Scrubkit
High-performance, offline document parser and data prep library for .NET RAG and AI pipelines. Extracts text and metadata (PDF, Word, Excel, PowerPoint, HTML, RTF, Email, EPUB, OpenDocument) and redacts PII and secrets locally before sending to LLMs. Features parallel streaming, incremental scans via manifests, pluggable format extractors, and built-in chunking.
Activity
- Latest release
- 1mo ago
- Total releases
- 13
- Cadence
- ~daily
- Last 12 months
- 13
Details
- License
- MPL-2.0
- First release
- Jul 12, 2026
| Version | Released | |
|---|---|---|
1.11.0
minor
|
1.11.0
minor
Dependencies (4)
|
|
1.10.0
minor
|
1.10.0
minor
Dependencies (4)
|
|
1.9.0
minor
|
1.9.0
minor
Dependencies (4)
|
|
1.8.0
minor
|
1.8.0
minor
Dependencies (4)
|
|
1.7.0
minor
|
1.7.0
minor
Dependencies (4)
|
|
1.6.0
minor
|
1.6.0
minor
Dependencies (4)
|
|
1.5.0
minor
|
1.5.0
minor
Dependencies (4)
|
|
1.4.0
minor
|
1.4.0
minor
Dependencies (4)
|
|
1.3.0
minor
|
1.3.0
minor
Dependencies (4)
|
|
1.2.0
minor
|
1.2.0
minor
Dependencies (4)
|
|
1.1.0
minor
|
1.1.0
minor
Dependencies (4)
|
|
1.0.0
initial
|
1.0.0
initial
Dependencies (4)
|
|
0.1.0-preview.1
pre
|
0.1.0-preview.1
pre
Dependencies (4)
|