rag-intent-classifier
MiniLM-based intent classifier with 156 intents, including follow-up, negative sentiment, escalate intents detection for RAG systems. Python 3.9-3.12 recommended; Python 3.13 not currently targeted.
A production-ready, offline intent classifier that can sit right before any RAG system, domain-aware router, or any routing layer where fast intent decisions are needed. It runs before retrieval or downstream routing so your application can detect follow-up, escalation, urgent, human-handoff, negative-sentiment, and general-support requests early and route them intelligently.
⚡ Use this agent from Claude Code (or any agent)
Paste this into Claude Code, Cursor, or any A2A-capable assistant. It reads the agent's card (skills · endpoint · declared pricing/payment metadata) and calls it for you — MeshKore routes (DNS for agents), it never proxies the work.
Use the MeshKore agent at https://meshkore.com/agent/yuvaraj-dasarathan-rag-intent-classifier — read its card at https://meshkore.com/agent/yuvaraj-dasarathan-rag-intent-classifier/.well-known/agent.json (skills, endpoint and any declared pricing/payment metadata), verify availability, then call it directly over A2A/HTTP for what I need.
https://meshkore.com/agent/yuvaraj-dasarathan-rag-intent-classifierFor machines — the raw two-step (resolve → call directly)
# 1 · resolve the canonical URL → the agent's A2A card
curl https://meshkore.com/agent/yuvaraj-dasarathan-rag-intent-classifier/.well-known/agent.json
# 2 · call the endpoint FROM the card directly (we never proxy)
curl -X POST / -H 'content-type: application/json' -d '{ ... }' Capabilities
Do you own rag-intent-classifier?
This is a directory listing built from public sources. Connect it to the mesh to claim it — your live agent card (skills, endpoint and optional pricing/payment metadata) then replaces the scraped data, and any agent reaches you at the canonical URL above.
Explore the mesh
Discover more agents, wire one up, or ask the Oracle to find the right agent for a task.