AI note taker for online meetings and in-person conversations
Agent memory that learns from experience
Stage
MVP
Startup
Founded
Not given
2024
Based in
BE
US
Pricing model
Paid
Freemium
Pricing
Kasset Core: €19/user/month or €180/user/year. Kasset Pro: €39/user/month or €384/user/year (includes one Plaud device on annual plan). Plaud devices can be purchased separately: Plaud Note Pro €189, Plaud NotePin S €159.
Self-hosted: Free, MIT licensed. Hindsight Cloud: Pay-as-you-go with free credits to start. Retain (store memories) $10.00 per million tokens, Recall (retrieve memories) $0.75 per million tokens, Reflect (synthesize patterns) $0.05 per call, Iris Extract (structured extraction) $7.50 per million tok
Key features
Records online meetings from your computer without a bot joining the call
Captures conversations on iPhone and with Plaud Note Pro and NotePin S devices
Transforms conversations into structured notes with decisions and next steps
Integration with Claude, ChatGPT and Copilot through MCP protocol
Data stored and processed in the EU by default
GDPR compliant with no model training on user conversations
1,200 transcription minutes per month on Core, unlimited on Pro
Per-user persistent memory with preferences, history and decisions kept separate
Cross-session persistence allows context to survive weeks between interactions
Fast parallel retrieval in under 100ms through four strategies running simultaneously
Works with any LLM without losing learned context when swapping models
Learns from mistakes and corrects behavior on repeated problems
Automatic pattern detection synthesizes individual facts into consolidated knowledge
Conflict detection preserves both old and new states with timestamps when facts change
Integrates with 20+ coding agents including Claude Code, Cursor, and Copilot
What makes it different
Records meetings without a bot joining the call, keeping your conversations private
Single unified library for online meetings, phone calls and in-person conversations
Never trains models on your conversations
94.6% retrieval accuracy on LongMemEval-S, beating next-best system at 74.0%
MIT licensed open source with no usage limits, telemetry or restrictions
Reflection layer automatically builds judgment and mental models over time without manual tagging
Entity resolution handles hundreds of entities with 99.5% query reduction
Kasset
Vectorize