
OpenTrain
io.github.OpenTrain-AIPublished by GitHub account OpenTrain-AIv0.2.2Updated Oct 24, 2026
Hire human data labelers, RLHF annotators, and evaluators from your coding agent.
Overview
OpenTrain lets a coding agent hire human data labelers, RLHF annotators and evaluators through the OpenTrain platform.
- What you can do
- Connect a coding agent to the OpenTrain platform to commission human work.
- Hire human data labelers, RLHF annotators and evaluators from within the agent session.
- Use a personal API token to act on an existing OpenTrain account, or let the server register an anonymous agent account for a human to claim.
- Point the server at a different OpenTrain API base URL when needed.
- When to use it
- Useful when an agent's task needs human-labeled data, RLHF preference annotations or human evaluation rather than automated processing, and you want to request that work without leaving the coding agent.
- Requirements
- Runs locally over stdio via npx from the npm package @opentrain-ai/mcp, so Node.js is needed. An OpenTrain personal API token is supplied through the OPENTRAIN_PERSONAL_API_TOKEN environment variable; it is optional, since without it the server can register an anonymous agent account for a human to claim. OPENTRAIN_API_BASE_URL optionally overrides the default API base URL. Network access to OpenTrain is required.
Installation
In SourceWeft
- Open OpenTrain in the dashboard and add it to a workspace.
- Enable the server for the chats that should use its tools.
Desktop only via STDIO. STDIO servers start a local process, so they need the SourceWeft desktop host.
Other MCP clients
Follow the launch instructions in the repository.
README
This repository has no README.
Tools
0Version history
1- v0.2.2LatestSep 16, 2026
Score
25% of the applicable checks met
How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.
- Reached in the last 30 days25 pts
Keep the endpoint answering the MCP handshake; SourceWeft probes it every 30 days.
- Auth declared10 pts
Declare the credential headers in the registry entry, or keep the endpoint answering the probe so its auth can be classified.
- Tools listed15 pts
Answer tools/list without a credential, or ship a package that starts in a sandbox without one.
- DescriptionRequired15 pts
- Logo10 pts
- Documentation15 pts
Declare a GitHub repository with a README, or serve resource_documentation in the OAuth protected-resource metadata.
- License10 pts
Declare a license in the repository or the registry entry.