sirdas CLI

Same engine as the web app and the MCP server, from the terminal. No network, no accounts, no telemetry.

#Install

npx sirdas factura.pdf       # nothing to install but Node 20+
npm i -g sirdas              # or keep it around

From source:

git clone https://github.com/Brayan15p/SIRDAS-APP-PDF.git && cd SIRDAS-APP-PDF
npm install && npm run build -w packages/core -w packages/mcp -w packages/cli
node packages/cli/dist/main.js --help     # or: npm link -w packages/cli

#Commands

# Start here: reads any file end to end (PDF, scan, DOCX, XLSX, PPTX, HTML, EPUB, CSV, EML, PNG/JPG)
sirdas <file>
sirdas leer      <file> [--json] [--no-anonymize] [--no-ocr] [--max-tokens 1500] [-o out.md]

# Ask a folder: the smallest cited context for a question
sirdas contexto  <folder|files...> -p "which contracts expire this quarter?" [--max-tokens 4000]
                 [--mantener FECHA] [--no-anonymize] [--ocr] [--json] [-o context.md]
                 [--indice folder.sirdas]   # opt-in: keep what was read so the next question converts nothing
sirdas olvidar   <index.sirdas>             # delete an index; refuses any other file
                 # ends with a numbers-only sentence you can share: no file names, no text

# Many documents to one table: cited fields, duplicates, totals that don't add up
sirdas campos    <folder|files...> [--tipo factura] [-o facturas.xlsx|.csv] [--force]
                 [--no-anonymize] [--ocr] [--json]

sirdas convertir <file.docx|xlsx|pptx|odt|epub|html|csv|eml|rtf|srt|vtt> [--json] [-o out.md]
sirdas separar   <batch.pdf> [-d dir] [--json]        # one PDF per document inside a batch
sirdas formulario <file.pdf> [--json]                  # filled form fields and checkboxes
sirdas classify  <file.pdf> [--json]                   # factura, contrato, historia_clinica…
sirdas revisar   <folder> [--sin-nombres]              # run everything over real files, report without content

sirdas pages     <file.pdf> delete|extract|rotate [--pages "2, 4-6"] [--angle 90] [-o out.pdf]
sirdas number    <file.pdf> [--format "Página {n} de {total}"] [--position bottom-right] [--skip-first 1]
sirdas watermark <file.pdf> --text CONFIDENCIAL [--opacity 0.15]
sirdas protect   <file.pdf> [--no-print] [--no-copy] [--no-edit] [-o out.pdf]   # asks for the password, or SIRDAS_PASSWORD
sirdas unlock    <file.pdf> [-o out.pdf]

sirdas markdown  <file.pdf> [--no-anonymize] [--json] [-o out.md] [--force]
sirdas ocr       <scan.pdf> [--lang spa+eng] [--lang-path dir] [--no-anonymize]
sirdas ocr --download-models [--lang spa]   # once; then it works offline
sirdas anonymize [file.txt] [--json] [--map map.json]  # reads stdin when no file
sirdas restore   [file.txt] --map map.json            # puts the real data back
sirdas chunks    <file.pdf> [--max-tokens 2000] [--json] [-d dir]
sirdas tables    <file.pdf> [--csv|--markdown|--json|--xlsx [-o out.xlsx]] [-d dir] [--delimiter ";"] [--lang es|en]
sirdas compare   <before.pdf> <after.pdf> [--all] [--json] [--ignore-case]
sirdas info      <file.pdf> [--json]
sirdas merge     <a.pdf> <b.pdf> [...] -o out.pdf [--force]
sirdas split     <file.pdf> [--ranges "1-3, 5, 8-end"] [-d dir] [--force]
sirdas compress  <file.pdf> [-o out.pdf] [--force]   # lossless

