cd /news/ai-agents/lumi-from-learning-rag-to-an-open-so… · home › topics › ai-agents › article
[ARTICLE · art-171987] src=github.com ↗ pub= topic=ai-agents verified=true sentiment=↑ positive

Lumi, from learning RAG to an open-source, self-hosted chatbot for agencies

Nieve Consulting has released Lumi, an open-source, self-hosted AI website concierge for agencies and consultancies that answers visitor questions from a business's own knowledge sources, asks configurable qualification questions, and hands off to booking or enquiries. Lumi runs as a complete product via Docker Compose with only an OpenAI API key and a Docker host, one business per installation, and ships a GraphQL API, a streaming agents API and an MCP server for ChatGPT and other MCP clients, with English and Spanish interface support. Nieve also offers a managed hosting option and says agencies may adapt Lumi for their clients and offer implementation or hosting services under its license.

key takeaway

Lumi self-hosts via Docker Compose with only an OpenAI API key and a Docker host, one business per installation, and exposes a GraphQL API, a streaming agents API and an MCP server for ChatGPT and other MCP clients.

read4 min views7 publishedNov 18, 2026
Lumi, from learning RAG to an open-source, self-hosted chatbot for agencies
Image: Michielbdejong (auto-discovered)

An AI website concierge for service businesses.

Lumi answers your website visitors' questions from your business knowledge, asks the questions that tell you whether they're a fit, and helps them book a conversation with your team or send an enquiry. Your team manages the knowledge and reviews conversations in an admin interface.

Read the documentation at docs.lumi.nieve.ai · Try Lumi · Getting started · Self-hosting · Releases · Contributing

Lumi is for consultancies, agencies, studios, practices and anyone selling expertise. A prospective client arrives with a question, such as "Have you delivered a project like ours?". Lumi looks up the relevant company information, clients and projects, answers, and helps the visitor take the next step.

Nieve Consulting builds and maintains Lumi, and runs it on its own website: try it at chat.lumi.nieve.ai. Agencies are welcome to adapt it for their clients and to offer implementation or hosting services under the license.

  • Business knowledge: answers from your website, with optional team, project, client and job-opening sources; seeKnowledge sources .

  • Visitor conversations: streaming responses and persisted conversation state.

  • Qualification and handoff: configurable qualification questions, a booking page or in-chat Google Calendar booking, and enquiries delivered by email or webhook; seeQualification, booking and enquiries .

  • Embeddable chat: a launcher for your website that opens the chat in an iframe; seeEmbedding the widget .

  • English and Spanish: localized interface text and widget language selection.

  • Team administration: knowledge management, conversation review and model-usage visibility; seeThe admin interface .

  • Developer integrations: aGraphQL API , astreaming agents API and anMCP server for ChatGPT and other MCP clients.

  • Self-host it. A Docker Compose installation runs the complete product on a host you control, one business per installation, with only an OpenAI API key and a host with Docker. Follow theSelf-hosting guide .

- **Let Nieve run it.** With Nieve's managed option, Nieve hosts and operates Lumi for you; see[lumi.nieve.ai](https://lumi.nieve.ai) .

Both run the same open-source product described in the [documentation](https://docs.lumi.nieve.ai).

To install Lumi for a business, the Self-hosting guide takes you from a release to a running installation with Docker Compose: the settings to fill in, initializing the database, setting up the business, embedding the widget and checking the result.

To work on Lumi itself, Getting started sets up the development servers and local services.

Lumi is actively maintained and released regularly. Each release has notes on what changed, and every installation upgrades to a release on its own schedule; see Upgrades. Releases published with the image workflow also provide versioned backend and frontend images for Linux x86-64 and arm64 in GitHub Container Registry; the self-hosting guide explains down them or building from source. The roadmap describes where Lumi is heading.

Directory Purpose
frontend/ Public chat, widget iframe, onboarding wizard and admin interface
backend/ GraphQL, streaming agents, business services, and integrations
| [widget/](https://github.com/nieve-consulting/lumi/blob/main/widget/README.md) | Embeddable website launcher | 
| [packages/shared-contracts/](https://github.com/nieve-consulting/lumi/blob/main/packages/shared-contracts/README.md) | Shared chat schemas and types | 

| deploy/ | Container installation: Compose stack, proxy and settings |

| local-dev/ | Local services for development: database, storage and proxy | Architecture gives the system overview, Data and privacy what an installation stores and sends, Operations upgrades, export and deletion, and Security trust boundaries, limits and the operator checklist.

  • Questions and installation help: seeSupport .

  • Contributing: documentation improvements, reproducible bug reports and contributions that make Lumi easier to adopt are welcome. ReadContributing for the workflow and required checks. The documentation has its own repository,nieve-consulting/lumi-docs .

  • Vulnerabilities: report them privately, asSecurity describes. Copyright © 2024–2026 Nieve Consulting Services S.L.

Lumi is licensed under the GNU Affero General Public License v3 (AGPL v3), version 3 only. If you modify Lumi and let users interact with that version over a network, you must prominently offer those users access to the corresponding source under the license.

The embeddable widget in widget/, which runs on the websites that embed Lumi's chat, is licensed under the Apache License 2.0, and so is the script built from it that every installation serves at /scripts/lumi-widget.bundle.umd.js (committed as frontend/public/scripts/lumi-widget.bundle.umd.js; release images build it from widget/). Websites can embed it without taking on the AGPL's obligations.

Dependencies retain their own licenses.

Maintained by Nieve Consulting. See Governance for how contributions and product decisions are handled.

── more in #ai-agents 4 stories · sorted by recency
── more on @nieve consulting 3 stories trending now
sponsored brought to you by zahid.host 4,200+ EU-deployed projects
reading about agents? ship yours in a single git push.

Run your AI side-project on zahid.host

EU-based hosting, git-push deploys, automatic HTTPS, no cold starts. Free tier with a custom domain — perfect for shipping the agent you just read about.

$git push zahid main
→ Live at https://your-agent.zahid.host ✓
Get free account → Pricing
from €0/mo · no card required
LIVE [news/lumi-from-learning-r…] indexed:0 read:4min 2026-11-18 · —