TongFlow Goes Open Source — Announcing v0.1.0

Today we’re open-sourcing TongFlow and cutting our first public release, v0.1.0. The desktop app, the tongflow Python SDK, and the official plugin catalog are all available right now — go build something.

TongFlow is a multi-modal GenAI workflow studio: every AI model becomes a node on an infinite canvas, so you can chain text, image, video, audio, document, and 3D models together — like snapping building blocks — to make things no single model could produce on its own. If this is your first time hearing about it, start with the introduction post for the full story.

What’s in v0.1.0

This release is the whole stack, in the open:

• Desktop app — native builds for macOS (Apple Silicon / Intel) and Windows, on the Releases page. First launch preloads an example workflow so you have something to run immediately.
• The infinite canvas — work with three verbs: Add material, Transform it, Combine the results. Drop something on the canvas, pick the next step, and the connection is made for you. No parameter panels, no manual wiring.
• The plugin architecture — every runnable node is backed by a typed contract (the ABI), and a plugin supplies the how. Contracts are enforced at compile time by generated TypeScript and Python types — no runtime validation overhead.
• The tongflow Python SDK — published on PyPI, so anyone can package a model as a plugin against the ABI-generated types.
• An official plugin catalog — API plugins (OpenAI, Gemini, OpenRouter) and GPU/CPU plugins (Z-Image, FLUX.2 Klein 9B, LTX, InfiniteTalk, Wan-Animate, SeedVR2, Whisper, Qwen3, ACE-Step, and more) that work out of the box.

Start for free

The official GPU/CPU plugins run on Modal, which gives every new account up to $30/month of free GPU compute on real H100/A100-class hardware. That’s enough to generate images, animate videos, synthesize speech and music, and run an entire multi-step pipeline — without owning a GPU or paying a cent. Bring your own keys or scale up only when you’re ready.

Up and running in five minutes

1. Install the desktop app from the Releases page. The canvas opens on an example workflow.
2. Install plugins — the app ships with none. Open the plugin manager and install what you need; new plugins are usable immediately, no restart.
3. Configure credentials — open Settings and add the variables your plugins need (e.g. OPENAI_API_KEY, or MODAL_TOKEN_* for GPU plugins). Values are stored locally and take effect without a restart.
4. Run the example — node by node, or switch to Execute Mode and run the whole graph in one click.

Prefer not to install anything? Jump straight into the hosted studio at app.tongflow.com.

License and community

TongFlow is dual-licensed: AGPL-3.0 (free for individuals, research, and open-source projects) and a commercial license for closed-source or SaaS use. For business inquiries, reach us at [email protected].

This is just the first release, and the roadmap is open. If TongFlow is useful to you, a star on GitHub helps a lot. Come build with us on Discord, file issues, and ship your own plugins.

Expand your imagination, stretch your ideas — give it a try.