Critical Thinking AI for constructive criticism and science evaluation
Agent memory that learns from experience
Stage
Not given
Startup
Founded
Not given
2024
Based in
IL
US
Pricing model
Freemium
Freemium
Pricing
Not given
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
Core claim extraction and validation
Grant proposal evaluation
Personalized research insights feed
Validity scoring and contradiction resolution
SOC 2 Type II and ISO 27001 compliance
Data privacy with no model training on submissions
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
Only AI platform trained on feedback from thousands of domain experts including Nobel laureates
User manuscripts never used for model training or fine-tuning
Provides nature-reviewer-level feedback at scale
Built by scientists for scientists
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
QED Science
Vectorize