Tanuki: Your New AI Companion.
Transform unstructured data into structured documents effortlessly.
See It in Action
Beautiful screenshots showcasing your app's best features.
Why Choose Us
The key reasons users love our product.
Fast Inference
Leverages MLX for ultra-responsive inference, ensuring quick processing of documents, text, and audio.
Flexible Workflows
Tanuki workspace allows you to create your own workflows and tune them in real time. Once you've got a workflow right drop in files and trigger at the press of a button.
Use any Hugging Face models!
We dont ship any models, one is pulled on first launch. From there you can use whatever models you choose. Gated huggingface models are accessible by adding a token.
Tanuki wont touch your wallet.
It might be boring but Tanuki will never know where your bank account is. He wont send emails on your behalf. He will help you draft them but you'll never have to apologise for your Tanuki's behaviour.
Powerful Features
Everything you need to get things done.
Fast Inference
Tanuki offers super responsive inference with MLX, ensuring quick processing of documents, text, and audio. As MLX and Apple Silicon improve, so does your Tanuki.
No Risk
Experience the benefits of machine learning without understanding the technical details, Tanuki isn't an agent, it runs workflows with fixed inputs and outputs, it doesnt have access to tools or your bank account. Tanuki is excited by boring things that you dont want to do, not showing off.
Configurable Multi Step Workflows
Chain transcription, extraction, rewriting and auditing (for example) into a single, reusable action. Clean up your notes by dropping them in and one click!
Real-time Editing
Edit workflows in real-time with an intuitive editor, see the changes through the pipeline in real time.
Versatile Use Cases
Use Tanuki for transcription, summarization, and more across various industries.
Configurable Output Targets
On workflow completion, Tanuki can forward the output to your storage locations, S3, iCloud and 7 other adapters with more to come. Your workflows can choose where to send their output.
Full artefacts accessible
If you choose to persist the inference session you have access to the output from each of those steps, handy for tuning your personal workflows!
Builtin and custom workflows
Tanuki ships with a set of built in workflows so you can start work as soon as you install. We also allow you to create and tune your own workflows, all the way down to model configuration.
Works offline!
Once you have model(s) on your machine, your inference no longer requires internet access.
Local Network Access
Enable optional HTTP(S) and OIDC capacilities for for secure local network usage.
Flat, local network license
If you choose to use Tanuki on your local network, there is a single montly or annual subscription. No per user, no per token charge. Tokens are ALWAYS free!
We never snoop!
Nothing leaves your machine unless you choose to forward output to your own storage, no cloud services ever see your prompts, inputs or work. Ever.
What Users Say
Hear what our users have to say.
Tanuki is my little study buddy! Med school means im always summarising, reviewing my notes. With Tanuki helping out i can clean up my notes, summarise research materials at the press of a button. I love him!
We are testing out machine learning tasks locally on our desktops. We weren't expecting to find useful tools available. The fact that we can iterate over different models and run the same input through different models and compare results makes it a really helpful prompt engineering workbench!
Tanuki is fantastic
Tanuki is a great app for anyone who needs to process large amounts of text or audio. It's super fast and easy to use, and I can customize the workflows to fit my specific needs. I've been using it to process customer feedback and summarize customer reviews, and it's been a great tool for me.
Frequently Asked Questions
Find answers to common questions.
Yes! Tanuki can run on every generation of M series Macs. Inference is a heavy load and different generations will have different capabilities. Tanuki App can run on any machine but its performance is bound to memory, both the amount and speed. Tanuki allows you to select your own models to suite your machine. Our blog includes articles on right sizing models for your use case.
Tanuki is unique in many ways. Most importantly nothing that runs in Tanuki ever leaves your environment. You might set up Output Adapters to send your content to your own storage, but thats it! Once you have completed the first start widget and install your first model (and potentially add more) Tanuki can work without the internet! Your content is yours, we don't see it, we don't train on it, we can't use it against you.
While there are tasks that Tanuki cannot perform today, its perfect for things you do often (converting voice to notes), for summarising documents or drafting emails.
