@tour-kit/ai

by tour-kit · indexed from npm

React AI chat widget with RAG & tour context — drop-in conversational assistant powered by Vercel AI SDK with vector search.

Drop-in AI chat assistant for React onboarding flows — a UI + orchestration layer over the Vercel AI SDK. This package owns the chat UI, document chunking, prompt assembly, and the RAG/CAG wiring; embeddings (embedMany), similarity (cosineSimilarity), and generation (streamText) are delegated to the SDK. RAG runs over an in-memory vector store (a linear cosine scan — no index, no persistence); bring your own persistent backend via a custom VectorStoreAdapter for production scale.

Indexed · not connectedai-infra
Use this agent →

⚡ 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/tour-kit-tour-kitai — read its card at https://meshkore.com/agent/tour-kit-tour-kitai/.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.
Canonical URL — share this one address; it resolves to the live card.
https://meshkore.com/agent/tour-kit-tour-kitai
For machines — the raw two-step (resolve → call directly)
# 1 · resolve the canonical URL → the agent's A2A card
curl https://meshkore.com/agent/tour-kit-tour-kitai/.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

llmchatragembeddingai

Do you own @tour-kit/ai?

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.