DreamerOS is answering right now. Last checked 1 min ago.
Your intent, in every AI call - every model means what you meant, not what it guessed.
The linked repository no longer exists on GitHub — it was deleted or made private.
Over the last week it answered 50.0% of our checks. We check every 15 minutes, so you hear about the next outage within the hour — not from your users.
Endpoint below is the one we actually reach during checks — not the one copied from a README. Last verified 1 min ago.
claude mcp add dreameros-scs-gateway --transport http https://dreameros-scs-gateway-production.up.railway.app/mcp
{
"mcpServers": {
"dreameros-scs-gateway": {
"url": "https://dreameros-scs-gateway-production.up.railway.app/mcp"
}
}
}
[mcp_servers.dreameros-scs-gateway]
url = "https://dreameros-scs-gateway-production.up.railway.app/mcp"
{
"mcpServers": {
"dreameros-scs-gateway": {
"url": "https://dreameros-scs-gateway-production.up.railway.app/mcp"
}
}
}
{
"mcpServers": {
"dreameros-scs-gateway": {
"url": "https://dreameros-scs-gateway-production.up.railway.app/mcp"
}
}
}
This endpoint answered with an authorization challenge. The server is running, and it signs you in through your browser: there is no API key to paste.
This server publishes 3 more addresses. The block above uses the one we reach during checks; the full list is under Endpoints below, and the author may intend a particular one for your client.
| URL | Transport | State | Latency | Checked |
|---|---|---|---|---|
| https://dreameros-scs-gateway-production.up.railway.app/mcp | streamable-http | sign-in | 273 ms | 3 min ago |
| https://dreameros-scs-gateway-production.up.railway.app/mcp/sse | sse | answering | 20000 ms | 1 min ago |
| https://mcp.dreameros.app/mcp | streamable-http | sign-in | 299 ms | 3 min ago |
| https://mcp.dreameros.app/mcp/sse | sse | answering | 20000 ms | 1 min ago |
Call every global AI model through one OpenAI-compatible API. One key, all models.
Deterministic intent preflight before your agent builds: six gates, keyless, no model call.
Make videos and docs with your AI agent — describe what you need, every output stays editable.
Score your judgment over AI-assisted work. Hone scores you, not the model.
Search, edit, design, and undo: everything you can do in Teamo, now from your AI assistant
Pull Deep Memory from across your Claude Code Sessions — when you need it.
Retail media measurement in Gus Dantas's own words. No model inside: every answer is text he wrote.
Shared memory for AI agents, as a graph in your own Postgres. Writes never call an LLM.
Answers built from our own checks of this server.