# nlweb-ai/NLWeb

Main reference implementation for NLWeb, implemented in Python.

Repository: https://github.com/nlweb-ai/NLWeb
Canonical: https://ross.abutalabs.com/products/nlweb
Language: Python
License: MIT
License Family: permissive
Last push: 2026-08-11T20:35:58+00:00

## Health v2 (maintenance only)
Score: 63/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 97, release rhythm 35, longevity 35
- inputs: {"age_days": 492, "days_push": 22, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 6250, forks 699 (observed 2026-08-28T04:09:40.990775+00:00)

## What it is
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
- artifact type: framework
- maturity: active
- function: mcp, rag, chatbot, web-framework, search-engine, api-framework
- domain: artificial-intelligence, web-development, chatbots, apis
- platform: python, windows, self-hosted
- tags: schema-org, conversational-search, mcp-server, natural-language-interface, vector-search, a2a, ai-agents, retrieval-augmented-generation, linux, macos, web-server

## Member repositories
- nlweb-ai/NLWeb (main) score 63

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:09:40.990775+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T17:47:08.890161+00:00, confidence not recorded.
  - readme: https://github.com/nlweb-ai/NLWeb (fetched 2026-08-28T04:09:40.990775+00:00, sha bf3dc481d838)
- Data as of 2026-08-30T08:39:29.467469+00:00.