Concept
Vector memory
Storing facts as embeddings for semantic retrieval — Niyra's long-term memory layer.
Instead of storing memory as raw text and keyword-searching, vector memory stores embeddings (high-dimensional numerical representations) and retrieves by semantic similarity. 'When does my insurance expire' finds memories about insurance even if you said 'policy renewal'.
Niyra uses pgvector (Postgres extension) with OpenAI text-embedding-3-small for embeddings.
Related
32+
Integrations
OAuth-first
5
Channels
Web, WhatsApp, Telegram, Discord, voice
100+
Native tools
Memory, voice, browser, automation
18
Skills
JIT-loaded per turn
Keep going
Channel
Niyra on WhatsApp
Voice notes, photos, PDFs. Same Niyra as web. Where you already are.
ReadFeature
She remembers
Vector memory across sessions. Tell her on Monday, she knows on Friday.
ReadSolutions
AI for founders
The AI that runs the boring half of your company while you build.
ReadPricing
Free trial, no card
2,000 credits to put Niyra through a real day. Pro at $9 intro.
ReadIntegrations
32 apps connected
Gmail, Calendar, Slack, Linear, GitHub, Notion. All via OAuth.
ReadDocs
5-minute quickstart
Sign up, connect Gmail, set a brief. Niyra running in 5 minutes.
Read