Read local files, compare spreadsheets, review decks, synthesize PDFs, create artifacts, continue long threads, and keep the work on your machine.
OpenYak is built for real work, not just one-off chat prompts.
- Work from your actual files. Upload DOCX, XLSX, PPTX, PDFs, CSVs, and local project context, then ask for briefs, tables, follow-ups, plans, and reusable artifacts.
- Keep the workflow in one thread. Start with analysis, continue into a RACI, ask for a follow-up email, and preserve context across long conversations.
- Choose your model path. Use free models, bring your own API key, connect a ChatGPT subscription, or run local models through Ollama.
- Stay local by default. Files, conversations, memory, and generated artifacts are stored on your device. Cloud model calls go directly to the model provider you choose.
- Use it from another device. Remote access lets you scan a QR code and send tasks to your desktop through a secure tunnel.
| Ask OpenYak to... | It should give you... |
|---|---|
| Read a long memo | Executive brief, risks, owners, next actions, and a send-ready email |
| Analyze a workbook | Budget vs. actual variance, drivers, anomalies, and finance talking points |
| Review a deck | Slide-by-slide story, evidence gaps, speaker notes, and decision ask |
| Synthesize several files | One board brief that reconciles memo, budget, deck, and PDF context |
| Continue the same thread | RACI, 30-day plan, agenda, and follow-up drafts without restating context |
| Recover from an error | Clear next step when upload, auth, or file parsing fails |
OpenYak can turn a dense memo into a structured brief that is ready for a manager, team update, or follow-up email.
Use spreadsheets as working inputs, not screenshots. Ask for budget variance, forecast risks, owner-level action items, and meeting-ready talking points.
OpenYak can synthesize several files in the same thread and open a right-side artifact panel for reusable briefs, plans, diagrams, and structured outputs.
Real office work rarely fits in one message. OpenYak is designed for follow-ups, revisions, and long conversations where the important context needs to remain available.
Professional workflows include failure states. Upload errors and missing inputs should keep the composer usable and tell the user what to do next.
| Platform | Architecture | Formats |
|---|---|---|
| macOS | Apple Silicon / Intel | .dmg, .app |
| Windows | x64 | .exe installer |
| Linux | x64 | .deb, .rpm |
Download the latest release or visit open-yak.com/download.
Linux users can also read LINUX.md for requirements and troubleshooting.
- Install OpenYak for your platform.
- Connect a model using free cloud models, your own API key, ChatGPT subscription, or local Ollama.
- Start a new conversation and attach a real file.
- Ask for a deliverable, not just a summary: brief, action plan, RACI, email, table, or artifact.
- Review the result in the chat and artifact panel, then continue in the same thread.
Example prompt:
Please read the files I uploaded and turn them into a concise team brief.
Start with three key takeaways, then list risks, owners, and next actions.
Finally, write a follow-up email I can send to the team directly.
| Provider | Access | Notes |
|---|---|---|
| OpenRouter | Built-in | Free models and premium models |
| OpenAI | BYOK | Bring your own API key |
| Anthropic | BYOK | Bring your own API key |
| BYOK | Gemini models | |
| DeepSeek | BYOK | Direct provider key |
| Groq | BYOK | Fast hosted inference |
| Mistral | BYOK | Direct provider key |
| xAI | BYOK | Grok models |
| Qwen | BYOK | Direct provider key |
| Kimi | BYOK | Moonshot models |
| MiniMax | BYOK | Direct provider key |
| Zhipu | BYOK | Direct provider key |
| ChatGPT | Subscription | Use an existing ChatGPT Plus, Pro, Team, or Enterprise plan when available |
Run any model available through Ollama. Local models are auto-detected and can be used without an internet connection.
- File understanding: office docs, spreadsheets, slide decks, PDFs, CSVs, local folders, and generated artifacts.
- Artifact workspace: reusable Markdown briefs, tables, diagrams, checklists, and structured outputs.
- Tool execution: read, write, rename, organize, and automate files with user-controlled permissions.
- Long-context work: continue from analysis to planning to follow-up without starting over.
- Remote access: connect from mobile through QR code and Cloudflare Tunnel.
- Automations: schedule recurring cleanup, reporting, and file workflows.
- Privacy controls: local storage, BYOK options, and local model support.
Tech Stack: Tauri v2, Rust, Next.js 15, FastAPI, SQLite
Monorepo Structure:
desktop-tauri/ Rust desktop shell and system integration
frontend/ Next.js chat UI, settings, artifacts, and SSE streaming
backend/ FastAPI agent engine, tool execution, LLM streaming, storage
Quick Start:
npm run dev:allThis starts the backend on port 8000 and the frontend on port 3000. For deeper setup notes, see frontend/README.md and backend/README.md.
Does my data leave my machine?
Files, conversations, memory, and generated artifacts are stored locally. If you use a cloud model, the prompt and relevant context are sent directly to the model provider you selected. You can also use local Ollama models for offline work.
Do I need an OpenYak account?
No. OpenYak is designed to work without a required OpenYak account. You can use free models, bring provider keys, connect a subscription, or run local models depending on your setup.
How is OpenYak different from ChatGPT or Claude.ai?
OpenYak runs on your desktop and is designed around local files, artifacts, tools, and workflow continuity. Web chat products are great assistants; OpenYak is closer to a local workbench for files and repeatable office tasks.
Can I use it offline?
Yes. Install Ollama, download a model, and OpenYak can run locally without cloud model calls.
How does remote access work?
Enable remote access in settings, scan the QR code, and open the mobile web client. OpenYak connects through Cloudflare Tunnel with token-based authentication, so you do not need port forwarding.
- Questions and Discussions: GitHub Discussions
- Bug Reports: GitHub Issues
- Contributing: CONTRIBUTING.md