GenOffice

GenOffice is a free, open-source alternative to Microsoft Office for macOS, Windows and Linux. It opens and saves native .docx, .xlsx and .pptx files, edits PDF, Markdown and HTML, and puts an AI agent next to every document — not a chat box bolted on the side, but an editor that reads the file, makes the change, and shows you exactly what it touched. ODF files (.odt, .ods, .odp and the .ott/.ots/.otp templates) open as editable OOXML copies; the import is open-only — saving writes OOXML, never ODF.

• Real formats, byte-preserving. Only what you edit is rewritten. Everything else in the file survives byte-for-byte, so documents keep working in Word, Excel and PowerPoint.
• AI you can review. Edits land as tracked changes and diffs with one-click rollback. Spreadsheets get live formulas, not pasted numbers. Decks and pages are generated onto the canvas and stay fully editable. Hide a Docs selection or a Sheets cell range from the model and the AI sees only a named placeholder; the original words stay in the file and come back. Hiding covers this app's AI — the CLI, MCP tools and headless export read the file directly and still see these words.
• Local by design. Files open, edit, save and convert on your machine. PDF → Word / Excel / PowerPoint, Markdown → Word and HTML → Word all run on-device. Only the AI calls leave the machine, to the provider you choose.
• Find files by what they say. The home screen searches the names, folders and full text of your .docx, .xlsx, .pptx, PDF, Markdown and HTML files from a local SQLite index, CJK included. Optionally, the top hits are reranked by TypeSafe Jev, the System One judgment model, so the file that answers your question comes first.
• Ask your files, with sources. Star a set of documents and Ask AI on the home screen answers questions across them, citing the file behind every claim so you can open it and check.
• Your keys or none. Sign in with Genspark and skip keys, or bring your own key for Claude, OpenAI, Gemini, DeepSeek, Kimi, GLM, Qwen, Doubao, MiniMax, Grok, Mistral, OpenRouter, Requesty, Opper, Cheaper Inference, Atlas Cloud, or any OpenAI-compatible endpoint, local servers included.
• Scriptable and agent-ready. The app ships a genoffice command line and a skill for Claude Code, Codex, Cursor, Gemini CLI, GitHub Copilot, OpenCode and Windsurf, so a coding agent can create, convert, read and edit real Office files on your machine without opening a window.

Get it: macOS (Apple Silicon and Intel) · Windows (x64 and Arm) · Linux (deb, rpm, AppImage) — details and requirements in Download.

Demo

Six apps, one AI panel, a file search reranked by TypeSafe Jev, an Ask AI that answers from your starred files with sources, and a command line for your coding agent. Every screenshot is the real app on macOS, with the AI driven from the prompt you can read in the panel.

1 · Docs — open and edit .docx with an AI you can review

2 · Sheets — .xlsx with live formulas and charts, not pasted numbers

3 · Slides — from a prompt to a .pptx deck

Slide Show → Record narrates the deck slide by slide, with pause and resume. The narration and the auto-advance timings it measures are saved into the .pptx, and PowerPoint plays them back the same way.

4 · PDF — edit PDF text in place, convert PDF to Word on-device

5 · HTML — an AI page and UI builder, design brief first

Say what the page is for and who it is for. The AI proposes a design brief first — hook, palette, typography and style directions — then builds a single self-contained .html file against those tokens.

6 · Markdown — a block editor over plain .md, with Ask AI

Linked notes, the way Obsidian does it. [[wiki links]] click through to the note they name, typing [[ offers note-name completion, and ![[…]] embeds a note or a picture inline. A Backlinks panel lists every note that points at the open one, and the Graph view maps the links of the whole vault.

7 · Search — find the file that answers the question, with TypeSafe Jev

Every file in your work folder is indexed on-device: names, folders and the extracted text of Word, Excel, PowerPoint, PDF, Markdown and HTML files, in a SQLite full-text index with CJK-aware tokenizing. Switch on Jev search reranking and the top 20 local hits are judged by TypeSafe Jev, the System One model that returns one calibrated relevance score per document in a single call instead of generating text. The list is reordered by that score; if the call fails or times out, the local order stays.

