EIDONIX

Solutions Knowledge discovery

Eidonix Lens

Turns private documents and selected public-web material into a knowledge base that gets better as people use it.

Status
Live
Shape
Web application and API
Built with
Go · Qdrant · Postgres

Consolidate and Discover Data

Every plant runs on documents nobody can find. Equipment manuals, service bulletins, filings, scanned drawings, the folder of PDFs somebody saved in 2019. The knowledge exists; locating it is the problem.

Lens takes that material in, extracts the text, and makes it searchable in plain language. It also goes out to the public web when the answer is not in-house, grades what it finds, and keeps the sources worth keeping. Answers come back with citations and the ranked evidence they came from, so you can check the work rather than trust it.

Cletus queries it directly. That is where it gets interesting: an analysis can pull the numbers and the manual in the same run, and the corpus keeps getting better every time somebody uses it.

Capabilities

CatalogsManuals, filings, PDFs, images, and folders. Extraction and OCR run in the background.
Web probesFinds candidate sites, grades them, and crawls the ones worth keeping.
SearchHybrid retrieval with reranking scores, source links, and streamed summaries.
API accessScope application keys to specific catalogs or workspaces.

Related

CletusIn active use

An analytics workspace that investigates a question, runs the analysis, and hands back the work.

  • Works across sources — Spreadsheets, shared files, SQL databases, market data, and Eidonix Lens knowledge catalogs.
  • Runs the analysis — SQL, DuckDB, Python, R, and charting inside a controlled sandbox.
  • Produces real artifacts — Charts, native Excel workbooks, and reports you can hand to someone.
  • Carries knowledge forward — Skills leave with the retiring workforce. Cletus helps you capture and transfer that knowledge to the new generation.
Go · Svelte
go-llm-proxyllm.eidonix.com

One endpoint for every model your tools need.

  • Protocol translation — Anthropic Messages, OpenAI Responses, Chat Completions, and Bedrock Converse, translated automatically so any client reaches any backend.
  • Model multiplexing — Local GPU servers, cloud APIs, and third-party providers behind a single model list.
  • Documents and images — Text extraction from PDFs with an OCR fallback for scans. Images described for models that cannot see.
  • Search and MCP — Web searches run server-side and the results are injected, with an MCP endpoint for agent clients.
  • Key management — Proxy keys carry per-key model restrictions. Backend credentials never leave the server.
Go · MCP · SQLite