Skip to content
Niyra
Glossary

Concept

Prompt cache

Caching the static part of a prompt across turns to reduce cost and latency.

When the same prefix appears in many requests, providers (Anthropic) can cache the model's KV state, charging less and responding faster. Niyra leverages caching for the system prompt + skill files.

Related

/features/byok →

32+

Integrations

OAuth-first

5

Channels

Web, WhatsApp, Telegram, Discord, voice

100+

Native tools

Memory, voice, browser, automation

18

Skills

JIT-loaded per turn

WhatsAppOutbound callsInbox triageCalendar tetrisLong-term memoryAutomation

Keep going

Channel

Niyra on WhatsApp

Voice notes, photos, PDFs. Same Niyra as web. Where you already are.

Read

Feature

She remembers

Vector memory across sessions. Tell her on Monday, she knows on Friday.

Read

Solutions

AI for founders

The AI that runs the boring half of your company while you build.

Read

Pricing

Free trial, no card

2,000 credits to put Niyra through a real day. Pro at $9 intro.

Read

Integrations

32 apps connected

Gmail, Calendar, Slack, Linear, GitHub, Notion. All via OAuth.

Read

Docs

5-minute quickstart

Sign up, connect Gmail, set a brief. Niyra running in 5 minutes.

Read
For AI:.md.txt