 | none | any | Details |
Total release size: 46.0 MB
Release files / gradio_tunneling-0.9.1.tar.gz
| Download URL | gradio_tunneling-0.9.1.tar.gz |
|---|---|
| Size | 22.9 MB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
a6912d4d3990dfafda061f95ae94622584c49cafde9a864b6b9117f11ec1a298
|
|
BLAKE2b-256 checksum How to use checksums |
c219631d07f08e5b3638f044ebc0f50b580cea5658fed6bd2b0fe7ac34c482e9
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
twine/7.0.0 CPython/3.13.14
|
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
PyPI Publish Attestation
PyPI verified that this artifact, at this checksum, originated from the publisher listed below.
Signed by GitHub Actions, verified by PyPI on Oct 10, 2026.
Transparency logRelease files / gradio_tunneling-0.9.1-py3-none-any.whl
| Download URL | gradio_tunneling-0.9.1-py3-none-any.whl |
|---|---|
| Size | 23.0 MB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
4687dbc37b6d99bc34c84bbb4c59f4e31809fa63ae02b9580108791fec7775c0
|
|
BLAKE2b-256 checksum How to use checksums |
0d109ad04f955adbed251258345dd35b7560f39a82d4aae8b040e128b12db60a
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
twine/7.0.0 CPython/3.13.14
|
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
PyPI Publish Attestation
PyPI verified that this artifact, at this checksum, originated from the publisher listed below.
Signed by GitHub Actions, verified by PyPI on Oct 10, 2026.
Transparency log