Bring your sources together
Add individual files, folders, static websites, or a local code repository to one ingestion workspace.
Keep batches moving
Track progress, cancel a job, pause the next jobs, and inspect warnings without losing your place.
Read scanned pages locally
Built-in English OCR extracts text from PDF pages with little usable native text.
Shape the output
Use saved schema mappings and validation to turn extracted content into structured JSON.
Keep the source attached
Retain metadata, source hashes, and supported page, slide, cell, or line references.
Review before you export
Inspect extracted text, structure, metadata, warnings, and output before choosing a destination.
Built around real work
Control the process.
Understand the result.
File and folder ingestion
Add individual documents or process folders in batches. Save sources and pipeline configurations for repeatable work.
Website and local repository ingestion
Extract static HTML through bounded same-origin crawls. Inspect local repository files with line references and heuristic symbol hints.
Schema mapping and validation
Choose deterministic field mappings, validate against JSON Schema, and inspect output before export.
Metadata and provenance
Retain source hashes and supported page, slide, cell, and line references. Read extraction warnings directly in the job results.
Check the supported scope for your format →Beyond documents
Media ingestion
and continuity.
Audio, image, and video ingestion
Ingest and convert common audio formats (WAV, MP3, FLAC, AIFF, AAC/M4A, OGG, OPUS, WMA where supported), image formats (JPG, PNG, WEBP, TIFF, BMP, GIF, HEIC/HEIF where supported, AVIF, ICO), and video formats (MP4, MOV, MKV, AVI, WEBM, M4V). Combine a still image with audio to create a video.
Local English OCR
Extract text from scanned PDF pages with little usable native text, processed locally.
Provenance and verification
Every ingested file is tracked with SHA-256 checksums, collection manifests, and job-level provenance so you can verify what was processed and when.
AI Continuity Vault
A local-first continuity and archive system that preserves and reconstructs conversations, documents, images, audio, video, projects, metadata, decisions, and structured context, with search and index data, entirely on your machine.