Show HN: Interakt – open-source self-hosted search and AI chat for your website

Alpha Solutions released Interakt, an MIT-licensed open-source, self-hosted search and AI chat platform for websites, available via git clone from its GitHub repository. Interakt combines hybrid keyword and vector search on Elasticsearch 9 or Azure AI Search with grounded chat pipelines, MCP server support, and bring-your-own-model options including OpenAI, OpenAI-compatible endpoints, and Ollama, requiring Node.js 24 and Docker. The platform ships drop-in Preact and Shadow DOM widgets, versioned prompts, and a separate analytics database, and Alpha Solutions runs it on Azure Container Apps.

Open-source, self-hosted search and AI chat for your website, grounded in your own data. Website https://interakt.app · Documentation https://docs.interakt.app · API Reference https://docs.interakt.app/api/ · Integrations https://docs.interakt.app/integrations/ · Discussions https://github.com/alphasolutionsrepo/interakt/discussions Interakt puts a search box and a chat window in front of your users without you assembling the pieces yourself. Point it at your data, decide how it should behave in the admin dashboard, and paste a snippet into your site. Underneath is a curated stack: a search engine, an AI provider, a chat pipeline, a versioned prompt library and an analytics database. You see one dashboard, one API and two widgets. - Search that understands intent. Keyword, semantic or hybrid, with facets, synonyms, autocomplete and AI query understanding. - Chat that knows your data. Answers are grounded in your indexes through tools, streamed, with optional citations, and kept on topic by guardrails. - Analytics that show what works. Search events, chat sessions and execution traces land in a separate analytics database, with dashboards and an analytics assistant. | <sub Backend setup From git clone to localhost:3000</sub | <sub AI search and a sales assistant Interakt on a Medusa storefront</sub | <sub Managing the integration The admin side of the Medusa setup</sub | | 🔍 Hybrid search Keyword and vector results fused with reciprocal rank fusion, on Elasticsearch 9 or Azure AI Search. Facets, sorting, synonyms and stop words per index. | 💬 Grounded chat A deterministic pipeline plan → retrieve → synthesize or an agentic loop, chosen per experience. Streaming responses, with optional inline or footnote citations. | | 🧩 Tools and MCP Every index ships with search, lookup, inspect and enumerate tools. Add custom HTTP tools, or connect MCP servers over Streamable HTTP or SSE. | 🧠 Bring your own model OpenAI, OpenAI-compatible endpoints through a custom base URL, or Ollama for fully local inference. Choose the provider per experience. | | 📦 Drop-in widgets Preact and Shadow DOM, loaded from a single script bundle. Search and chat widgets that work on any site, no framework required. | 📝 Versioned prompts Every pipeline step is an editable template with history and rollback. Tune behaviour without redeploying. | | 🛡️ Guardrails and credentials Topic gating and greeting detection. Read-only public access tokens, server-side ingestion keys, and an encrypted secrets vault. | 🏠 Self-hosted One Docker image, Postgres with pgvector, and Elasticsearch or Azure AI Search. Runs wherever Docker runs; Alpha Solutions runs it on Azure Container Apps. MIT licensed. | php flowchart LR D "Your data<br/ catalog · docs · CMS · files" -- IX "Search index" IX -- SE "Search experience" IX -- "tools" -- AE "AI chat experience" T "Custom HTTP tools · MCP servers" -- AE SE -- W "Widgets · REST API" AE -- W W -- Y "Your website" IX -.- ES "Elasticsearch or<br/ Azure AI Search" AE -.