ythx-101ythx-101/grok-bridge/llms.txt

grok-bridge

llms.txt163 starsChanged 3 days agoMITView on GitHub

grok-bridge turns the Grok web app (grok.com) in your signed-in Safari into a local REST API and CLI on macOS, so scripts and AI agents can call Grok without an xAI API key. 在 macOS 上把已登录 Safari 的 Grok 变成本地 REST API / CLI，无需 API key。 Unofficial project, not affiliated with xAI. Current release: v3.1.1. Python 3 stdlib only, MIT.

Sends data out

In this repositoryOne other file it gives its agents.
- SKILL.mdSkill

The file

We split this llms.txt into the rules it gives an agent

2 rules. About 0 are common, 1 is distinctive, and 1 is very specific to this project.

≈0
Common · estimate
Many files like this have a rule of this kind.
≈1
Distinctive · estimate
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.

Common
Distinctive
Very specific

Very specific:
No Accessibility permission by default (only the optional --foreground-fallback uses System Events)
line 10
Distinctive:
No streaming; requests are serialized.
line 26

≈ “Common” is an estimate: at least 1 in 5 of the 3,592 llms.txt files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.

Files

llms.txt

# grok-bridge

> grok-bridge turns the Grok web app (grok.com) in your signed-in Safari into a local REST API and CLI on macOS, so scripts and AI agents can call Grok without an xAI API key. 在 macOS 上把已登录 Safari 的 Grok 变成本地 REST API / CLI，无需 API key。

Unofficial project, not affiliated with xAI. Current release: v3.1.1. Python 3 stdlib only, MIT.

## Requirements
- macOS with Safari, signed in to https://grok.com (free or SuperGrok)
- Safari > Settings > Advanced > Show features for web developers; Safari > Develop > Allow JavaScript from Apple Events
- No Accessibility permission by default (only the optional --foreground-fallback uses System Events)

## Quick start
- `python3 scripts/grok_bridge.py --doctor`
- `python3 scripts/grok_bridge.py --bind 127.0.0.1 --port 19998`
- `curl -X POST http://127.0.0.1:19998/chat -H "Content-Type: application/json" -d '{"prompt":"hello","timeout":60}'`

## Endpoints
- POST /chat: body {"prompt": "<non-empty string>", "timeout": <seconds, default 120>}; returns {"status":"ok","response":"...","elapsed":...}, or status "timeout" with a partial response, or {"status":"error","error":"..."}; invalid input returns HTTP 400
- POST /new: start a new conversation
- GET /health: status, url (redacted), on_grok, version, dedicated_tab, tab_name, foreground_fallback
- GET /history: read the current page conversation

## Limitations
- Unofficial; single user, local machine; macOS + Safari only
- Binds 127.0.0.1 by default; use an SSH tunnel for remote access
- No streaming; requests are serialized; grok.com UI changes can break selectors
- Uses a dedicated Safari tab (window.name="grok-bridge-agent") unless --shared-tab is set

## Docs
- [README](https://github.com/ythx-101/grok-bridge/blob/main/README.md)
- [SKILL.md](https://github.com/ythx-101/grok-bridge/blob/main/SKILL.md)
- [Release notes v3.1.1](https://github.com/ythx-101/grok-bridge/blob/main/docs/release-v3.1.1.md)
- [Review playbook](https://github.com/ythx-101/grok-bridge/blob/main/docs/review-playbook.md)

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

It worked
Partly
It didn't

What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free