A decentralized concurrent runtime for long-running workflows across distributed execution layers
Hosted memory for AI agents that forgets like people do
Stage
Not given
Not given
Founded
Not given
Not given
Based in
Not given
Not given
Pricing model
Not given
Free trial
Pricing
Not given
Two meters: user turns (per user turn) and stored memory (per GB-month). Pricing to be announced. Free tier with monthly allowance of turns and memories.
Key features
Tuple-Space Virtual Machine for concurrent process communication
Object Capability security model with unforgeable channel references
BlockGit DAG consensus for parallel block finalization
EVM contract compatibility through isolated sandboxes
Deterministic replay through ReplayTrie
Heterogeneous VM sandbox for concurrent coordination
Scoped authority with capability attenuation and lifecycle rules
Conversation episodes with automatic cutting and concept-based organization
Activation fading by square root of time with significance tracking
Automatic fact extraction and indexing for recall
Recall system that surfaces relevant past facts when needed
Sleep function that fades context after 24+ hours of silence
Fallback to local tail when service is unreachable
What makes it different
Durable long-running workflows that suspend and resume while keeping execution context