8 · Ask AI — your starred files, answered with sources

Star the files you work with and the home screen's Ask AI treats them as a knowledge base. Ask a question in plain language; the agent searches the starred files, reads the ones it needs and answers with a citation after every claim. Click a citation and the file opens in the right app. Attach files to the question by dragging, pasting or from the + menu — images go to the model as visual input — and every question is kept as its own conversation: switch between them, start a new one, delete one, the list survives a restart.

Ask AI searches the same on-device full-text index as Search and reads files in pages, so the model only sees the hits and the passages it asked for, through the provider you chose. It can also call the built-in genoffice CLI to build files outright; each one appears as an artifact card under the answer, and a click opens it.

9 · CLI — your coding agent drives GenOffice, on your machine

GenOffice ships a genoffice command line and an agent skill. Install the skill and Claude Code, Codex, Cursor, Gemini CLI, GitHub Copilot, OpenCode or Windsurf can create, convert, read and edit real Office files through the same engines as the apps, without opening a window.

10 · MCP — the same tools over the Model Context Protocol

Every genoffice command is also an MCP tool. Claude Code, Claude Desktop, Cursor and any other MCP client can start genoffice mcp themselves, with no skill to install and no window open, and get 29 tools plus the op references as resources. A second, HTTP server inside the app lets an agent build a Word document in a visible editor tab while you watch.

Why GenOffice

• Open source, Apache-2.0, built in the open on GitHub.
• Yours to run. Native apps for macOS, Windows and Linux; files stay on your disk and every edit, save and conversion happens on your machine.
• Real Office files. Native .docx, .xlsx and .pptx, byte-preserving: the parts of a file you did not touch are copied exactly as they were.
• An AI that edits the document itself. Tracked changes in Docs, live formulas and charts in Sheets, slides drawn onto the canvas, every AI turn a snapshot you can roll back.
• Your model, your key. Sign in with Genspark, or bring a key for Claude, OpenAI, Gemini, DeepSeek and more, local servers and any OpenAI-compatible endpoint included.
• PDF done properly. Edit text inside the page, and convert PDF to Word, Excel or PowerPoint on-device, with system OCR for scans.
• Markdown and HTML too, with the same AI panel and local export to Word.
• Search that finds the answer, not the keyword. Full-text search over every document in your folders, indexed on-device, with optional reranking by TypeSafe Jev, the System One judgment model.
• Ask AI across your files. Star the files that matter and ask questions in plain language; every answer cites the file it came from, one click away.
• Skills. Ready-made skills, or your own SKILL.md, attached from the + menu of any AI panel.
• Scriptable. A genoffice command line, an agent skill and an MCP server put every engine at the service of Claude Code, Claude Desktop, Codex, Cursor and other agents, still on-device.
• Free, for individuals and teams alike.

AI backends

Sign in with Genspark and there is nothing to configure: model calls route through the Genspark proxy (Claude, GPT and Gemini families) and the agents get web and image search, image generation, and image/audio/video analysis.

Or bring your own key. Settings → AI lists Claude, OpenAI, Gemini, DeepSeek, Kimi, GLM, Qwen, Doubao, MiniMax, Grok, Mistral, OpenRouter, Requesty, Opper, Cheaper Inference, Atlas Cloud and OpenCode Zen/Go, plus a custom slot for any OpenAI-compatible endpoint (base URL + key), including local model servers. Search and media have their own per-capability providers under AI Media & Search: Serper, Serply, Tavily, Parallel, Keenable, Exa or Firecrawl for web search, and OpenAI, Gemini, Doubao/Seedream, GLM, Grok, Qwen, MiniMax or any OpenAI-compatible images endpoint for image generation and image/video analysis, plus DeepSeek V4.1 Flash for image analysis.

TypeSafe Jev reranks the home screen's file search. Under AI Media & Search → Local file search, switch on Jev search reranking and pick an endpoint: OpenRouter (model typesafe/jev-1.13) or TypeSafe's own API. The key is stored only on this device. It is off by default; when on, the excerpts of the top 20 local hits are sent for judgment and nothing else leaves the machine.

