Memory layer for AI agents that saves tokens, improves itself, and enforces access control
Hosted memory for AI agents that forgets like people do
Stage
Startup
Not given
Founded
2024
Not given
Based in
US
Not given
Pricing model
Freemium
Free trial
Pricing
Self-hosted: Free for commercial use. GoodMem Cloud: From $15/mo with usage-based pricing, 14-day free trial. Enterprise: Custom pricing.
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
Automated retrieval stack optimization
Multimodal document processing with page images
Granular access control and permissions
Hybrid search with dense and sparse embedders
Support for multiple LLM providers
Multi-language SDKs and APIs
Flexible deployment options
ISO/IEC 27001 certified security
SLSA Build L3 provenance
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
Achieves frontier model quality at 1/35 of the cost using small self-hosted models
Automatically optimizes retrieval stack for your data on real queries
Never locks you in with proprietary storage
Runs on-premises with full data control
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