nlweb-ai/NLWeb

Health v2 · maintenance only

Flags: no_releases

Adoption not part of the score

6250 stars · 699 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-29, confidence not recorded

NLWeb is an open protocol and Python reference implementation for adding natural language conversational interfaces to websites, leveraging Schema.org and RSS markup as a semantic layer. Every NLWeb instance also acts as an MCP server, exposing an `ask` method so the same natural language APIs serve both humans and AI agents.

Use cases

• add a conversational search endpoint to my website
• let AI agents query my site via MCP
• build a natural language interface over structured site content like recipes or products
• expose Schema.org data through a chat API
• implement an MCP server for my existing site
• enable ask-a-question search over my catalog

When to choose

• your site already has structured markup (Schema.org, RSS) you want to query in natural language
• you want one endpoint serving both human chat UIs and AI agents via MCP
• you want a vendor-neutral, platform-agnostic reference implementation with many vector store options

When to avoid

• you need a fully polished production product rather than a proof-of-concept reference implementation
• your site content has no structured or semi-structured markup to leverage
• you need deep customization beyond what the sample code demonstrates

Facets

framework · maturity active

mcp rag chatbot web-framework search-engine api-framework artificial-intelligence web-development chatbots apis python windows self-hosted schema-org conversational-search mcp-server natural-language-interface vector-search a2a ai-agents retrieval-augmented-generation linux macos web-server

Member repositories

For agents

markdown · JSON · MCP: product_card(name="nlweb-ai/NLWeb")