Viglet Turing
Enterprise search, cited RAG and AI agents over your content. Self-hosted, with your choice of search engine and LLM.
Turing, in 4 moves
What Turing does, step by step.
Faceted search, any engine
Faceted, multilingual, typo-tolerant search on Apache Solr, Elasticsearch or embedded Lucene, with hybrid keyword + vector ranking (RRF).
Cited RAG answers
A chatbot grounded in your content streams answers with source citations, a pluggable reranker, a relevance gate and an optional groundedness check.
Agents, tools, skills & MCP
Configurable agents call your tools, run Anthropic-standard skills in a sandbox, federate over MCP, and use each provider’s native server-side tools.
Self-hosted, any LLM
Runs on your own infrastructure under Apache 2.0, with OpenAI, Anthropic, Gemini, Azure or local Ollama models. Multi-tenant and observable.
$ docker pull ghcr.io/openviglet/turing-ce # get the image
$ docker run -d -p 2700:2700 --name turing ghcr.io/openviglet/turing-ce # then open localhost:2700Built for enterprise
What ships with Turing.
One query API, three engines
Run faceted, multilingual, typo-tolerant search on Apache Solr, Elasticsearch or an embedded Lucene index. Swap engines per site without changing your front-end.
Hybrid keyword + vector ranking
Reciprocal Rank Fusion merges BM25 with per-site vector scores, so semantic matches rank alongside exact keyword matches.
Cited RAG answers you can audit
Every streamed answer carries source chips (title, URL, score) traceable to the exact passage, with a pluggable reranker, a relevance gate and an optional groundedness check.
AI agents with tools, skills & MCP
Agents call custom tools, run Anthropic-standard skills in a Docker sandbox, and federate over MCP in both directions: as a client, and with Viglet Turing as the server.
Native provider tools
Turn on each vendor’s server-side web search, code execution, computer use, URL fetch and image generation across OpenAI, Anthropic and Gemini, opt-in per agent.
Bring any LLM, keep your data
OpenAI, Anthropic, Gemini, Azure and local Ollama models plug in behind one interface, switchable per agent, with keys encrypted at rest.
Self-host, multi-tenant, observable
Apache 2.0 on your own infrastructure with OIDC SSO, multi-tenancy behind a feature flag, chat & conversion analytics, LLM cost tracking and Micrometer metrics.
Connect to your ecosystem
Extend Turing with ready-to-use integration modules.
Dumont
Viglet Dumont, the data exchange platform, feeds Viglet Turing with content from Adobe AEM, WordPress, databases, files and the web.
React SDK
React 19 headless hooks and UI components for search, chat and autocomplete, with full TypeScript support.
JavaScript SDK
Framework-agnostic, zero-dependency vanilla-JS client. Works in Adobe EDS blocks, a plain <script>, or any bundler.
Turing CLI
Zero-dependency developer CLI: scaffold a project, run a local stack, deploy agents/flows/tools/skills, and run YAML eval suites.
Java SDK
Java library to index and query Turing from JVM applications.
MCP Server & Client
Expose Turing search as an MCP server for any MCP-aware client, and connect agents out to federated MCP servers.
Model Catalog
Vendor-neutral public catalog of LLM, embedding, rerank and media models: context windows, capabilities, indicative pricing and deprecations. Turing reads it to enrich the model picker and warn on retired models.
Shio
Viglet Shio integrates with Turing: choose which attributes get indexed while modeling post types.
How-tos & comparisons
Step-by-step integration guides and comparisons on the Viglet blog.
Turing AEM Search: What Your AEM Site Could Do If Search Actually Understood People
Your AEM search box is the most honest feedback channel you own, and usually the most neglected. Hybrid search plus a conversational layer over the AEM content you already published, with citations, self-hosted and Apache 2.0.
RAG Over Enterprise Content with Viglet Turing and MCP
Combine retrieval-augmented generation over your indexed enterprise content with the Model Context Protocol (MCP), so AI agents can search your AEM, WordPress, and database content as a first-class tool.
Semantic & Vector Search in Adobe AEM with Viglet Turing
Go beyond keyword search on Adobe Experience Manager content: add embedding-based vector search and semantic navigation with an open-source platform, on your own infrastructure.
When to Choose Apache Solr, Elasticsearch, or Viglet Turing
Raw Solr and Elasticsearch are search engines; Viglet Turing is an enterprise search platform built on top of them. Here's how to decide which layer you actually need.
Coveo vs. Lucidworks Fusion (and an Open-Source Option)
Coveo is managed SaaS priced per query; Lucidworks Fusion is licensed, Solr-based and runs in your perimeter. How they compare on pricing, data residency, connectors and RAG, plus Viglet Turing as the open-source alternative.
Adding Enterprise Search to WordPress with Viglet Turing
Index WordPress posts, pages, and custom post types into an open-source enterprise search engine with faceted navigation and semantic search: a self-hosted alternative to Algolia and ElasticPress.
Open-Source Alternatives to Algolia and Coveo for Adobe AEM
Comparing search options for Adobe Experience Manager: Algolia, Coveo, Lucidworks, raw Solr/Elasticsearch, and the open-source Viglet Turing. Pricing model, data residency, facets, semantic search, and RAG.
How to Add Enterprise Search to Adobe AEM with Viglet Turing
A step-by-step guide to indexing Adobe Experience Manager content into an open-source enterprise search engine with faceted navigation, semantic search, and RAG: an alternative to Algolia, Coveo, and Lucidworks.
Ready to try Turing?
Free and open source. One Docker command to get it running.