- LLM "OpenAI · Ollama" You connect a data source, populate a search index, then build one or more experiences on top of it. The chat experience calls the search tools to answer from your data. The architecture overview https://docs.interakt.app/getting-started/architecture/ has the full picture. Needs Node.js 24 and Docker. Prefer to watch? The backend setup video https://www.youtube.com/watch?v=oxcFsP9UGiY walks through these steps. git clone https://github.com/alphasolutionsrepo/interakt.git cd interakt/backend cp .env.example .env fill in the three generated secrets at the top cp setup/setup.config.example.yaml setup/setup.config.yaml set your admin email and password npm install npm run infra:up Postgres pgvector and Elasticsearch in Docker npm run dev migrates, seeds, creates the admin user → http://localhost:3000 Sign in and open Platform → Initial Setup . Connect an AI provider Ollama is free and local , then load the Fashion Catalog demo: a populated index plus ready-made search and chat experiences with access tokens. Point the reference app in demo-site/ https://github.com/alphasolutionsrepo/interakt/blob/main/demo-site at it, or embed the widget below. The full walkthrough, scripts and bring-your-own-database notes are in CONTRIBUTING.md https://github.com/alphasolutionsrepo/interakt/blob/main/CONTRIBUTING.md local-development . Hosting notes are in backend/docker/ https://github.com/alphasolutionsrepo/interakt/blob/main/backend/docker/README.md . <div id="chat" </div <script src="https://your-interakt-host/embed/v1/widgets.js" </script <script window.ChatDropinUI.init { containerId: 'chat', accessToken: '<access token from the admin UI ', } ; </script Use SearchDropinUI for the search widget. The admin UI generates the exact snippet for each experience, and the widget docs https://docs.interakt.app/concepts/embed-widgets/ cover launcher modes, placement and theming. Search through a search experience curl -X POST https://your-interakt-host/api/v1/search/<experience-slug /search \ -H "Authorization: Bearer <access token " \ -H "Content-Type: application/json" \ -d '{ "query": "waterproof trail shoes" }' Chat through an AI experience streams server-sent events curl -N -X POST https://your-interakt-host/api/v1/ai-experiences/<experience-slug /chat \ -H "Authorization: Bearer <access token " \ -H "Content-Type: application/json" \ -d '{ "message": "Which of these run true to size?" }' Access tokens are issued per experience and are public and read-only by design. Writing documents into an index uses a server-side ingestion key instead. See the search https://docs.interakt.app/guides/call-the-search-api/ , chat https://docs.interakt.app/guides/call-the-chat-api/ and ingestion https://docs.interakt.app/guides/ingestion-api-reference/ guides, or the full API reference https://docs.interakt.app/api/ . Step-by-step guides for Medusa https://docs.interakt.app/integrations/ecommerce/medusa/how-to-integrate-interakt-with-medusa/ , Storyblok https://docs.interakt.app/integrations/cms-dxp/storyblok/how-to-integrate-interakt-with-storyblok/ and React / Next.js https://docs.interakt.app/integrations/frontend/react-nextjs/ . The Interakt-Medusa https://github.com/alphasolutionsrepo/Interakt-Medusa repository is the demo storefront that guide is built on. interakt/ ├── backend/ Admin dashboard + REST APIs · Next.js 16, Drizzle, Postgres + pgvector │ ├── widgets/ Embeddable search and chat widgets · Preact, built to public/embed/v1/widgets.js │ ├── docker/ Production Dockerfile + local docker-compose Postgres, pgAdmin, Elasticsearch │ └── src/content/docs/ The documentation, served in-app at /docs and published to docs.interakt.app ├── demo-site/ Reference consumer app on port 3001 └── docs-site/ Docusaurus + Redocusaurus shell for docs.interakt.app Contributions are welcome. CONTRIBUTING.md https://github.com/alphasolutionsrepo/interakt/blob/main/CONTRIBUTING.md covers local setup, conventions and how review works here. Found a bug or want a feature? Open an issue https://github.com/alphasolutionsrepo/interakt/issues/new/choose . Have a question? Start a discussion https://github.com/alphasolutionsrepo/interakt/discussions . For security issues, follow SECURITY.md https://github.com/alphasolutionsrepo/interakt/blob/main/SECURITY.md and never open a public issue. This project follows the Contributor Covenant https://github.com/alphasolutionsrepo/interakt/blob/main/CODE OF CONDUCT.md code of conduct.