tap vs OpenTrain
tap is a plugin bundle for AI coding tools published by HUA-Labs. Marketplaces we read that list it: 1 (Claude Code: claude-plugins-community). OpenTrain is an MCP server published by OpenTrain-AI. Marketplaces we read that list it: 1 (Official MCP Registry). As of our marketplace pass on 2026-10-14. This pair was picked by a reader, not by our comparison rule, so search engines are asked not to index the page.
Where each is published
| Marketplace |  tap | |
|---|---|---|
| Claude Code: claude-plugins-community | Listed Version: 0.1.0 Forks (GitHub): 7 Stars (GitHub): 37 Not marked · First seen |
Not listed |
| Official MCP Registry | Not listed | Listed Version: 0.2.2 Downloads/month (npm): 3 778 Downloads/week (npm): 941 Not marked · First seen |
Each figure is the marketplace's own and is never added up across marketplaces. A marketplace that publishes no figure shows none: no number is not zero.
The facts side by side
| Fact | tap | OpenTrain |
|---|---|---|
| Marketplaces that list it | 1 | 1 |
| Stars (GitHub) (differs) | 37 | No figure on GitHub |
| Forks (GitHub) (differs) | 7 | No figure on GitHub |
| Last release | Not published | Not published |
| Where it runs (differs) | Installs as a plugin bundle | On your machine (@opentrain-ai/mcp) |
| Transport (differs) | Not stated | stdio |
| Tools it declares | Not published | Not published |
| Environment variables it asks for (differs) | Not published | 2, secrets among them: 1 |
| Hooks it runs (differs) | 1 | Not published |
| Parts of the bundle (differs) | 7 | Not a bundle |
| Licence (differs) | MIT | Not stated |
| Repository (differs) | github.com/hua-labs/tap | github.com/opentrain-ai/opentrain-platform-monorepo |
| Changes in the last 7 days | 0 | 0 |
| First seen (differs) | 2026-10-12 | 2026-10-11 |
Lines where the two differ have a tinted background and bold values. Where the data itself says which value is better (more marketplaces, a larger figure of the same marketplace, a fresher release, a verified mark on a marketplace that lists both), the better one is also marked green with ▲ and the worse one red with ▼. Where it runs, the transport, the tools, the settings, hooks, the bundle's parts, the licence and the week's changes are marked only as different: more or fewer is not better in itself.
What each says it does
tap
Cross-model AI agent communication protocol. Connect Claude, Codex, and Gemini agents through a shared file-based messaging layer. Features include: control tower orchestration, cross-model code review routing, broadcast/DM/CC messaging, agent heartbeat monitoring, mission tracking with kanban board, web GUI dashboard, and generational knowledge transfer through retros, letters, and findings. Other tools give agents instructions. tap gives them context.
OpenTrain
Hire human data labelers, RLHF annotators, and evaluators from your coding agent.
How to run each
tap As a Claude Code plugin
/plugin marketplace add anthropics/claude-plugins-community
/plugin install tap@claude-communityOpenTrain As a local MCP server: npm package
claude mcp add --env "OPENTRAIN_PERSONAL_API_TOKEN=<YOUR_OPENTRAIN_PERSONAL_API_TOKEN>" --transport stdio opentrain -- npx -y @opentrain-ai/mcpRequires: OPENTRAIN_PERSONAL_API_TOKEN (secret)
Commands built only from what the marketplaces declare; the full set for every client is on each card.
Tools each declares
Neither one's marketplaces publish a list of tools, so there is nothing to compare.
Settings each asks for
The marketplaces of tap publish no settings it asks for, so we do not compare settings.
What it can do: tap · What it can do: OpenTrain · Compare two other plugins
Data comes from the public marketplace file https://github.com/anthropics/claude-plugins-community/blob/HEAD/.claude-plugin/marketplace.json. Data comes from the Official MCP Registry (registry.modelcontextprotocol.io), CC0 1.0. Figures come from our own regular passes over the marketplaces, last read on . We publish no contact details for plugin publishers.