Palmier – bridge your AI agents and your phone
Phone as both agent remote and agent tool — genuinely new infrastructure for local AI.
Multi-backend notification system (audio, Telegram, SMS, phone)
Seven unanswered audio alerts trigger a phone call — works through iPhone Silent Mode.
AI agent developers, ML engineers running long jobs
Apprise · ntfy · Gotify
scitex-notification gives AI agents working on local and remote servers (via MCP) a multi-backend notification system — they speak progress aloud from speakers on your desktop, and escalate to a phone call if you don't respond (Twilio setup needed).
The escalation chain: TTS audio → desktop → email → SMS → phone call. After 7 unanswered audio alerts, the agent calls your phone. Works through iPhone Silent Mode via Emergency Bypass or the repeated-calls trick (iOS allows the second call from the same number within 3 minutes).
Spun out of SciTeX, a scientific computing ecosystem — but works standalone.
pip install "scitex-notification[all]"
Phone as both agent remote and agent tool — genuinely new infrastructure for local AI.
Single API key gives agents email, phone, and credit card — all with spend limits.
Hands-off: each agent gets its own mailbox, phone number, inbox and API key, and the project bundles a local Stalwart mail server in Docker plus Gmail-relay or custom-domain outbound with DKIM/SPF/DMARC. Concrete safety features (outbound scanning to catch API keys/PII) and Google Voice SMS extraction for verification codes are genuinely useful and uncommon together. If you want to prototype agents that actually talk to people/services this is a focused, pragmatic stack — but expect telephony fiddliness and compliance trade-offs in real deployments.
Full agent tool access on every utterance, unlike native realtime plugins.
TwiML polling trades latency for zero-dependency simplicity—no WebSocket server or external STT/TTS APIs.
Voice calls punch through DND where notifications fail, but reminder APIs already exist.