37 projects
txtai-xberg
Xberg document extraction and chunking pipeline for txtai embeddings
surrealdb-xberg
Xberg-to-SurrealDB connector for document ingestion pipelines — schema management, content deduplication, chunk storage, and index configuration
llama-index-readers-xberg
LlamaIndex reader for 107 document formats powered by xberg's Rust extraction engine
llama-index-node-parser-xberg
Structure-aware LlamaIndex node parser that turns xberg native chunks and elements into nodes
langchain-xberg
LangChain document loader for Xberg — extract 88+ file formats into Documents with async, batching, chunking, and rich metadata
crewai-xberg
Xberg document extraction tools for CrewAI agents — text, metadata, and batch extraction across 107 file formats
xberg
High-performance document intelligence library
xberg-cli
CLI proxy for xberg — downloads and runs the native xberg binary from GitHub releases.
ai-rulez
Complete AI development workflow for 14 AI coding tools. Ships with builtin rules, agents, and conventions. Generate native configs for Claude, Cursor, Copilot, Windsurf, Gemini, Codex and more from a single source.
xberg-hermes-plugin
Local document extraction: text, tables, metadata, images from 107 formats with optional OCR.
polylint
Universal zero-dependency linter & formatter. Installs the prebuilt poly binary and puts `poly` on PATH.
html-to-markdown
High-performance HTML to Markdown converter
html-to-markdown-hermes-plugin
Fast, lossless HTML→Markdown conversion with structured metadata, tables, and document-structure extraction.
liter-llm
Universal LLM API client with Rust-powered polyglot bindings.
liter-llm-hermes-plugin
Universal LLM API client for 165 providers — chat, streaming, tools, embeddings, search, OCR, plus an OpenAI-compatible proxy and an MCP server.
basemind
Full AI context layer over MCP — tree-sitter code-map, document RAG (PDF/Office/HTML/email + OCR + reranker), shared agent memory, on-demand web crawl, git history + blame + per-symbol diff. 300+ languages, 10+ coding-agent harnesses, content-addressed Fjall + LanceDB.
basemind-hermes-plugin
Full AI context layer over MCP — tree-sitter code-map, document RAG (PDF/Office/HTML/email + OCR + reranker), shared agent memory, on-demand web crawl, git history + blame + per-symbol diff. 300+ languages, 10+ coding-agent harnesses, content-addressed Fjall + LanceDB.
gh-actions-updater
Fast GitHub Actions reference scanner and updater
uncomment
A fast Rust-based CLI tool for removing comments from source code
crawlberg
High-performance web crawling engine
crawlberg-hermes-plugin
Web crawling and scraping with HTML→Markdown and headless-Chrome fallback.
gitfluff
Commit message linter and formatter
kreuzberg
High-performance document intelligence library for Python. Extract text, metadata, and structured data from PDFs, Office documents, images, and 88+ formats. Powered by Rust core for 10-50x speed improvements.
xberg-io-sdk
Official Python client for the Xberg Enterprise and Xberg Pro document-processing APIs.
voom-cli
Fast, safe, parallel build-artifact pruning across every major language ecosystem
tree-sitter-language-pack
Pre-compiled tree-sitter grammars for 371 programming languages
tree-sitter-language-pack-hermes-plugin
Parse and extract code intelligence from 371 programming languages with tree-sitter — structure, imports, symbols, and syntax-aware chunking.
spikard
Codegen-first polyglot web toolkit with a Rust core and bindings for 14 languages
scythe-sql
SQL compilation and code generation CLI -- PyPI wrapper that downloads the prebuilt scythe binary
starmetal
High-performance, self-hosted multi-language package registry and pull-through registry proxy for private software supply chains.
xberg-enterprise-sdk
Reserved name for the Xberg Enterprise SDK — official Python client for the Xberg Enterprise document extraction API. See https://github.com/xberg-io/sdks
kreuzcrawl
High-performance web crawling engine
kreuzberg-cloud-sdk
Official Python client for the Kreuzberg Cloud document-processing API.
langchain-kreuzberg
Kreuzberg document loader for LangChain — extract text from 88+ file formats with true async and rich metadata
prompt-template
A robust zero-dependency library for creating prompt templates
semantic-chunker
Semantic Chunker
gitmind
AI powered Git repository analysis and reporting
