Three engineers from IIT Madras building an AI that thinks like the human brain.
We went back to neuroscience - Tulving's episodic memory, Complementary Learning Systems theory, the Ebbinghaus forgetting curve - and asked: can we replicate how the human brain handles memory? Not approximate it. Replicate it.
Foundation
Built on neuroscience, not buzzwords
Tulving, 1972
Episodic Memory
Your brain runs two memory systems. Semantic memory stores general facts - what a dog is. Episodic memory stores personal experiences - YOUR dog, the way he greets you, the time he ate your shoes. Current AI has semantic memory from training data. But zero episodic memory. Anant adds the missing half.
McClelland et al., 1995
Complementary Learning Systems
The hippocampus captures experiences instantly. The neocortex consolidates them into deep understanding during sleep. Fast learning and slow integration working together. Anant's Memory Dreams are our implementation of this - daily consolidation that merges, strengthens, and prunes memories.
Ebbinghaus, 1885
The Forgetting Curve
Memory decays exponentially. But repetition and emotional significance flatten the curve. Anant implements this with confidence decay - facts you haven't mentioned in months gradually become ‘believed’ instead of ‘known’, while emotionally significant memories persist. Your grandfather's advice stays. Yesterday's lunch fades.
Build the future of AI with us.
Experience the frontier.
Join the waitlist to get early access to Anant 1.0 - an AI that builds a knowledge graph of your life.
Get Early Access