[opensourcedex]

HermesOffice is a free, open source office suites project written in TypeScript and released under Apache-2.0. It has 589 GitHub stars, 78 forks and 27 open issues, and was last pushed 36 hours ago. On this registry it ranks #13 of 13 tracked projects in Office Suites, with 5 head-to-head comparisons available.

What is HermesOffice?

HermesOffice is a free, Apache-2.0-licensed, AI-native office suite for macOS, Windows, and Linux that opens and saves the real Microsoft Office formats — Word (.docx), Excel (.xlsx) and PowerPoint (.pptx) — alongside PDF and Markdown, and it is aimed at individuals and teams who want AI-assisted document editing without sending their files to a cloud service.

What it is

HermesOffice is an open-source alternative to Microsoft Office, built around AI editing as a first-class workflow rather than a chat box bolted onto a traditional editor. It is written in TypeScript and shipped as six Electron apps that share one engine layer: a word processor, a spreadsheet, a presentation editor, a PDF editor and a Markdown editor. The project lives in the criptogus/HermesOffice repository under the Apache-2.0 licence and carries topic tags including ai-native, local-first, docx, xlsx, pptx, pdf, mcp, electron and univer.

The concrete problem it addresses is the fidelity gap that normally comes with leaving a paid office suite. Its .docx editing is byte-preserving, meaning only the content a user actually touched changes, and its pagination is Word-faithful, so page breaks land where Word puts them. Spreadsheets run on an in-house engine with a Rust .xlsx sidecar, and presentations run on an in-house .pptx engine, so existing Word, Excel and PowerPoint files can be opened and saved rather than converted into a lossy foreign format. PDF conversion — to editable .docx, .pptx or .xlsx — runs entirely on the machine, with no cloud and no upload.

Key capabilities

  • Opens and saves the real Microsoft Office formats — .docx, .xlsx and .pptx — and also edits PDF and Markdown.
  • Retains text and images directly in the PDF page, preserving the original fonts, rather than round-tripping through a converter.
  • Converts PDF to Word, PowerPoint or Excel locally, and reads scanned pages with the system OCR on macOS and Windows.
  • Provides an Excel-compatible spreadsheet engine with its own charts, pivot tables and slicers, plus a PowerPoint-compatible engine with masters, layouts, smart guides and non-destructive crop.
  • Converts Markdown to Word fully locally through the same OOXML engine, with no Pandoc and no cloud service involved.
  • Edits documents with AI at block level, using snapshots and diffs and document-aware agents, and supports bring your own key (BYOK) across Claude, OpenAI, Gemini, DeepSeek, Kimi, GLM, Qwen, Doubao, MiniMax, Grok, Mistral, OpenRouter or any OpenAI-compatible endpoint — or a Genspark sign-in that skips API keys entirely.
  • Bundles agent tools for web and image search, image generation and media analysis, with light, dark and system themes.

Who uses it and how

  • Individual macOS users on Apple Silicon running macOS 11 or later install the published .dmg and get one-click updates to the newest build.
  • Teams that must keep document data on their own machines use the local PDF conversion and local Markdown-to-Word path, since neither route uploads a file.
  • Organisations that already hold large libraries of .docx, .xlsx and .pptx files use it for editing that stays compatible with Microsoft Word rather than exporting to a new format.
  • Users who want AI editing under their own provider contract configure BYOK against their chosen endpoint, while those without keys can sign in with Genspark.
  • Developers on Windows 10 and later, on Linux with x86_64 and glibc 2.34 or newer (FUSE 2 for some distributions), and on Intel macOS build the application from source.

Getting started

Download the latest HermesOffice-arm64.dmg for macOS on Apple Silicon from the releases page — the link is stable and always points at the newest build. Windows, Linux and Intel macOS users build from source, as no published artifact exists for those platforms yet.

How it compares

Microsoft Office is the paid product this project positions itself against, and the difference is chiefly one of licence and cost model: HermesOffice is Apache-2.0 and free, while Microsoft Office is proprietary and licensed. Because it runs as a desktop application with local conversion and local-first processing, documents stay on the user's machine, and AI requests travel only to the provider whose key the user supplies rather than through a vendor-hosted service.

