Now in beta

Champollion is open digital infrastructure for improving machine translation in low-resource languages — built for developers, language warriors, and anyone else working on the problem.

It combines a cited language index covering 7,900+ languages, a translation CLI, an evaluation harness that scores translation methods from any developer, and sovereignty machinery meant to ensure communities govern the data they contribute.

The source-available releases — free for noncommercial use — are live on npm and PyPI today:

Copies a setup prompt for your AI coding tool

Set up Champollion in this project. Champollion is open machine-translation infrastructure for low-resource languages: a translation CLI, a public benchmark queue, and a cited index of 7,900+ languages.

1. Read https://champollion.dev/for-agents.md — it lists every tool and machine-readable endpoint.
2. Add the Champollion MCP server using whatever mechanism this environment supports. It runs over stdio as: npx -y champollion-mcp-server
3. Confirm by listing the MCP server's tools, then tell me which ones are available.

Or install the tools yourself:

npm install champollionTranslation CLI

npx -y champollion-mcp-serverMCP server — for AI agents

pipx install mt-eval-harnessEvaluation harness

Contribute compute to the project queue ?The queue is a ranked list of translation benchmarks nobody has run yet. The script installs the harness, prices the work and asks before spending, then runs the top of the queue with your own API key — up to the budget you set — publishing each result to the public board.

curl -fsSL https://champollion.dev/run_queue | bash -s -- --budget 2

The site itself is in closed beta while we finish re-verifying our sources, licences, and claims.

It will open when the checking is done — and done right.

Questions, corrections, or a request for early access: info@champollion.dev. Corrections to any cited figure are especially welcome.