Parallel works without an account: its free Search MCP (rate-limited) is the default web search whenever no Genspark login or search key is configured, and it runs ahead of the DuckDuckGo scrape. Select Parallel under Web search and enter a Parallel key to use the Search API instead. Keenable is keyless too; a key only raises the rate limits.

The whole suite ships light, dark and system themes. Themes only change what is on screen: exports, prints and saved files always keep the document's own colors.

Skills

A skill is a SKILL.md that tells the AI how to do one job well: a weekly report, an NDA, a lesson plan. GenOffice ships a set of them and takes your own, in the same format coding agents use.

• Settings → Skills. Install a recommended skill, or Import a folder, a zip or a single SKILL.md. Nothing runs on import.
• In a chat. Open the + menu next to the composer of any AI panel, pick Skills, tick one, send. The skill goes along with that message only.

---

Command line and agent skill

Everything the apps can do to a file, the genoffice command line can do from a terminal: inspect, convert, create, read and edit Word, Excel, PowerPoint, PDF, Markdown and HTML on the same engines, headless. It installs with GenOffice, needs no runtime of its own, and never sends a document anywhere. Paired with the bundled agent skill, it turns a coding agent into a document worker that produces real Office files instead of Markdown approximations.

Works with: Claude Code, Codex, Cursor, Gemini CLI, GitHub Copilot, OpenCode and Windsurf out of the box, any other agent that reads skills, and, through the MCP server, Claude Desktop and every MCP client.

Install the skill

How	What happens
Settings → Integrations in the app	Lists the agents found on this computer; one click writes the skill into each one you choose. An Update button appears when a GenOffice release ships a newer skill.
Download as zip on the same page	The layout claude.ai, the Claude desktop apps and other assistants accept as an uploaded skill.
npx skills add genspark-ai/genoffice	Installs from this repository into any skills-compatible agent.

Then start a new chat and ask for a document. The skill teaches the agent when to reach for genoffice, how to read a file before editing it, and how to check its own work.

Quickstart from the terminal

genoffice --version
genoffice info report.docx --json                  # headings and blocks; or sheets, slides, pages
genoffice convert report.md --to pdf               # md/html/docx/xlsx/pptx → pdf, pdf → docx/xlsx/pptx/md/html, odt/ods/odp → docx/xlsx/pptx, …
genoffice create --type docx --from notes.md --out notes.docx
genoffice create --type xlsx --from table.json --out sales.xlsx   # "=SUM(B2:B9)" cells stay live formulas
genoffice docs read report.docx --range 0-9 --json # then `docs apply --ops edits.json` edits in place
genoffice docs compare original.docx revised.docx --out redline.docx   # the differences as tracked Word revisions
genoffice render report.docx --out shots/          # one PNG per page, to look at what you made
genoffice open sales.xlsx                          # hand the result to the editor

Every command prints a one-line summary, or a single JSON object with --json. Edits are atomic: a rejected op leaves the file untouched and comes back with a guided error. genoffice help lists the current command surface; the full reference is packages/cli/README.md.

What the agent actually runs

The Solar System deck in the demo took one prompt in Claude Code. Behind it, the agent followed the skill's staged workflow and the CLI checked every stage before the next one started:

genoffice capabilities --json                        # which cloud tools GenOffice has configured
genoffice guide slides design                        # the deck workflow and layout library
genoffice image "the eight planets in a row …" --aspect 16:9 --out deck/assets/cover.jpg
genoffice slides check deck/outline.json --json      # 8 pages, no findings
genoffice slides check deck/pages/01.json --json     # builds one slide, audits overflow and overlap
…                                                    # one page file per slide, fixed until each check is clean
genoffice create --type pptx --spec deck/pages --outline deck/outline.json --out deck/solar-system.pptx --json
genoffice slides render deck/solar-system.pptx --out deck/shots --json
genoffice slides audit deck/solar-system.pptx --json    # 8 slides, no layout issues
genoffice slides replace deck/solar-system.pptx --slide 4 --spec deck/pages/05.json --json
genoffice open deck/solar-system.pptx

No model call happens inside genoffice: the agent does the thinking, the CLI does the building and the checking, and the result opens in GenOffice or PowerPoint as an ordinary .pptx.

