Xberg
9,360 starsPolyglot document intelligence with a Rust core: extract text, tables, metadata and images from 107 formats — PDF, Office, images, HTML, email, archives, academic — with OCR, chunking and batch processing.
- First published：2025-01-31
- data as of：
- 2026-09-30
- Licence：
- Elastic-2.0
When to use it
For structured extraction from large volumes of mixed-format files — feeding RAG, building indexes, converting to Markdown.
Caution
Licensed Elastic License 2.0 — you may not offer it as a managed service; requires installing the Rust core binary. The repo ships Cursor and Hermes plugins alongside.
Install prompt
請幫我安裝「Xberg」技能：從 https://github.com/xberg-io/xberg/tree/main/plugin/skills/xberg（技能路徑：plugin/skills/xberg/） 取得完整的技能目錄，放進我的 Agent 的技能目錄（例如專案內的 skills/ 資料夾，或該 Agent 文件指明的全域技能位置），確認裡面的 SKILL.md 存在、frontmatter 的 name 與 description 完整，然後列出這個技能宣告的腳本、外部工具與 API 需求，先不要執行任何腳本。Paste this to your agent. It deliberately contains no tool subcommands — check the tool's official docs for commands.
Compatible with
Related patterns