OpenYak

Why OpenYak

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.

What It Feels Like

Office Workflows

From Memo to Executive Brief

OpenYak can turn a dense memo into a structured brief that is ready for a manager, team update, or follow-up email.

From Spreadsheet to Finance View

Use spreadsheets as working inputs, not screenshots. Ask for budget variance, forecast risks, owner-level action items, and meeting-ready talking points.

From Multiple Files to an Artifact

OpenYak can synthesize several files in the same thread and open a right-side artifact panel for reusable briefs, plans, diagrams, and structured outputs.

Long Threads and Auto-Compress

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.

Error Recovery

Professional workflows include failure states. Upload errors and missing inputs should keep the composer usable and tell the user what to do next.

Download

Download the latest release or visit open-yak.com/download.

Linux users can also read LINUX.md for requirements and troubleshooting.

Get Started

1. Install OpenYak for your platform.
2. Connect a model using free cloud models, your own API key, ChatGPT subscription, or local Ollama.
3. Start a new conversation and attach a real file.
4. Ask for a deliverable, not just a summary: brief, action plan, RACI, email, table, or artifact.
5. 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.

Supported Providers

Cloud and Subscription

Local

Run any model available through Ollama. Local models are auto-detected and can be used without an internet connection.

Core Capabilities

• 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.

For Developers

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:all

This starts the backend on port 8000 and the frontend on port 3000. For deeper setup notes, see frontend/README.md and backend/README.md.

FAQ

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.

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.

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.

Yes. Install Ollama, download a model, and OpenYak can run locally without cloud model calls.

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.

Community

• Questions and Discussions: GitHub Discussions
• Bug Reports: GitHub Issues
• Contributing: CONTRIBUTING.md

License

MIT