df0-io / df0
DF-0: Data processing Framework with Zero-overhead. Local-first C++20 data-processing infrastructure for deterministic, auditable, on-premise workflows. Supports 100+ formats, OCR, local AI, and opt-in cloud AI pipelines
Why this job: topics: rag, ocr
What it does
- Local-first and privacy-preserving data processing - the goal is for every processing stage to support an on-premise implementation. Today, parsing, OCR, local document AI, and local text embeddings can run fully offline. A few AI capabilit
- Able to extract/import and export text, images, formatting, and metadata along with annotations
- Handles unstructured and structured payloads. documents, images, web content, JSON, XML, CSV, and other structured or semi-structured formats can be processed in the same pipeline model.
- Data can be transformed between import and export (filtering, aggregating, translation, text classification, sentiment analysis, named entity recognition etc).
Get started
No single install command. Read the steps in the README (opens in new tab)
- Maintenance
- Active
- Last commit 3 days ago
- Stars
- 118
- +1 this week
- Licence
- Custom
- Read before business use
- Downloads for
- None listed
- No release files
- Latest version
- 2026.07.07
- Released 4 months ago
- Built with
- C++
- 89% of the code
Is it looked after?
- Contributors
- Not stated
- Last 90 days
- Issues
- 63% closed
- 44 still open
- Pull requests
- 152 merged
- 3 waiting
- Releases
- 45
- 4 in the last year
- No contributing guide
- No security policy
- No code of conduct
Similar repos
| Repo | Stars | Last commit | Licence | Downloads for |
|---|---|---|---|---|
| enoch3712 / ExtractThinker | 1,604 | 55 days ago | Apache-2.0 | No downloads |
| bzsanti / oxidizePdf | 194 | 4 days ago | MIT | No downloads |
| iamarunbrahma / pdf-to-markdown | 217 | 57 days ago | MIT | No downloads |
More: languages, topics and project record
Languages
- C++ 89%
- CMake 5%
- HTML 4%
- Rich Text Format 1%
Topics
- artificial-intelligence
- cpp
- cpp20
- cross-platform
- data-extraction
- data-processing
- document-processing
- edge-computing
- extract-transform-load
- large-language-models
- llm
- local-ai
Project record
- JobRAG and search
- StatusListed
- Commits1,710
- Forks25
- Watching8
- Stars in 28 days+1
- CreatedMay 29, 2023
- First seen by usNov 7, 2026
- CheckedNov 8, 2026