npm · PyPI
joshuaswarren/remnic
Open-source memory and context for user-aware agents: scoped memory, provenance, retrieval quality, correction, boundaries, evals, and MCP/HTTP access.
MIT20. Okt. 2026 · Metriken 2.10.0
Alle Tags
Katalog-Tag
#extraction
Alle Repositories im öffentlichen Register, die dieses Tag tragen — aus ihren GitHub-Topics oder den von ihren Paket-Registries veröffentlichten Schlagwörtern. Die Gesundheit wird nach derselben versionierten Methodik gemessen wie im übrigen Register.
40 Einträge
npm · Packagist · crates.io +1
xberg-io/xberg
Polyglot document intelligence with a Rust core: extract text, metadata, images, tables, and structured data from 106 formats across 140 file extensions, plus code intelligence for 371 languages. Fifteen bindings, with CLI, REST API, and MCP server.
MIT18. Okt. 2026 · Metriken 2.10.0
PyPI
chrismattmann/tika-python
Tika-Python is a Python binding to the Apache Tika™ REST services allowing Tika to be called natively in the Python community.
Apache-2.017. Sept. 2026 · Metriken 2.10.0
Packagist
j0k3r/php-readability
A fork of https://bitbucket.org/fivefilters/php-readability
Apache-2.011. Sept. 2026 · Metriken 2.10.0
NuGet
soenneker/soenneker.compression.sevenzip
A utility library for 7zip compression related operations
MIT8. Sept. 2026 · Metriken 2.10.0
npm
Ismail-elkorchi/dir-archiver
Directory archiving CLI and library for ZIP, TAR, and layered compression across Node.js, Deno, and Bun.
MIT15. Sept. 2026 · Metriken 2.10.0
NuGet
soenneker/soenneker.compression.tar.xz
A utility library dealing with Tar and XZ (tar.xz) extraction/archiving and (de)compression
MIT10. Sept. 2026 · Metriken 2.10.0
NuGet
ARKlab/Artesian.SDK
C# Library for Artesian
MIT21. Okt. 2026 · Metriken 2.10.0
PyPI
MaartenGr/KeyBERT
Minimal keyword extraction with BERT
MIT17. Sept. 2026 · Metriken 2.10.0
NuGet
iyulab/FileFlux
.NET RAG document processing library that transforms PDF, DOCX, HWP, and more into optimized chunks via a 5-stage pipeline with Rust-based FFI readers.
MIT20. Okt. 2026 · Metriken 2.10.0
npm · crates.io · RubyGems +5
retab-dev/retab
The developper starter pack for document processing
Keine Lizenz17. Sept. 2026 · Metriken 2.10.0
Packagist
thephpleague/uri
[READ-ONLY] URI manipulation Library
MIT20. Okt. 2026 · Metriken 2.10.0
Packagist
TYPO3-Solr/ext-tika
A TYPO3 CMS extension that provides Apache Tika functionality
GPL-3.010. Sept. 2026 · Metriken 2.10.0
npm
context4ai/context
A lightweight knowledge system for small‑and‑medium teams tailored to AI Agents. It compiles Feishu Docs, local Markdown, code structures and curated business data into structured, traceable knowledge, guiding Agents to retrieve high‑quality content via pattern‑driven reasoning and exploration.
MIT14. Sept. 2026 · Metriken 2.10.0
Packagist
symfony/property-access
Provides functions to read and write from/to an object or array using a simple string notation
MIT27. Aug. 2026 · Metriken 2.10.0
crates.io · npm
theiskaa/readabilityrs
Rust port of Mozilla's standalone readability library
Apache-2.017. Sept. 2026 · Metriken 2.10.0
PyPI · crates.io
chatnoir-eu/chatnoir-resiliparse
A robust web archive analytics toolkit
Apache-2.019. Okt. 2026 · Metriken 2.10.0
PyPI
datalab-to/omni_extract_bench
A consistent, fair, benchmark for structured extraction.
Apache-2.016. Okt. 2026 · Metriken 2.10.0
PyPI · crates.io · npm
weberdak/transtractor-lib
A Rust-based library for PDF bank statement extraction. Includes Python and WASM bindings. Aspires to be a universal parser. Checkout the website to see it deployed as a web app.
MIT15. Sept. 2026 · Metriken 2.10.0
npm · PyPI · crates.io +1
muthuishere/citenexus
Evidence-first, multilingual, S3-native RAG — answers only from cited evidence (exact quote, page, bbox) and abstains when the evidence is weak, missing or conflicting. The guarantee is "no ungrounded claim". Byte-identical core across Python, Go and JavaScript. Docs: https://muthuishere.github.io/citenexus/
MIT21. Okt. 2026 · Metriken 2.10.0
Packagist
joomla-framework/archive
Joomla Framework Archive Package
GPL-2.017. Sept. 2026 · Metriken 2.10.0
npm
laurengarcia/url-metadata
npm module: Fetch a url & scrape the metadata from its HTML with Node.js or the browser.
MIT6. Sept. 2026 · Metriken 2.10.0
PyPI
EverMind-AI/EverAlgo
EverAlgo is the algorithm library behind EverMind's memory system — stateless, storage-free, focused on extraction and ranking only. Orchestration, persistence, and routing live upstream in evermem.
Apache-2.013. Okt. 2026 · Metriken 2.10.0
—
MacPaw/XADMaster
Objective-C library for archive and file unarchiving and extraction
LGPL-2.118. Sept. 2026 · Metriken 2.10.0
crates.io · RubyGems · NuGet +1
nchapman/trafilatura-rs
Extract readable content, comments, and metadata from web pages
Apache-2.019. Okt. 2026 · Metriken 2.10.0
crates.io
clark-labs-inc/pdfsink-rs
Fast pure-Rust PDF extraction library and CLI by Clark Labs Inc. — 10–50x faster than pdfplumber for text, word, table, layout, image, and metadata extraction.
MIT16. Okt. 2026 · Metriken 2.10.0
crates.io · PyPI
nchapman/justext-rs
Rust port of JusText — paragraph-level boilerplate removal for HTML
BSD-2-Clause17. Okt. 2026 · Metriken 2.10.0
npm
vosjs/vos
A video is just inputs and a function, rendered. The open programmatic video engine: deterministic, resolution-independent, mixed media.
MIT13. Sept. 2026 · Metriken 2.10.0
npm · Go
laiye-ai/adp-cli
The official Laiye ADP CLI and skill built for humans and agents. It enables agents to perform parsing, classification, extraction, validation on any type of documents with high accuracy.
Eigene Lizenz12. Sept. 2026 · Metriken 2.10.0
crates.io · PyPI
nchapman/readability-rs
Rust port of readability — extract readable content from HTML
MIT17. Okt. 2026 · Metriken 2.10.0