xinyin025/LangBot
1
0
Fork 0
mirror of https://github.com/langbot-app/LangBot.git synced 2026-10-29 11:56:02 +08:00
Code Issues Packages Projects Releases Wiki Activity

docs: keep Docker setup simple and cross-platform (#129)

Browse Source 
Co-authored-by: dadachann <[email protected]>
This commit is contained in:
Hyu
2026-09-08 02:43:10 +08:00
committed by GitHub
co-authored by dadachann
parent e55f402c70
commit a86ecb4e97
4 changed files with 72 additions and 136 deletions
Download Patch File Download Diff File Expand all files Collapse all files
en/deploy/langbot/docker.mdx
+18 -40
View File
@@ -1,74 +1,52 @@
---
title: "Docker Deployment"
description: "Deploy LangBot with Docker and Docker Compose. Run an open-source multi-platform AI chatbot for Discord, Telegram, WeChat and more in minutes."
description: "Deploy LangBot with Docker Compose on Windows, Linux, or macOS."
---
## 1. Prepare your environment
Install Git, Docker, and Docker Compose, and make sure your account can run Docker commands.
- Install Git.
- **Windows / macOS**: install and start Docker Desktop.
- **Linux**: install Docker and Docker Compose.
## 2. Download the project
We recommend `/opt/LangBot`. Avoid restricted directories such as `/root` and `/etc`, where security rules can block sandbox features. The example below uses `/opt`; you can choose another deployment directory that your account can write to.
Choose a regular directory that you can write to. On Linux, avoid system directories such as `/root` and `/etc`; we recommend a location under `/opt` so sandbox features are not blocked by security rules.
Open a terminal in the directory where you want to store the project (PowerShell works on Windows), then run each line:
```bash
cd /opt
git clone https://github.com/langbot-app/LangBot
cd LangBot/docker
```
### Mainland China: optional image mirror
### Mainland China: change the image source before startup (optional)
If pulling images from Docker Hub is slow, edit `docker-compose.yaml` in the current directory **before starting the services**. Replace every occurrence of `rockchin/langbot:latest` with:
If Docker Hub downloads are slow, edit `LangBot/docker/docker-compose.yaml` first. Replace every occurrence of `rockchin/langbot:latest` with:
```text
docker.langbot.app/langbot-public/rockchin/langbot:latest
```
Save the file, then continue to the next step.
Save the file before starting. No other configuration changes are needed.
## 3. Start the services
## 3. Start LangBot
<Accordion title="Public servers: set access tokens before starting">
On a public server, set access tokens for the supporting services and avoid exposing runtime ports directly to the Internet.
<Note>
On a server, use a firewall to restrict dashboard and runtime ports to trusted sources only.
</Note>
Run this command twice to generate two different random values:
```bash
openssl rand -hex 32
```
Add the following settings to `.env` in the current directory, replacing the placeholders with the generated values. If either setting already exists, update it instead:
```dotenv
LANGBOT_PLUGIN_RUNTIME_CONTROL_TOKEN=<first-random-value>
LANGBOT_BOX_CONTROL_TOKEN=<second-random-value>
```
Compose passes the tokens to the matching services automatically; no other configuration changes are needed. Keep `.env` safe and do not commit it to a repository.
</Accordion>
Run from `LangBot/docker`:
In the same terminal, run:
```bash
docker compose --profile all up -d
```
This starts LangBot and its supporting services in the background, including sandbox, stdio MCP, and skill features.
The first startup downloads the container images. On Windows / macOS, keep Docker Desktop running.
## 4. Open the dashboard
Visit the appropriate address in your browser:
- **Local installation**: `http://127.0.0.1:5300`
- **Server installation**: `http://YOUR_SERVER_IP:5300`. Make sure the firewall allows your access to port `5300`.
- **Local installation**: open `http://localhost:5300`.
- **Server installation**: open `http://YOUR_SERVER_IP:5300` and make sure the firewall allows your device to access this port.
Follow the on-screen initialization steps, then add a [model](/en/usage/models/readme) and a [bot](/en/usage/platforms/readme).
If the page does not open, check the startup logs from the deployment directory:
```bash
docker compose --profile all logs --tail=100
```
For further configuration, see the [sandbox](/en/usage/sandbox/readme) and [skills](/en/usage/skills/readme) guides.