Open source · Apache 2.0 · Self-hosted
Enterprise search, cited RAG and AI agents over your own content.
AI search and grounded answers you can trace back to the source, on the LLM you choose, with the index in your own infrastructure. An open, self-hosted alternative to Algolia, with AI built in.
For engineering teams who need production search and RAG without shipping their data to someone else's cloud.
npx @viglet/turing-cli init my-search- Your data stays in your infra
- Choice of LLM provider
- Cited answers you can audit
Try it: type to search.
Search it, ask it, validate it, on the same content
All three run on Viglet Turing's own zero-dependency SDK, over the exact same corpus (Viglet Turing's documentation). Search finds the page; the assistant answers with a cited RAG response. You can switch personas to hear the same answer through different eyes, or validate whether your own copy lands for a given reader. Try a result's “Ask about this”.
Example: ask the assistant “Does Viglet Turing support self-hosting?”. Viglet Turing searches its own documentation, then answers with a retrieval-augmented (RAG) response that cites the documentation pages it used.
The Search tab runs a faceted keyword search over the same documentation, and each result offers “Ask about this” to continue in the cited chat. The Validate tab checks whether a piece of copy fits a chosen reader persona.
See the same content through a persona's eyes: a fit score, what lands, and the exact phrases that miss.
Search it. Ask it. Automate it. Run it.
Most teams stitch a search engine, a RAG pipeline and an agent framework together. Viglet Turing is all three, open source and self-hosted.
Production search over your content
Faceted, multilingual, typo-tolerant search on Solr, Elasticsearch or Lucene, with field manifests as code, currency/number localization and coverage observability.
RAG & chat with answers you can audit
Retrieval-augmented generation with a pluggable reranker (LLM, cross-encoder or Cohere) and an embedded vector store. Answers stream token-by-token with inline citations that trace back to the source passage, plus an optional groundedness check and a deterministic “not in this site” refusal.
Agents with tools, skills & MCP
Configurable AI agents that call your tools, run Anthropic-standard skills in a Docker sandbox and federate across MCP servers. Each provider's own server-side tools (web search, code execution, computer use, image generation) are opt-in per agent.
Self-hosted, your choice of LLM, your data
Open source under Apache 2.0. Pick the LLM per agent (OpenAI, Anthropic, Google Gemini, AWS Bedrock, local Ollama, any OpenAI-compatible endpoint and more), run on Solr, Elasticsearch or embedded Lucene, and keep your own storage. Multi-tenant and observable, on your infrastructure.
One platform, two ways in
Adopt it bottom-up as a developer, or bring it in as a governed enterprise search layer. The open-source core is the same.
Own your search stack, from npx to prod
Open source and self-hosted, with SDKs that drop into your app.
- Local stack in one command: npx @viglet/turing-cli init
- React SDK + zero-dependency vanilla-JS SDK (headless)
- Bring your own LLM and search engine
- Vendor-neutral funnel analytics to your own GA4, GTM, Segment or Matomo, zero-config
- Self-host with one docker run. No account, no telemetry
Production AI search on your own infrastructure
For regulated, content-heavy organizations that need control over their data.
- Your content, embeddings and query logs are stored on your own infrastructure
- Index Adobe Experience Manager (AEM 6.5 and AEM as a Cloud Service) pages, Content Fragments and DAM assets on publish, plus WordPress, databases and files
- SSO, encrypted secrets, your choice of LLM provider (including fully local models)
- Cited, auditable answers you can trace to the source
Pluggable LLM providers & search engines
The open-source way to do AI search
A hosted SaaS locks your data in someone else's cloud. A DIY stack is months of glue code. Viglet Turing gives you both halves, self-hosted.
| Viglet Turing | Hosted search SaaS | DIY (LangChain + vector DB) | |
|---|---|---|---|
| Open source (Apache 2.0) | partial | ||
| Self-host: data stays in your infra | |||
| Faceted enterprise search | build it | ||
| RAG + pluggable reranker | partial | build it | |
| Cited answers you can audit | partial | build it | |
| AI agents, tools & skills built in | partial | build it | |
| Native provider tools (web search, code, computer use) | build it | ||
| Choice of LLM provider per agent | partial | ||
| Bring your own search engine | partial |
High-level comparison as of 2026; verify current vendor capabilities. “DIY” = assembling LangChain/LlamaIndex with a vector database yourself.
$ docker run -p 2700:2700 ghcr.io/openviglet/turing
# pulling ghcr.io/openviglet/turing:latest ...
✓ image pulled no build step
✓ turing-app running
# console + API ready on http://localhost:2700Self-host the whole platform in one command
No account, no sales call, no data leaving your infrastructure. There is nothing to clone or build: the container image is already published to a public registry. Pull it, run it, then open the console and index your first site. Want the full stack (Solr, MariaDB, monitoring)? A readydocker composefile ships in the repo too.
- Prebuilt container image: nothing to clone, nothing to build
- Your content and embeddings are stored on your network. No SaaS tier, no telemetry
- Point it at a supported LLM provider (or a local model) and your own Solr, Elasticsearch or embedded Lucene
docker run -p 2700:2700 ghcr.io/openviglet/turingThe detail lives on its own page
Each of these has a page of its own. Pick the one that answers your next question.
How it answers a question
Retrieve from your sites, rerank, answer with inline citations, and refuse when the sources do not support an answer.
Build it into your front end
The playground above runs on @viglet/turing-sdk, the zero-dependency JavaScript SDK. React hooks and components are in @viglet/turing-react-sdk.
Agents, tools, skills and MCP
Agents call your tools, run skills in a sandbox, use the tools your model provider ships, and speak the Model Context Protocol.
Ship agents from your terminal
The turing CLI scaffolds a project, runs a local stack, deploys agents, flows and tools, and runs eval suites in CI.
Start from a working example
Three example search sites, each with its own data and front end.
Own your AI search stack
Open source, self-hosted, and works with the LLM provider you choose, local models included. Stand up the full platform in one command and ship cited AI answers over your own content, with the index stored on your own infrastructure.