MCP server

The same commands are available as Model Context Protocol tools, for assistants that cannot run a terminal or that you would rather not give one. There are two ways in, both shown with copy-ready snippets in Settings → Integrations → MCP:

Way	What it is
A · genoffice mcp (recommended)	A stdio server the assistant starts itself; GenOffice does not need to be open. One tool per command (info, convert, create_docx, create_xlsx, create_pptx, create_pdf, docs_read / docs_apply / docs_check, sheet_*, slides_*, render, guide, search, image, media, open) plus the staged deck flow deck_start → deck_page → deck_build → deck_replace. Ops, specs and Markdown are passed inline, so a client without a file system still works.
B · Local HTTP server	Runs inside the GenOffice app on http://127.0.0.1:3093/mcp (Streamable HTTP, with legacy SSE). Its tools drive a visible Word editor tab: create_session, insert_content, replace_blocks, apply_ops, read_document, save_session, and you watch the document take shape. Off by default; switch it on in the same settings pane.
C · genoffice mcp --http	The stdio tool set as a Streamable HTTP server for clients on other machines: a container, a sandbox, a shared box on your network. Files travel with the calls: PUT /files/<name> uploads one and returns a URL, every file parameter takes an http(s) URL, and a tool that writes a file hands it back as a download URL plus, when small, the bytes as an MCP resource. --host 0.0.0.0 opens it to the network, --token protects it.

# Claude Code
claude mcp add --transport stdio genoffice -- genoffice mcp

// Cursor, Claude Desktop or any other MCP client
{ "mcpServers": { "genoffice": { "command": "genoffice", "args": ["mcp"] } } }

# On the machine that has GenOffice (private network; add --token for a shared box)
genoffice mcp --http 3093 --host 0.0.0.0 --token "$GENOFFICE_MCP_TOKEN"

# From the client: upload, then use the URL wherever a tool takes a file
curl -T report.docx -H "Authorization: Bearer $GENOFFICE_MCP_TOKEN" http://server:3093/files/
#   → { "url": "http://server:3093/files/<id>/report.docx", ... }
#   docs_read({ "file": "http://server:3093/files/<id>/report.docx" })
#   docs_apply(...) → output_url, downloadable with curl -o

Over HTTP every session gets a private scratch folder, relative paths and deck folders resolve inside it, open is not offered, and with GENOFFICE_ALLOWED_ROOTS unset the tools cannot leave the server's own file store. render, convert to PDF and create_pdf still start a hidden GenOffice process, so a headless host needs the app installed and a virtual display (xvfb-run).

genoffice here is the CLI shipped inside the app (on macOS /Applications/GenOffice.app/Contents/Resources/cli/genoffice; the settings pane prints the exact path for your install). The server carries its own workflow instructions and exposes the op references as genoffice://guide/* resources, so no skill is needed; the skill and the MCP server can coexist and the assistant picks one. Cloud features (search, image, media) still go through the provider configured in GenOffice; everything else runs locally, and GENOFFICE_ALLOWED_ROOTS confines every tool to the folders you list.

The renewable-energy deck in the demo is what one prompt in Claude Code with only the genoffice MCP server attached looks like from the protocol side:

capabilities · guide(slides, spec) · guide(slides, design)
search(query) ×4                         → IEA, BNEF and IRENA figures for the slides
search(query, images) ×7 · media(url, ask) ×7
                                         → candidate photos, each one checked to be a real photograph
deck_start(dir, style, outline)          → outline checked: 8 pages to write
deck_page(dir, 0, page) … deck_page(dir, 7, page)
                                         → each page checked against the outline and the palette; one page sent again
deck_build(dir, out)                     → renewables-2026.pptx, no image failures
slides_audit(file) · slides_render(file, out)
                                         → no layout findings; 8 PNGs come back as image content
deck_replace(dir, n, page) ×3 · slides_render(file, out)
                                         → three pages fixed after looking at the renders

Thirty-eight calls, about thirteen minutes, and the assistant never touched a shell: the figures, the photos, the guides, the checks and the renders all travelled as MCP tool results. Only search and media left the machine, to the provider configured in GenOffice.

