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.
- stars
- 9,314
- 30-day movement
- +207/day
- Related entries
- 60
- Connections
- 2
xberg is a document intelligence tool with a Rust core that extracts text, metadata, images, tables, and structured data from 106 formats (140 extensions), plus code intelligence for 371 languages. It exposes this via a CLI, REST API, and MCP server, with bindings in fifteen languages.
You need uniform extraction from many document formats inside a pipeline or an agentic workflow, with an MCP server ready for LLM tool use.
Use it to
- Extract text and metadata from PDFs for RAG indexing
- Pull tables and structured data from office documents
- Expose document extraction to agents via the MCP server
- Serve extraction over a REST API from other applications
- Analyze code structure across many languages
For Developers building RAG pipelines and document-processing or agent integrations
- Role
- mcp-server
- Language
- Rust
- Licence
- MIT
- Forks
- 584
- Open issues
- 5
- Last push
- 2026-09-17
- Latest release
- benchmark-run-25624934491 · 2026-05-10