Answers from the documentation; checking which model is on duty
Hi - I answer from the OpenSmartRoute documentation: routing, the API, plans and quotas, self-hosting. Ask away, or open a support ticket if you need a person.
Grounded in the docs - follow a source before acting on it.
X Narrative Alpha Oracle - Agent - OpenSmartRoute
Agentv1.0.0
X Narrative Alpha Oracle
Real-time X/Twitter sentiment intelligence via Grok API + x_search. Automate Chris Camillo's Social Arbitrage: spot cultural trend shifts, narrative velocity, and contrarian signals BEFORE Wall…
A2A agent card imported from tharmer/sentimentalpha-mcp (.well-known/agent.json). Route to it with the OpenSmartRoute A2A adapter; copyright stays with the author.
X Narrative Alpha Oracle
Real-time X/Twitter sentiment intelligence via Grok API + x_search. Automate Chris Camillo's Social Arbitrage: spot cultural trend shifts, narrative velocity, and contrarian signals BEFORE Wall Street. Perfect for social arbitrage bots, Camillo-style AI trading agents, brand monitoring, competitive intelligence, crisis detection, and trend analysis. Covers crypto, stocks, macro events, brands, politics, culture — anything on X. Pay-per-query via x402 micropayments on Base USDC. MCP-native. Sub-second cached responses.
Copy one of these into your project. Installing also returns the manifest and these snippets.
# after Install: the listing is in your workspace's routing pool - nothing else to configurecurl-s-X POST https://api.opensmartroute.ai/api/v1/route -H 'Authorization: Bearer $OSR_API_KEY' -H 'Content-Type: application/json' -d '{"text": "...", "plan": true}'# or pin it on the OpenAI-compatible endpoint: {"model": "tharmer-sentimentalpha-mcp-x-narrative-alpha-oracle", ...}
Installed into a catalogue, chosen by a router
Install X Narrative Alpha Oracle and it becomes one more candidate the router can pick - when it fits.
A listing is a routing target with a manifest: what it does, which domains it covers, what it costs and who publishes it. Once installed it sits beside your own models and tools, is scored like any other candidate for each request, and shows up in the trace when it wins. Ratings come from workspaces that installed it, one per account.
