No licence per robot
Kinenix is Apache-2.0. Run unattended workers on the VMs, office PCs, or Raspberry Pis you already have. Excel and CSV work through openpyxl and pandas, so no Office installation is needed either.
Kinenix is an open-source RPA framework in Python. Each automation is a flow.md file that people and AI assistants can read, review in git, and run on any machine, with local language models for the steps that need judgment and no licence per robot.
pip install kinenix # BOT FX Transfer Rate Collector
> Description: Collect Bank of Thailand transfer rates for one month, write a CSV, and email it.
### 3. Open BOT Exchange Rate Page (`web.open`)
- **url:** `${config.url}`
- **on_error:** retry
- **max_retries:** 2
### 18. Read Transfer Rates Per Currency (`logic.loop`)
- **items:** `${config.currencies}`
- **item_var:** `currency`
### 19. Write Grouped Rates To CSV (`csv.write`)
- **file_path:** `${config.output_path}` Robots are easy to start and hard to maintain. Kinenix is designed around the second part.
Kinenix is Apache-2.0. Run unattended workers on the VMs, office PCs, or Raspberry Pis you already have. Excel and CSV work through openpyxl and pandas, so no Office installation is needed either.
A flow is Markdown that an analyst can read and a reviewer can approve in a pull request. Describe the task in requirements.md and an AI assistant writes the flow.md for you.
ai.extract, ai.prompt and ai.decide call small models through Ollama on your own hardware. Invoices, HR records and customer e-mails never leave your network, and there are no API tokens to pay for.
Retries, On Error and Finally sections, one record per run with a screenshot of each failure, and secrets redacted before anything is logged. The Hub summarizes what went wrong in plain words.
Create a project and write what the robot should do in plain language.
kinenix init "Get stock data" Validation reports unknown actions and expression errors with their line number.
kinenix validate Run once from the terminal, or hand it to a worker with a schedule or a file watch.
kinenix run Workers report to a self-hosted Hub you can query with SQL from the command line.
kinenix hub query Steps run in the order written, the same way every time. An AI step is one action among the others, with a defined output, so a model can classify an e-mail or read an invoice without deciding what the robot does next.
The format itself was chosen by testing. Small local models wrote the same flow in flow.md and in YAML; flow.md came out ahead for every model of 3B parameters or more.
5 of 5 flows parsed in flow.md, against 2 of 5 in YAML, written by qwen2.5-coder:7b
### 2. Route Customer E-mail (`ai.decide`)
- **state:** ${email.body}
- **question:** {"name": "intent",
"type": "choice",
"options": ["Receipt request",
"Problem report",
"Price enquiry",
"Cancellation"]}
- **output_var:** `route`
### 3. Open A Support Ticket (`http.request`)
- **condition:** ${route.choice} == Problem report Kinenix sits between a commercial RPA suite and a folder of Python scripts.
| Kinenix | Commercial RPA suites | Plain Python scripts | |
|---|---|---|---|
| Cost of one more robot | None | Per-robot or per-user licence | None |
| How a process is written | Markdown, diffable in git | Proprietary designer files | Python code |
| AI steps | Local models via Ollama, built in | Usually a cloud add-on | Wire up an SDK yourself |
| Where documents go | Stay on your machines | Often through vendor cloud services | Stay on your machines |
| Unattended runs | Worker with schedules and file watch | Orchestrator, licensed separately | cron or Task Scheduler |
| Run history | Self-hosted Hub with SQL views | Vendor orchestrator | Build it yourself |
| Maturity | Beta; APIs still change | Mature, with vendor support | Up to you |
Kinenix 1.0 is stable: a flow written for 1.0 keeps running on every 1.x version. Pin the version a flow needs with > Requires: kinenix>=1.0.0 so older workers refuse it instead of misreading it.
Flow interpreter, 47 actions across web, Excel, CSV, files, HTTP, e-mail and AI, and the kinenix CLI.
Unattended runner with schedules and file-watch triggers. Dispatch from the Hub is planned.
Central run records, dashboard, and plain-language failure summaries.
Visual flow editor. Flows are written with an AI assistant instead for now.
The quickstart installs Kinenix, runs an example, and connects a worker to the Hub.