AI/ML●●●Banger
LiteParse, a fast open-source document parser for AI agents
Beats PyPDF and MarkItDown on accuracy without needing GPUs or cloud APIs.
Solve My ProblemSlickCrowd Pleaser
freezed8
1202mo ago
Back to browse
udoc. Dependency-free document extraction in Rust
by newelh·May 20, 2026·5 points·1 comment
AI Analysis
●●●BangerWizardryBig Brain
Pure Rust parsers for legacy Office formats with zero external dependencies.
Strengths
- •Native parsers for binary .doc and .xls eliminate need for LibreOffice headless.
- •Streaming JSONL output allows processing multi-gigabyte PDFs without OOM errors.
- •Unified document model abstracts away format-specific quirks for all inputs.
Weaknesses
- •Cargo crate not yet published, requiring manual build or uvx for now.
- •OCR and layout detection require piping output to external hooks manually.
Category
Target Audience
Backend engineers building document processing pipelines
Similar To
Apache Tika · Pandoc · Poppler
Similar Projects
Developer Tools●●●Banger
LibreOffice-rs – I built a pure-Rust LibreOffice using autoresearch
Pure-Rust DOCX to PDF converter running 100x faster than LibreOffice with zero C dependencies.
WizardryBig BrainZero to One
stan_kirdey
10124d ago
Infrastructure●Mid
Aegis-DB – Multi-paradigm database in Rust,in production
Six data models in one binary, but no proof of production use or comparison benchmarks.
Bold Bet
AutomataNexus
113mo ago
AI/ML●●Solid
DocMason – AI Agent Knowledge Base for local complex office files
Preserves document structure instead of flattening to text like most RAG tools.
Solve My ProblemBold Bet
Jet_Xu
232mo ago
AI/ML●●Solid
ProofPudding – Document Extraction API with Citations (PDF/Docx)
ProofPudding returns extraction results with explicit links back to the exact page and source text, supports native and scanned PDFs plus DOCX/images, and ships Python/TypeScript SDKs — handy for agents that need auditable facts. It’s a pragmatic product (per-extraction pricing and confidence scores are nice), but the market is crowded; I want clarity on underlying models, real-world accuracy numbers, and how it compares to Document AI/Textract in edge cases.
Solve My ProblemSlick
garai
104mo ago
AI/ML●●Solid
DocMason – Agent Knowledge Base for local complex office files
Provenance-first RAG beats anonymous text chunks, but Cursor and Continue already own this space.
Big BrainNiche Gem
Jet_Xu
1102mo ago