Alternatives to Xberg

Free, open-source Python framework for extracting structured data from documents using LLMs and decision models with minimal code

LitePali is a small open-source Python library for image-based document retrieval built on the ColPali architecture.

DocLine.ai extracts data from invoices, receipts, contracts, and forms using pre-trained document AI models and no-code custom field

Open-source RAG engine with built-in ETL, hybrid vector/BM25 search and visual agent orchestration for enterprise AI agents.

Open-source Microsoft Research RAG that builds a knowledge graph and community summaries from your documents, then queries them in four modes.

LanceDB is an open-source multimodal lakehouse that keeps curation, feature engineering, hybrid search, and training on one Lance table.

Apache Doris unifies OLAP analytics, full-text search, and vector search in one open-source SQL engine.

Molku extracts data from PDFs, images, and handwritten documents, then auto-fills your PDF or Google Sheets templates.

Free, open-source document AI, team management, and growth tools that you self-host with your own API keys.

Self-hosted RAG search engine for private document search — BM25 plus hybrid retrieval across 34 file formats.

OpenCrab turns your documents into versioned ontology knowledge packs that Claude, ChatGPT, Cursor and Codex query through one MCP URL.

Open-source wire protocol suite that standardizes LLM, vector, graph, and embedding calls so you swap providers in config, not code

Open-source command-line pipeline that extracts, chunks, and embeds PDFs for RAG, with switchable libraries via one parameter.

AI customs clearance automation for HS code classification and trade document processing.

Instabase (now SuperApp) turns multi-document packets into auditable, verifiable intelligence with packet-aware AI agents.

Multimodal retrieval that indexes video, image, audio and PDF files straight from your S3, GCS or R2 bucket.

Box pairs secure cloud content management with permission-aware AI for document Q&A, extraction, and drafting.

Milvus is an open-source vector database for billion-scale similarity search, hybrid retrieval, and lake-native RAG workloads

LlamaParse is a document parsing API that turns scanned PDFs, dense tables, and handwriting into AI-ready markdown or schema-bound JSON.

Vespa is an open-source AI search platform for hybrid vector, text, and tensor retrieval with machine-learned ranking.

pgvector brings open-source vector similarity search to Postgres so embeddings live next to your relational data.

Vespa AI is an open-source AI search platform for hybrid vector, text and structured retrieval with ML ranking in one query pass.

Open-source CLI that turns 18 source types into AI skills and RAG knowledge for 22 AI platforms.

Browser-based converter that turns PDFs, Office files, and images into Markdown locally — files are not uploaded.

Databend is an open-source, cloud-native data warehouse in Rust that runs BI analytics, vector search, full-text search and geospatial on

Open-source Python framework that incrementally keeps AI agent context fresh by reprocessing only changed data.

Open-source in-process vector database from Alibaba — install one Python package, query millions of vectors in seconds.

Sparrow turns PDFs and images into schema-defined JSON with Vision LLM document extraction.

REST API for pixel-level image forgery detection plus specialized OCR for Southeast Asian documents.

CellSource links every Excel figure to the exact PDF, scan, or receipt that supports it — a Mac-native audit evidence engine.