Neuro-symbolic AI for enterprise agents that combine language understanding with symbolic logic in one integrated runtime
Hosted memory for AI agents that forgets like people do
Stage
Established
Not given
Founded
2017
Not given
Based in
US
Not given
Pricing model
Contact for pricing
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
One integrated runtime combining neural and symbolic systems
Deterministic policy enforcement before action
Complete execution trace for every turn
Natural language program authoring with code generation
Consistent decisions from identical inputs
CPU-based logic execution with lightweight language models
Managed service and custom enterprise deployment options
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
Symbolic logic governs decisions instead of neural weights
Lower operational costs through CPU-based logic and lightweight models
Forgets like people do with fading by time, not truncation
Your model, your key, your loop; service only holds history
Facts kept permanently even as episodes fade from view
Decorate, submit, report: only three lines of integration
Human-inspired memory mechanism based on cognitive science
Apollo-1
Threadless AI