█████╗ ██████╗ ██╗███████╗ █████╗ ██╔══██╗██╔══██╗██║██╔════╝██╔══██╗ ███████║██████╔╝██║███████╗███████║ ██╔══██║██╔══██╗██║╚════██║██╔══██║ ██║ ██║██║ ██║██║███████║██║ ██║ ╚═╝ ╚═╝╚═╝ ╚═╝╚═╝╚══════╝╚═╝ ╚═╝
personal Telegram assistant·powered by Pi Agent
// the agent builds itself around the user, not the other way around
Arisa keeps exactly two things and nothing more: Telegram as the human interface and Pi Agent as the reasoning engine. No pre-loaded opinions about what the agent should do or which tools it should have.
If a capability does not exist yet, the system adds a new tool for it. It grows from real use — not from assumptions.
- Telegram is the human interface
- Pi Agent is the reasoning engine
- everything is an artifact
- capabilities live in isolated CLI tools
- tools can be chained through pipes
Install globally, then run arisa. On first launch it walks you through a guided bootstrap; or skip the questions entirely with CLI overrides.
Arisa separates pre-reasoning normalization from reasoned action. Some transformations belong to the input layer; others to the agent's runtime decisions.
Arisa can install Pi Agent packages from the public registry into your user runtime, using the same package manager as Pi Agent.
The agent should not come preloaded with vices or assumptions. It starts minimal and grows through real use — shaped by the user, not by the framework.
- check whether an existing tool can solve the task
- if not, build the missing tool
- keep the solution inside the tool architecture