When to use it — and when not to

Choose HermesOffice if the priority is Word-compatible editing on a local machine, PDF conversion that never leaves the device, and AI assistance billed through your own provider key; the one-click install path is currently limited to Apple Silicon macOS, so Windows, Linux and Intel macOS users must be willing to build from source. It is a poor fit for anyone who needs a fully hosted, browser-based suite with server-side collaboration, since the facts describe a desktop application rather than a cloud service. The repository also carries 27 open issues and a README that is heavily feature-oriented, so prospective adopters on the build-from-source platforms should expect to verify their own setup.

project readme (upstream, from github) — read inline

HermesOffice

The world's first full-featured open-source AI Office suite.

License: Apache-2.0 Latest release Downloads

Download · Privacy · Demo

HermesOffice is a free, open-source alternative to Microsoft Office for macOS, Windows, and Linux, built around AI editing as a first-class workflow rather than a bolted-on chat box. It opens and saves the real Microsoft Office formats — Word (.docx), Excel (.xlsx), PowerPoint (.pptx) — and edits PDF and Markdown too: a word processor, spreadsheet, presentation editor, PDF editor, and Markdown editor as six Electron apps sharing one engine layer.

Meet HermesOffice — the world's first full-featured open-source AI Office (video)

Watch the demo video on YouTube

Features

  • Real PDF editing — retype text and edit images in the page itself, original fonts preserved.
  • Local PDF → Word / PowerPoint / Excel conversion — turn a PDF into an editable .docx, .pptx, or .xlsx entirely on your machine: no cloud, no upload.
  • Scanned PDFs too — on macOS and Windows scanned pages are read with the system OCR, so they convert to editable text.
  • Microsoft Word–compatible, byte-preserving .docx editing — only what you touched changes; Word never notices.
  • Word-faithful pagination — page breaks land where Word puts them.
  • Excel-compatible spreadsheets — in-house engine with a Rust .xlsx sidecar, own charts, pivot tables, slicers.
  • PowerPoint-compatible presentations — in-house .pptx engine with masters, layouts, smart guides, non-destructive crop.
  • Markdown to Word, fully local — the same OOXML engine, no Pandoc, no cloud.
  • AI that edits documents — block-level edits with snapshots and diffs, document-aware agents.
  • Bring your own key (BYOK) — run the AI on your own API key: Claude, OpenAI, Gemini, DeepSeek, Kimi, GLM, Qwen, Doubao, MiniMax, Grok, Mistral, OpenRouter, or any OpenAI-compatible endpoint — or sign in with Genspark and skip keys entirely.
  • Agent tools built in — web/image search, image generation, media analysis.
  • Light / dark / system themes.
  • macOS, Windows, Linux.
  • Free & open-source (Apache-2.0).

Download

macOS · Apple Silicon — download the latest .dmg One click, always the newest build. That link never changes — it is also the one to share or put on a page.

Platform Requirements Download
macOS — Apple Silicon (arm64) macOS 11+ .dmg · .zip
macOS — Intel (x64) macOS 11+ build from source — no published artifact yet
Windows (x64) Windows 10+ build from source — no published artifact yet
Linux — Debian / Ubuntu x86_64, glibc 2.34+ build from source — no published artifact yet
Linux — Fedora / RHEL / openSUSE x86_64, glibc 2.34+ build from source — no published artifact yet
Linux — other distributions x86_64, glibc 2.34+, FUSE 2 build from source — no published artifact yet

Builds come from main. The macOS bundle is ad-hoc signed, not notarized (there is no Apple Developer ID behind it yet), so the first launch needs one confirmation: right-click the app → Open, or allow it under System Settings → Privacy & Security.

Older versions are on the Releases page.

Installing on Linux

The deb installs with apt — it pulls in the dependencies and adds HermesOffice to the applications menu:

sudo apt install ./hermesoffice_<version>_amd64.deb

On Fedora / RHEL-family / openSUSE, install the rpm instead:

sudo dnf install ./hermesoffice-<version>.x86_64.rpm     # Fedora / RHEL family
sudo zypper install ./hermesoffice-<version>.x86_64.rpm  # openSUSE

