Up and running in minutes
Get InTouch AI running and have your first AI-assisted automation by the end of this page. No Docker, no cloud account, no infrastructure project.
Before you start
InTouch AI is a single self-contained server that hosts both the API and the web UI — it runs anywhere Java runs. You need three things:
- Java 17 or newer. Check with
java -version. If you need it, grab the free Adoptium Temurin build. - Python 3 for the installer (one script, runs once).
- An AI provider account. We recommend Anthropic Claude (the assistant is tuned for it), or Ollama to run fully local and free. Details in Step 4.
OS-wise: Linux, macOS, and Windows 10/11 are all fine.
Download
One zip file, about 200 MB. It contains the server, the UI, the installer, and a handful of example skills and jobs to get you oriented.
intouch-personal-edition.zip · self-contained: server JAR, WAR, sample data, startup scripts. Unzip and run.
Install
Unpack the zip and run the installer. The installer asks where to install and which port to use; the defaults are fine for a first try.
unzip intouch-personal-edition.zip
cd intouch-personal-edition
python install.py
The installer drops everything under the install directory you choose. Nothing is written outside it.
Get an AI provider key
The assistant drives InTouch AI by reasoning over a large context, so it needs a provider with a generous context window. We recommend Anthropic's Claude — it's what the assistant is tuned for. Want zero-cost and fully local? Ollama runs on your own machine, no key required.
Recommended: Anthropic Claude
- Sign up at console.anthropic.com.
- Go to API Keys → Create Key. Name it "InTouch AI" and create.
- Copy the key — it starts with
sk-ant-…and you only see it once. Keep it handy for the next steps.
Other strong choices
- OpenAI (GPT-4o) — platform.openai.com
- Google Gemini — large context, generous free tier. aistudio.google.com
- Ollama — free, runs locally, no key (a capable model + decent GPU recommended). ollama.com
First launch
InTouch AI is one self-contained server that hosts both the REST API and the web UI — a single process, no separate UI to start.
cd /path/to/intouch-personal-edition
bin/startserver
It comes up in a couple of seconds. Then open http://localhost:2200 in your browser — the web UI is served right there, same origin as the API.
First login
The Personal edition is single-user with fixed defaults:
- Username:
intouch - Password:
blueisle
These are intentionally immutable on Personal — it's a single-user, friction-free model. If you need multi-user, RBAC, and password rotation, that's what the Team / Department / Enterprise editions exist for.
Add your AI provider credential
Credentials live in a vault — jobs reference them by name, never paste keys into scripts.
- Sidebar → Credentials → Add
- Type:
anthropic(oropenai/gemini/ollamaif you chose those in Step 4) - Name: anything — My Claude Key is fine
- Group: Default Credentials
- Secret: paste the key from Step 4
- Save
Configure the AI Assistant
The AI Assistant has its own provider settings (separate from the credential you just added — the credential is for jobs/tasks; this is what powers the chat).
- Sidebar → System → Settings → AI Assistant
- Provider: Anthropic (or whatever you used in Step 4 and Step 7)
- API Key: paste the same key here (or your provider's key if you went with a different one)
- Model: pick from the list — the default for each provider is the recommended starting point
- Enabled: check the box
- Save
Say hi
Open the AI Assistant chat (sidebar → the chat icon, or wherever the current build labels it). Type something simple:
What can you help me with?
You'll get a response in a moment. Try asking it to list your jobs, summarize a recent run, or build a new automation. The assistant has tool-use access to your InTouch AI server — it can read state and take actions on your behalf.
Browse the InTouch Hub
The InTouch Hub hosts example skills and jobs you can install with one click. Browse from the sidebar (Skills view or Hub browser) or visit hub.blueisle.com directly.
The items are example starting points — provided as-is for you to install, read, and adapt to your setup. They're not productized templates that will work out of the box for everyone. Read each one's README before running.
For ideas grouped by use case, see the Examples by vertical on the home page.
Got stuck?
We're happy to help — and your feedback makes the product better. If anything breaks, confuses, or could be improved:
- Discord — join the InTouch AI community (fastest Q&A)
- Slack — join the community on Slack
- Or use the contact page
Tell us what you were trying to do and what happened — screenshots help. Someone in the community (often us) will jump in.
Automate your first thing today
The platform is production-grade and has run in enterprise production for over two decades. The hub content is illustrative starting points. Everything else is between you and your laptop.