It has a lot of fun capabilities just like the hyper-scale alternatives. You can craft a template to transform your writing to sound like Dracula wrote it, or Homer Simpson. And the best part is, once you have crafted your own Workflow Templates you can run them over your content. This is a great tool for field operators, doctors, lawyers, anyone who does things on repeat and doesnt want to have to describe it every time. We are working on some really cool new workflows, things like realtime grammar support is coming this year, which we think is going to leave you wondering 'what other subscriptions can I cancel now'. If you do we'd love to hear about it!
Tokens cost nothing! This is the main difference between local inference and those giant cloud doohickey's. If you use Tanuki as a desktop tool once you purchase it thats all you pay. You can run Tanuki all day and there are no new charges. We have done load testing on Tanuki and discovered that using it all day every day will increase your annual electricity bill by something like $30-$50.
Sadly we cannot support Intel Macs, this isn't our Tanuki's being precious, MLX (the framework that runs Machine Learning models on Apple machines) can only support Apple Silicon. Again this isn't apple being precious, the performance required to run these models is only available through the unified memory architecture that makes new Macs so good to use.
Tanuki offers a subscription service that provides a HTTPS interface with an optional OIDC connection. Users can subscribe through the app's subscription page.
Yes you can and you should! Different models do different things better, and it's not always obvious why until you play. Thats why Tanuki lets you download models from Hugging Face. Just drop the id into the Model Library with the 'add model' button and Tanuki will pull that model. You can then assign it to one of the available slots (fast and deep today, more to come). Some models may not produce output by default, this is where overrides may help.
A good example is log analysis, log analysis is difficult due to its token density but coder models often handle them better.
If you have specific needs get in touch with us here, we'd love to hear about what you want to do and how our Tanuki's can help!
In the first launch wizard you have the option of selecting a 'local storage adapter', this allows tanuki to push the output of a workflow into a location on your local machine that you have set. This is helpful locally if you want the files to forward, you can always interact with the files from inside tanuki, but adapters serve a different purpose, as 'local storage' is only one variant.
Other variants allow you to push to various types of file storage, either in the cloud or locally on your network. S3/minio, iCloud, Dropbox Google, Microsoft and generic
In config there is an 'output adapters' pane that allows you to enable more output adapters globally, once enabled and configured you can enable them either in workflow templates directly, or via the Workspace homepage.
Thinking of Inference the input and other content that is passed into the Machine Learning model is called context, this includes the specific user input like a document to summarise, and other instructions. Tanuki assembles this context per workflow step based on the configuration of each steps context template. The context template has metadata that allows the user to set a series of parameters for that particular step in the workflow.
A single step might only want the input of the step before, or it may like all the steps input, or be selective, the context template lets the user make these configurations at various layers of the application.
The context templates include the prompt to the model that consumes the input and performs a task on it. That task could be cleaning up language, doing a check against organisational policy, or making your email sound like Dracula wrote it.
These templates are very similar to what you type into an online chatbot, the purpose is to reuse the same templates rather than making a new request in a chat window.
Overrides allow you to toggle the parameters of the model that your workflows are run through. There is a sophisticated stacking of overrides. At the platform level you can set the values for each 'slot', that runs a workflow step model. You can then override these values in both the Context Template and Workflow Template layer. Finally each surface you are working from includes an optional override block. These are stacked, if you change a field your change will be passed in to the model slot, all others will remain teh same.
With great power comes great responsibility, it is always possible to configure the model slot in such a way that the model crashes or runs to infinity, while working on new models be cautious, but don't worry, tokens are free!
The purpose of the widget is to take a quick sample of your voice and inject that into whatever app you are working on. In the widget configuration page you can select a workflow and choose a shortcut command. You can launch the Widget then with the shortcut, this will open the widget and start a session with it. Then you can either click on the widget or press the shortcut again. Your words will be processed by the workflow and injected in the app you are currently working in.
Compose is a scratch space that you can run a workflow over. This is useful for having Tanuki do things like draft up Emails. You can use the record button to drop text into the page or you can copy in text. You can then run the model over the content and see the change in the pane.
Compose has a chat panel that allows you to talk to Miles your Tanuki. While this is an evolving capability Miles is a little different to regular chat bots. Your full chat history lives within tanuki, so you are able to ask Miles questions that cloud based chat bots couldnt answer, like 'what types of cars did we talk about last january'.
Right now Miles cannot interact directly with the text you supply in the Compose window however in a coming release they will be able to make changes to your content based on chat.