Skip to content

Commit 077489d

Browse files
Goldziherakullpp
andauthored
Add xberg Java bindings
* Add xberg, html-to-markdown, crawlberg, liter-llm (Java bindings) * Clean up xberg Java entries --------- Co-authored-by: Andreas Kull <akullpp@gmail.com>
1 parent 746fce6 commit 077489d

1 file changed

Lines changed: 4 additions & 0 deletions

File tree

README.md

Lines changed: 4 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -125,6 +125,7 @@ _Frameworks that help you to leverage LLMs and AI._
125125
- [Dokimos](https://github.com/dokimos-dev/dokimos) - Evaluation framework for LLM and AI-agent applications that scores responses, validates tool calls and execution traces, and catches quality regressions in CI.
126126
- [JamJet](https://github.com/jamjet-labs/jamjet) - Agent runtime with a Java SDK for building AI agents, supporting graph-based workflow orchestration, multi-agent coordination, and MCP/A2A protocols.
127127
- [LangChain4j](https://github.com/langchain4j/langchain4j) - Simplifies integration of LLMs with unified APIs and a comprehensive toolbox.
128+
- [liter-llm](https://github.com/xberg-io/liter-llm) - Provides a Java binding for a unified LLM API client across multiple providers.
128129
- [MCP Java SDK](https://github.com/modelcontextprotocol/java-sdk) - Enables applications to interact with AI models and tools through a standardized interface (i.e. Model Context Protocol), supporting both synchronous and asynchronous communication patterns.
129130
- [Regulus](https://github.com/neul-labs/regulus) - Google ADK plugin suite that adds runtime compliance profiles, audit envelopes and GRC adapters for regulated Java AI agents.
130131
- [simple-openai](https://github.com/sashirestela/simple-openai) - Library to use the OpenAI API (and compatible ones) in the simplest possible way.
@@ -497,8 +498,10 @@ _Libraries that assist with processing office document formats._
497498
- [documents4j](https://documents4j.com/#/) - API for document format conversion using third-party converters such as MS Word.
498499
- [docx4j](https://www.docx4java.org/trac/docx4j) - Create and manipulate Microsoft Open XML files.
499500
- [fastexcel](https://github.com/dhatim/fastexcel) - High performance library to read and write large Excel (XLSX) worksheets.
501+
- [html-to-markdown](https://github.com/xberg-io/html-to-markdown) - Converts HTML to CommonMark-compatible Markdown through a Java binding.
500502
- [jackson-dataformat-spreadsheet](https://github.com/scndry/jackson-dataformat-spreadsheet) - Jackson dataformat module for reading and writing Excel (XLSX/XLS) as POJOs via `ObjectMapper`.
501503
- [Sheetz](https://github.com/chitralabs/sheetz) - Reads and writes Excel, CSV and ODS files with annotation mapping, streaming, styling and validation.
504+
- [xberg](https://github.com/xberg-io/xberg) - Extracts text, tables and metadata from PDFs, Office documents, images and other formats through a Java binding.
502505
- [zerocell](https://github.com/creditdatamw/zerocell) - Annotation-based API for reading data from Excel sheets into POJOs with focus on reduced overhead.
503506

504507
### Financial
@@ -1323,6 +1326,7 @@ _Utilities that help create the development shell environment and switch between
13231326
_Libraries that analyze the content of websites._
13241327

13251328
- [Apache Nutch](https://nutch.apache.org) - Highly extensible, highly scalable web crawler for production environments.
1329+
- [crawlberg](https://github.com/xberg-io/crawlberg) - Crawls and scrapes websites through a Java binding with Markdown conversion and optional browser rendering.
13261330
- [Crawler4j](https://github.com/yasserg/crawler4j) - Simple and lightweight web crawler.
13271331
- [jsoup](https://jsoup.org) - Scrapes, parses, manipulates and cleans HTML.
13281332
- [StormCrawler](http://stormcrawler.net) - SDK for building low-latency and scalable web crawlers.

0 commit comments

Comments
 (0)