Solutions Agentic analytics for decision makers

Cletus

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

Status: In active use
Shape: Desktop application
Built with: Go · Svelte

Agentic Analytics for Deep Insights

Most analysis dies in the gap between asking a question and having the time to answer it. Somebody wants downtime compared across plants with the drivers explained, and getting there means pulling exports, reconciling them, writing the queries, building the chart, and formatting a workbook. By the time it lands, the question has moved on.

Cletus does that work. You ask in plain language, it goes and gets the data, runs the analysis in a controlled sandbox, and hands back the artifacts — charts, a native Excel workbook, a written summary.

It is wired into Eidonix Lens, so a question can reach the whole organization at once — the databases and the equipment manuals, the filings, the reports somebody wrote three years ago. The answer comes from what the company already knows, not just from what happens to be in a table.

In use

Cletus fitting an OLS regression on the mtcars dataset, running assumption checks in R, and rendering diagnostic plots — Asked for a regression with the assumptions proved. It picks the tests, writes the R, hits a plotting library error, and fixes it without being asked.

Cletus producing a horizontal bar chart of fuel efficiency by model, colored by cylinder count — The same session, one instruction later. Charts come back as artifacts, not as code to run yourself.

Capabilities

Works across sourcesSpreadsheets, shared files, SQL databases, market data, and Eidonix Lens knowledge catalogs.

Runs the analysisSQL, DuckDB, Python, R, and charting inside a controlled sandbox.

Produces real artifactsCharts, native Excel workbooks, and reports you can hand to someone.

Carries knowledge forwardSkills leave with the retiring workforce. Cletus helps you capture and transfer that knowledge to the new generation.

Eidonix LensLive

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

Catalogs — Manuals, filings, PDFs, images, and folders. Extraction and OCR run in the background.
Web probes — Finds candidate sites, grades them, and crawls the ones worth keeping.
Search — Hybrid retrieval with reranking scores, source links, and streamed summaries.
API access — Scope application keys to specific catalogs or workspaces.

Go · Qdrant · Postgres

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