The AppImage instead runs in place: install the FUSE 2 runtime (sudo apt install libfuse2; on Ubuntu 24.04 the package is libfuse2t64), make the file executable, then run it:

chmod +x HermesOffice-<version>.AppImage
./HermesOffice-<version>.AppImage

Apps

App Product What it is
apps/docs HermesOffice Docs .docx word processor. Byte-preserving round trip: only dirty paragraphs are regenerated (paragraph patch), everything else in the original file is kept byte-for-byte, so opening and saving never breaks layout in Word. Paginated view whose line metrics reproduce the original document's layout, tracked changes, comments, styles, equations, ink.
apps/sheets HermesOffice Sheets .xlsx spreadsheet. UI built on the open-source Univer core (Apache-2.0) with a large layer of in-house extensions; .xlsx import/export runs through an in-house Rust sidecar (calamine + IronCalc), charts are rendered in-house (Konva), plus pivot tables, slicers, conditional formatting, and formula tracing.
apps/slides HermesOffice Slides .pptx presentations. In-house .pptx parse/render/edit engine with masters, charts, cropping, ink, and text shaping (HarfBuzz metrics).
apps/pdf HermesOffice PDF .pdf viewer/editor on pdf.js (Apache-2.0) + pdf-lib (MIT): annotations, forms, outlines, stamps, signatures, page operations, and printing support. True text editing — paragraph selection with in-block reflow, alignment restoration, original-font preservation — and content-stream image insert/edit, all rewriting page content streams through PDFium wasm (BSD-3-Clause) with subset-embedded fonts — no cover-up annotations. Converts PDFs into editable Word, PowerPoint, and Excel files fully locally (packages/pdf2docx), with OCR support for scanned pages (system OCR on macOS and Windows).
apps/markdown HermesOffice Markdown .md / .markdown editor: Tiptap block editor over plain Markdown files — headings, lists, tables, images, code blocks — saved back as plain Markdown, hosted in shell tabs.
apps/shell HermesOffice The suite shell: home screen, tabbed hosting of the five editors, light/dark/system theme, auto-update.

Every app embeds the same AI panel: block-granular AI editing with version snapshots and diffs in docs, a tool-calling agent over workbook/slide/PDF state in the others.

The whole suite ships light / dark / system UI themes built on shared design tokens (packages/ui), with a CI guard that keeps chrome colors on the token system. Document surfaces stay light in dark mode — Word-style dark chrome around white paper — so files render and export identically in both themes.

AI backends — Genspark sign-in or bring your own key. By default the apps sign in to a Genspark account through a device-code flow — no model API key to enter — and model calls route through the Genspark proxy (Claude, GPT, and Gemini families). Or bring your own key (BYOK) in the AI settings: Claude, OpenAI, Gemini, DeepSeek, Kimi, GLM, Qwen, Doubao, MiniMax, Grok, Mistral, and OpenRouter are built in, plus a custom provider slot for any OpenAI-compatible endpoint (base URL + key), local servers included. A Genspark account also unlocks the Genspark ("gsk") tool endpoints the agents build on — web and image search, image generation and editing, image/audio/video analysis, and audio transcription — all reachable through packages/ai-search for anyone extending the agent layer.

Engine packages

All pure TypeScript, no Electron dependency, unit-tested (except the UI kit):

  • packages/docx-engine — docx parsing → block tree (with docxIndex anchors and passthrough), OOXML fragment generation, byte-level paragraph patching.
  • packages/pptx-engine / packages/pptx-render — pptx model and rendering.
  • packages/pdf2docx — local PDF → DOCX conversion: PDFium character-level extraction, pure-geometry layout analysis, rebuild through docx-engine; the same analysis drives the PDF app's PowerPoint and Excel exports.
  • packages/file-parse — text extraction for AI attachments (office formats, text formats).
  • packages/agent-core — the AI agent loop and skill composition shared by every app.
  • packages/ai-provider — provider abstraction and streaming for the model backends.
  • packages/ai-search — Genspark auth + web/image search tools.
  • packages/i18n, packages/ui, packages/project-store, packages/electron-utils — shared i18n core, React UI kit, recent-files store, and Electron main-process helpers.

Development

npm install
npm run fixtures     # generate test .docx fixtures
npm test             # engine + app unit tests (docs/sheets/slides need no display)
npm run typecheck    # tsc --noEmit across every workspace
npm run dev          # all five editors + shell against Vite dev servers
npm run dev:docs     # a single app (same pattern works per workspace)
npm run dist:mac     # package macOS dmg (regenerates third-party notices)
npm run dist:win     # package Windows nsis installer
npm run dist:linux   # package Linux AppImage + deb + rpm

The sheets app additionally needs a Rust toolchain for its xlsx sidecar (cargo on PATH); npm run build -w @hermesoffice/sheets compiles it automatically.

Local UI/e2e driver scripts (Playwright + Electron, for local acceptance, not committed by default) live in scripts/drivers/.

