Python
Browser-local CPython through Pyodide for data analysis and scientific workflows.
Import data, run Python, analytical SQL and R, search scholarly evidence, connect claims to sources and preserve the path from question to result.
Numerical and statistical results should come from executed software. Lwati uses AI for assistance while deterministic runtimes do the work.
Browser-local CPython through Pyodide for data analysis and scientific workflows.
Query CSV, JSON and Parquet data with analytical SQL inside the browser.
Run R and statistical workflows through WebAssembly without a dedicated R server.
Search scholarly metadata, verify DOI-linked sources, create explicit claims, connect executed analyses to those claims and preserve dataset and code provenance.
Scientific data has its own storage layer rather than being forced through small source-code payloads.
Record runtime, code hash, dataset hash and execution information around analyses.
Keep sources, relationships and research claims inspectable instead of hiding them in generated prose.
Export datasets, notebook context, evidence and provenance as a portable research artifact.