Actuellement en version bêta
Machine translation development and deployment on rails, built with low-resource and Indigenous language communities in mind.
We are putting the tools on rails: a project on your own computer that takes you from the files your community keeps to a measured model, while the people who hold the language decide where its sentences may go, what counts as good enough, and what ships. That release is being prepared; the rails promise you will know how good a model is — not that it is good. Today's releases are below.
Today's releases, on npm and PyPI — the CLI and the MCP server are source-available and free for noncommercial use; the evaluation harness is open source (AGPL):
Set up Champollion in this project. Champollion is machine translation development and deployment on rails, built with low-resource and Indigenous language communities in mind. 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. 4. Do not open or read my data files yourself; ask me first. Asking is not a lock — for protected text, use an agent whose model runs on this computer.
Ou installez les outils vous-même :
npm install champollionCLI de traductionnpx -y champollion-mcp-serverServeur MCP — pour les agents IApipx install mt-eval-harnessHarness d'évaluationcurl -fsSL https://champollion.dev/run_queue | bash -s -- --budget 2
Le site lui-même est en version bêta fermée pendant que nous terminons de revérifier nos sources, nos licences et nos déclarations.
Il ouvrira lorsque les vérifications seront terminées — et effectuées correctement.
Questions, corrections ou demande d'accès anticipé : info@champollion.dev. Les corrections concernant toute donnée chiffrée citée sont particulièrement les bienvenues.