[ arisa.sh ] v5.2.11thinking...
 █████╗ ██████╗ ██╗███████╗ █████╗ 
██╔══██╗██╔══██╗██║██╔════╝██╔══██╗
███████║██████╔╝██║███████╗███████║
██╔══██║██╔══██╗██║╚════██║██╔══██║
██║  ██║██║  ██║██║███████║██║  ██║
╚═╝  ╚═╝╚═╝  ╚═╝╚═╝╚══════╝╚═╝  ╚═╝

Arisa: an open-source AI assistant for Telegram

Run it on your own machine. Powered by Pi Agent.

$npm i -g arisa && arisa

1.1about

readme ▸ overview

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. It starts minimal and grows from real use.

  • 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

1.2load

minimal experience
arisa37 kB
openclaw85 MB
3 deps vs 55 deps · openclaw is ≈ 2,300× heavier and carries 18× more dependencies
version 5.2.11footprint 37 kBdeps 3iface Telegram

2install

npm i -g arisa

Install globally, then run arisa. First launch guides you through Telegram setup, Pi provider/model selection, authentication, and validation.

ChatGPT subscription is enough: Arisa can authenticate through Pi's Codex OAuth flow, so you do not need a standard OpenAI API key when using supported providers.

commandaction
arisarun in foreground, blocking
arisa startstart in background
arisa stopstop background service
arisa statusshow background service status
arisa flushremove ~/.arisa
arisa --silentrun without verbose logs
arisa --pi.model ...override the model for the current process only

3arch

two pipes ▸ one engine

Arisa separates pre-reasoning normalization from reasoned action. Voice can become text before reasoning; TTS, downloads, and other chains happen after the agent decides.

telegram
text · voice · media
pi agent
one session per chat · queued batches
tools + artifacts
isolated CLI · chained pipes

4zero tools

assembled on demand

A fresh install ships with zero tools. The core is Telegram transport, the Pi Agent reasoning loop, the artifact store, and the tool registry.

  1. a request arrives that current tools cannot satisfy
  2. Arisa checks the official catalog for a matching tool
  3. low-footprint tools install immediately; heavier tools ask for confirmation
  4. if no catalog tool fits, Arisa builds the missing capability
  5. installed tools live in ~/.arisa/tools/ and are reused later

create and publish

Turn text and ideas into files or live sites.

communicate

Work across email, WhatsApp, and X with explicit safety rules.

operate

Schedule work, connect machines, and run realtime infrastructure.

extend and maintain

Connect external tools, review operations, and keep installations reproducible.

review

Check security and clean up public writing.

browse all 41 official tools on GitHub

5cookbook

tools in the wild

Arisa is not a feature list. It adapts to the work: it connects tools, keeps context, and lets each chat decide how much control to retain.

use caseflow
multiplayer
WebRTC without a game server
signaling-server coordinates peers and turn-server provides TURN relays when a direct connection is not enough. Useful for rooms, calls, data channels, and multiplayer games.
a live site
idea → design → HTTPS
Ask for a landing page or internal tool: site-builder shapes the page and roster-sites publishes it with a domain and HTTPS.
MCP workflows
secure profile → specialized action
mcp-client connects chat-scoped MCP profiles with guarded OAuth and endpoint validation. magnific-mcp turns that transport into direct image generation, collection, download, and upscale workflows.
headless Arisa
master → paired slave → bounded operation
master-slave pairs a main Arisa with headless Linux Slaves. Each Slave reconnects outward and exposes only the roots and inspect, read, or command capabilities allowed by its stored policy.
process review
observe → explain → propose
process-retrospective reviews recent operations on a rotating focus, surfaces a bounded set of improvements, and never applies changes without approval.
live WhatsApp
group, lookup, or reply
whatsapp-web keeps one session per chat. It can reply in a group, search the web to compare prices, or send received audio through openai-transcribe before Arisa replies.
press campaign
research → draft → Gmail
lightpanda-browser finds a real reference. pr-campaign tracks the contact, creates the personalized outreach, and calls gmail-workspace to save it in Gmail Drafts. In review mode, it waits for approval; in automatic mode, it sends only within the campaign rules. stop-slop-writer checks the tone.
X outreach
discover → approve → verify
x-session-reader reads public session content, x-campaign-runner selects one evidence-backed prospect, and x-dm follows or sends only after explicit approval and account checks.
remember and remind
context → scheduled task
context-vault stores chat-scoped facts and preferences. schedule-agent-task wakes the agent later with the right instruction.
read it aloud
web page → text → voice
url-to-markdown extracts readable text from a page, then openai-tts returns an OGG voice message.
deliver a report
research → Markdown → PDF
web-browser gathers sources, markdown-pdf renders the report, and file-document can return an existing local file through Telegram.
web security
authorized audit
web-pentest-auditor checks headers, CORS, public routes, bundles, and token storage without attacking or modifying the site. It is technical review a normal chat cannot run on its own.
understand media
download → inspect → transcribe
video-downloader fetches the source, video-analyze samples visual evidence, and audio-extractor prepares sound for openai-transcribe or local whispermix-transcribe.
pipes
one tool prepares the next
Tools do not live in isolation: URL → video → audio → transcript; research → reference → draft; message → WhatsApp reply. Arisa assembles the pipe it needs and reuses it.

6philosophy

working model

Arisa starts small and changes through the work you give it.

Telegram carries the conversation. Pi Agent handles the reasoning. Arisa adds each new capability as an isolated tool when someone needs it.

In Stories, Arisa documents how those choices shape real work.

Read Stories →
01 · user-shaped
The person using Arisa chooses what it may access, remember, automate, and publish.
02 · tool-shaped
Arisa puts each new capability in an isolated tool. The core stays focused on transport, reasoning, artifacts, and orchestration.
03 · inspectable
Arisa records artifacts, state, or receipts for its work and asks for approval before sensitive changes.
04 · self-improving
Arisa can read and patch its own code. The person using it decides which changes remain.