Show HN: Ekselio – Loveable for finance workflows (local first)
Ekselio is a local-first financial workflow tool that uses LLMs to generate repeatable SQL queries executed via browser-based DuckDB-WASM.
summary is enough The landing page is minimal, but the creator's detailed comments on local-first DuckDB-WASM architecture provide valuable technical context.
summary
Ekselio is a browser-based tool designed for finance and FP&A teams to build recurring workflows using sensitive company data. It utilizes a local-first architecture with DuckDB-WASM, where an LLM plans steps and writes SQL once, allowing users to re-run reports deterministically every month without recurring token costs or cloud data exposure. Commenters and the creator discuss how this differs from general chat tools or app builders by focusing on persistent, scriptable data pipelines.
key points
- Executes financial queries entirely in the browser using DuckDB-WASM to ensure sensitive ledger data stays local.
- The LLM plans workflows and generates SQL on the first run, enabling deterministic, token-free re-runs for monthly reports.
- Connects directly to external financial data sources like QuickBooks, Edgar, and FRED alongside local file uploads.
who should read it
Finance professionals and developers interested in local-first data applications.
discussion warm
consensus
Commenters are generally positive, praising the local-first approach for handling sensitive financial data and the emphasis on repeatable workflows.
pushback
Initial confusion existed regarding how the workflow canvas differs from standard chat-based assistants or app builders.
Sorry for the delay, had to put my 15 month old to sleep yes, Lovable - I spelled it “Love-able” on purpose-ish since the architecture is different. Lovable builds you an app; this builds a workflow. The LLM plans the steps once (based on file schema), then the actual math runs as SQL in duck-db wasm in your browser. Next month you simply upload the revised file and hit re-run - same SQL (no add'l tokens needed). The AI can still write bad SQL, but it's all visible on the canvas, so it can be checked and once you save it, then next time it is deterministic. For Finance, the local first …
The creator details the specific technical architectural differences between building an app and executing deterministic SQL via DuckDB-WASM.
Generated by an LLM from the article and thread. Check the sources before relying on it.