# Training data (all local, no model is ever called)
sirdas dataset       <a.pdf|b.docx|c.html> [...] [--format text|chat|prompt-completion|alpaca|sharegpt|langchain|llamaindex|embeddings]
                     [--hf]   # train/validation/test.jsonl + Hugging Face README.md
                     [--max-tokens 2000] [--no-anonymize] [--no-dedupe]
                     [--strip-boilerplate] [--split] [--seed s]
                     [--template "..."] [--system "..."]
                     [-d dir] [--no-meta] [--json]
sirdas dedupe        <a.pdf> <b.pdf> [...] [--threshold 0.8] [--json]
sirdas boilerplate   <a.pdf> <b.pdf> [...] [--min-words 5] [--json]
sirdas contamination <train.pdf> [...] --against <eval.pdf> [--n 13] [--json]
sirdas rl            <a.pdf> [...] [--max-per-table 10] [--lang es|en] [-o f.jsonl]
sirdas rl --reward-fn                                # the Python reward function
sirdas mcp                                           # start the MCP server over stdio
sirdas auditoria     <audit.jsonl> [--json]          # verify the SIRDAS_AUDIT_LOG hash chain and list files read and written
sirdas procedencia   <file> --registro <audit.jsonl> [--json]   # where a file came from, back to its originals

md is an alias of markdown.

#On-disk index (opt-in)

Since 0.4.1.

sirdas contexto reads every file again on each run. With --indice <file> it keeps what it read in that file and, on the next run, converts only what changed (files are matched by sha256). The index exists only when you pass a path, and:

• it contains the text of your documents: it is written with owner-only permissions (0600), and you should keep it like the originals;
• it holds only what the last run read, so a file deleted from the folder leaves the index on the next run;
• it is rebuilt when a different engine version wrote it;
• it never overwrites a file that is not an index, and sirdas olvidar deletes an index and refuses any other file.

The MCP server does not write an index: build_context remembers files in the process only, so its tools stay read-only.

#Conventions agents can rely on

• Exit codes: 0 success · 1 usage error (bad flags, missing input, refusing to overwrite) · 2 the file could not be processed (password-protected, damaged, not a PDF). The reason is printed to stderr in one sentence.
• stdout is the payload. markdown prints Markdown; with --json it prints one JSON object (markdown, pages, tokens_estimate, anonymized, redacted, has_text, source). Progress and warnings go to stderr.
• Anonymization is on by default for markdown; --no-anonymize keeps the original data.
• Never overwrites an existing file without --force.
• anonymize --json includes the placeholder→value mapping; keep it local.

#The anonymize → AI → restore round trip

Nothing is ever deleted. The original PDF is untouched and the mapping — which holds the real values — stays on your machine.

# 1. Anonymize, keeping the mapping
sirdas markdown historia.pdf --json | jq -r .markdown > anonima.md
sirdas anonymize anonima.md --map mapa.json > anonima-final.md

# 2. Send anonima-final.md to any model, then restore its answer locally
cat respuesta-de-la-ia.txt | sirdas restore --map mapa.json

A name always comes back whole: placeholders map to the complete original value, never a fragment.

#Examples

# Markdown for an LLM, personal data replaced
sirdas markdown historia.pdf > historia.md

# Structured output for a script
sirdas markdown contrato.pdf --json | jq '.tokens_estimate, .redacted'

# Anonymize a snippet before pasting it anywhere
echo "Paciente: Ana Gómez, C.C. 52.123.456" | sirdas anonymize

# Split the first three pages and the last one
sirdas split informe.pdf --ranges "1-3, 8-end" -d ./partes

# Pull an invoice's line items into a spreadsheet (CSV carries a BOM for Excel)
sirdas tables factura.pdf --delimiter ";" -d ./tablas
sirdas tables extracto.pdf --xlsx          # one sheet per table, amounts as numbers

# Split a long document into chat-sized pieces
sirdas chunks informe.pdf --max-tokens 2000 -d ./partes

# Merge, then shrink losslessly
sirdas merge a.pdf b.pdf -o todo.pdf && sirdas compress todo.pdf

#Docker

For machines without Node, or an isolated network. The image has the OCR models inside and needs no network at run time:

docker run --rm --network none -v "$PWD:/work" ghcr.io/brayan15p/sirdas factura.pdf
docker run --rm -i -v "$PWD:/work" ghcr.io/brayan15p/sirdas mcp   # MCP over stdio

The image is published to GHCR by the release workflow with every version. You can also build it from the repository's Dockerfile with docker build -t sirdas ..