Architecture notes (docx round trip)

open docx ─► archive original by hash (never touched)
          ─► docx-engine parses word/document.xml top-level elements (w:p / w:tbl / …)
          ─► Block tree, each block anchored by docxIndex + original XML slice
          ─► Tiptap streaming editor (manual + AI editing, dirty tracking)
save      ─► dirty blocks → OOXML fragments (referencing existing styles only)
          ─► splice into original document.xml (untouched blocks keep original bytes)
          ─► repack zip; all other entries copied byte-for-byte

The same philosophy holds in sheets and slides: the original file is the source of truth, edits are applied as narrow patches, and everything the editor didn't touch survives the round trip untouched.

FAQ

Is HermesOffice free? Yes. HermesOffice is free and open-source under the Apache-2.0 license — no trial, no paid tier for the apps themselves.

Can HermesOffice open Microsoft Word, Excel, and PowerPoint files? Yes. HermesOffice opens and saves native .docx, .xlsx, and .pptx files. Saving is byte-preserving: parts of the file you didn't touch are written back byte-for-byte, so documents keep working in Microsoft Office.

Does HermesOffice work offline? Document editing is fully local — files never leave your machine to be opened, edited, or saved. The AI features (agents, search, image tools) need a network connection, with either a Genspark sign-in or your own model API key (BYOK).

Can HermesOffice edit PDF files? Yes — real PDF text and image editing that rewrites the page content stream with the original fonts preserved, not cover-up annotations.

Can HermesOffice convert PDF to Word, Excel, or PowerPoint? Yes — HermesOffice converts PDFs into editable .docx, .xlsx, and .pptx files entirely on-device: PDFium character-level extraction plus geometry-based layout analysis, no cloud service, no upload. Scanned pages are covered too — on macOS and Windows the system OCR reads them, so they convert to editable text rather than a page image.

Can I use my own AI model or API key? Yes. Besides the keyless Genspark sign-in, HermesOffice supports bring your own key (BYOK) for Claude, OpenAI, Gemini, DeepSeek, Kimi, GLM, Qwen, Doubao, MiniMax, Grok, Mistral, and OpenRouter, plus any OpenAI-compatible endpoint — including local model servers.

Does HermesOffice collect any data? Official packaged builds send limited usage analytics by default, and you can disable reporting at any time under Settings → General. Analytics never sends document content, file names, file paths, account identity, or email addresses. See HermesOffice Privacy for the complete event and data disclosures.

Security

See SECURITY.md for the process security posture (renderer sandboxing, IPC validation, external-link gating) and the threat models for AI-generated content.

Acknowledgements

HermesOffice would not be possible without these open-source projects:

  • Electron — the desktop runtime for every app.
  • Univer (Apache-2.0) — the spreadsheet UI core that Sheets extends.
  • PDFium (BSD-3-Clause, bundled via @embedpdf/pdfium) — the content-stream engine behind true PDF text and image editing.
  • pdf.js (Apache-2.0) and pdf-lib (MIT) — PDF rendering and document assembly.
  • Tiptap / ProseMirror — the block editors in Docs and Markdown.
  • Konva — canvas rendering for Slides and Sheets charts.
  • HarfBuzz (wasm) — text-shaping metrics for complex scripts.
  • calamine and IronCalc — the read and calc layers of the Rust xlsx sidecar.
  • Liberation, Carlito, Caladea, and Noto CJK fonts (OFL/Apache-2.0) — bundled document fonts.

Third-party notices

npm run notices regenerates the bundled third-party license summary (tools/gen-third-party-notices.mjs); all runtime dependencies are MIT/Apache-2.0/BSD-3-Clause/OFL, and the bundled fonts (Liberation, Carlito, Caladea, Noto CJK subsets) are OFL/Apache.

License

HermesOffice is licensed under the Apache License 2.0, with one exception: the ee/ directory is reserved for future enterprise modules and is covered by the HermesOffice Enterprise License.

The HermesOffice and Genspark names and logos are trademarks of Mainfunc, Inc. The Apache-2.0 license does not grant permission to use them (see section 6); forks should use their own branding.

Frequently asked questions

Is HermesOffice free to use?

HermesOffice is open source under the Apache-2.0 licence. There is no licence fee and no seat count — you can self-host it or, where the project offers one, pay a vendor for a managed version instead.

What does HermesOffice do?

Free, open-source AI Office suite (Word, Excel, PowerPoint, PDF, Markdown) — macOS build, one-click install

What is HermesOffice written in?

HermesOffice is primarily written in TypeScript. Its source is publicly available at https://github.com/criptogus/HermesOffice, and it has 589 GitHub stars.