Download

Platform	Requirements	Download
macOS — Apple Silicon (arm64)	macOS 11+	Latest .dmg (arm64)
macOS — Intel (x64)	macOS 11+	Latest .dmg (x64)
Windows (x64, most PCs)	Windows 10+, Intel/AMD	Latest -x64.exe installer
Windows on Arm (ARM64)	Windows 11 on Arm (Snapdragon X and similar)	Latest -arm64.exe installer
Linux — Debian / Ubuntu	x86_64, glibc 2.34+ (Ubuntu 22.04 or newer)	Latest .deb
Linux — Fedora / RHEL / openSUSE	x86_64, glibc 2.34+ (Fedora 35+, RHEL 9+, Leap 15.6+)	Latest .rpm
Linux — other distributions	x86_64, glibc 2.34+, FUSE 2	Latest .AppImage

All builds come from main; the macOS and Windows installers are signed. Older versions are on the Releases page.

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

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

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

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

The AppImage 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 GenOffice-<version>.AppImage
./GenOffice-<version>.AppImage

How it works

Seven Electron apps — Docs, Sheets, Slides, PDF, Markdown, HTML and the tabbed shell — share one engine layer of pure TypeScript packages plus a Rust sidecar for .xlsx. The original file is always the source of truth: edits are applied as narrow patches, and everything the editor did not touch survives the round trip untouched.

open docx ─► archive original by hash (never touched)
          ─► parse word/document.xml into a block tree, each block anchored to its original XML
          ─► Tiptap editor (manual + AI editing, dirty tracking)
save      ─► dirty blocks → OOXML fragments (referencing existing styles only)
          ─► splice into the original document.xml; untouched blocks keep their bytes
          ─► repack the zip; every other entry is copied byte-for-byte

The package-by-package tour (docx/pptx engines, pdf2docx, html2docx, the agent core and providers) lives in CONTRIBUTING.md.

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 six 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 @genoffice/sheets compiles it automatically. See CONTRIBUTING.md for the checks every change must pass and how pull requests land.

Community

GenOffice is in active development and your feedback shapes it.

• Report a bug or request a feature in GitHub Issues.
• Join the GenOffice group chat on GenTeam to talk to the team and other users.
• Follow @merrickbuilds on X for release notes, demos and what is being built next.
• Star the repo if GenOffice is useful to you — it is the best way to support the project.

FAQ

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

Yes. GenOffice 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.

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

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

Yes — 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.

Yes. Besides the keyless Genspark sign-in, GenOffice supports bring your own key for Claude, OpenAI, Gemini, DeepSeek, Kimi, GLM, Qwen, Doubao, MiniMax, Grok, Mistral, OpenRouter, Requesty, Opper, Cheaper Inference, Atlas Cloud and OpenCode Zen/Go, plus any OpenAI-compatible endpoint — including local model servers. Search, image generation and image/video analysis take their own keys under Settings → AI Media & Search.

Yes. Settings → AI carries a Show the AI sidebar switch. Off, and every editor hides the sidebar; new documents stop opening it on their own. An explicit AI action — a ribbon button, a menu item — still opens the panel for that document, and closing it returns to hidden.

Yes — Export as Word in the HTML app produces a native, editable .docx entirely on-device. The page is rendered in the built-in Chromium and reduced to real Word structures: headings, paragraphs, lists, tables, cards, KPI rows, form fields and page backgrounds; only visuals with no Word counterpart (charts, icons, decorated boxes) are embedded as pictures.

Yes. GenOffice installs a genoffice command line that runs the same engines headless: inspect, convert, create, read and edit documents from a terminal or a script, with --json output for programs. The bundled agent skill teaches Claude Code, Codex, Cursor, Gemini CLI, GitHub Copilot, OpenCode and Windsurf to use it; install it from Settings → Integrations. See Command line and agent skill.

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 GenOffice 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

GenOffice 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.
• CodeMirror (MIT) — the source editor in HTML.
• 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.
• libeot (MPL-2.0) — the MicroType Express decoder for embedded PowerPoint fonts, ported to TypeScript.
• React (MIT) — the UI layer of every app.
• Mermaid (MIT) and (MIT) — diagrams and math in Markdown and Docs.

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.

License

GenOffice 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 GenOffice Enterprise License.

The GenOffice 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.