ai-agent

LibreTranslate

Name: LibreTranslate
Author: LibreTranslate

Free and Open Source Machine Translation API. Self-hosted, offline capable and easy to setup.

17,062 stars+71★ this week1,774 forksPythonUpdated 10/12/2026100% free · open source

What it does

LibreTranslate is a self-hosted, open-source machine translation API that allows you to translate text from one language to another without relying on external services.

When to use it

•When you need to integrate machine translation into your application without paying for a third-party API
•When you want to keep your translation data private and secure
•When you need to support languages that are not well-supported by commercial translation APIs

Ready-to-paste prompt

curl -X POST 'http://localhost:5000/translate' -H 'Content-Type: application/json' -d '{"q":"This is a test sentence.","source":"en","target":"fr"}'

Heads up: You need to have Docker installed and running on your system to use LibreTranslate, and you should be aware that the initial download of the model data may take some time due to its large size.

Saves to your device

Use with Claude

New

Skip the builder — one click puts this in Claude, Cursor, Antigravity and more.

✅ Light setup

Installs with a command or two; your AI agent can do it for you.

Try it instantly — no install

Claude Code

mkdir -p ~/.claude/skills/libretranslate && curl -fsSL https://workflowstacks.com/api/skills/libretranslate/claude-skill -o ~/.claude/skills/libretranslate/SKILL.md

Open in another AI app

Opens the app with this repo with the prompt ready to go — no copy-paste needed.

Connect the whole catalog (MCP)

claude mcp add --transport http workflowstacks https://workflowstacks.com/api/mcp

Adds a WorkflowStacks connector to Claude Code: search and load any skill here by chatting.

How LibreTranslate works

Codeflow

Free to inspect

LibreTranslate is a medium Python project (~11k lines across 34 code files, plus 10 test files). Setup is light: installs like a normal app. Reading the code is optional. Last commit this month, AGPL-3.0 license, has a test suite.

Size

Medium codebase

~11k lines · 34 code files · ~1 h to skim

Setup

One-command install

Installs like a normal app. Reading the code is optional.

Runs on

Python · Docker

No API keys detected

Python 74%HTML 11%Dockerfile 6%CSS 6%Shell 3%

Where to start reading

1
README.md
Start here — what it does and how to install it
2
AGENTS.md
The instructions the AI actually follows
3
main.py
Where the program starts running
4
pyproject.toml
Dependencies and the commands it exposes
5
libretranslate/__init__.py
Inside libretranslate/ — the main logic begins here

What's in each folder

libretranslate/Core code — the actual logic173 files

scripts/Helper scripts8 files

docker/Deployment / infrastructure5 files

db/Folder1 files

.github/CI / automation (GitHub Actions)6 files

.well-known/Tool / agent settings1 files

READMEHas testsDocumentedCI checksDocker readyAGPL-3.0 licenseUpdated this month