IRIS presenting DeltaStore
Watch IRIS walk through how DeltaStore compresses state in real time while keeping every frame fully reconstructable.
Most AI systems are quietly drowning in their own memory. Every snapshot of agent state, every reasoning trace, and every branching simulation path gets stored in full, over and over again. DeltaStore takes a fundamentally different approach: store changes, not state. The result is lower infrastructure cost, practical time-travel debugging, and auditability by design.
Watch IRIS walk through how DeltaStore compresses state in real time while keeping every frame fully reconstructable.
Traditional AI systems repeatedly store full snapshots of state. DeltaStore records only the minimal change required to move from one state to the next, while still preserving full reconstruction.
Convergence, time-travel debug, RL replay, deep branch trees, and cache layers all show order-of-magnitude storage reduction when you store deltas instead of full snapshots.
Track 1 is healthcare and drug pricing auditability. Track 2 is DeltaStore as a drop-in memory layer for enterprise AI stacks.
Vector databases store embeddings. Experiment tools track runs. Event systems are generic. DeltaStore targets domain-specific state compression with audit-ready reconstruction.
Temporal State Compression treats the token dimension of a transformer KV cache like a temporal signal: store keyframes, store deltas between them, and reconstruct exactly or approximately later. It is the same DeltaStore idea, specialized for model memory.
Run the DeltaStore visualizer directly below and watch traditional full-frame storage diverge from delta-based storage as state evolves.
DeltaStore turns memory from a linear cost into a compressed timeline.