Memory layer for AI agents that saves tokens, improves itself, and enforces access control
Hybrid search, graph indexing, and vector-symbolic memory for AI agents
Stage
Startup
Startup
Founded
2024
2026
Based in
US
US
Pricing model
Freemium
Open source
Pricing
Self-hosted: Free for commercial use. GoodMem Cloud: From $15/mo with usage-based pricing, 14-day free trial. Enterprise: Custom pricing.
Open source under Apache-2.0 license. WARM Cloud is in development with usage-based pricing for sync, backup and verification; details to be published at launch.
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
Hybrid search combining BM25 lexical and vector scoring
Vertex graph vector index with 2.29-2.75x throughput vs hnswlib
Vector-symbolic fact memory with holographic reduced representations
AES-256-GCM encryption at rest with Argon2id key derivation
Signed audit log with Ed25519 and W3C DID identity
Secure purge that overwrites deleted data with zeros
Crash-safe append-only log with checksumming
Native Rust API with Python HTTP client and Node.js bindings
MCP server integration for editors and AI agents
WARM Cloud sync, backup and verification without server access to keys or documents
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
Runs entirely locally in your process with no network calls or telemetry
Encryption at rest built into the open-source engine itself, not an enterprise add-on
Significantly faster vector search than hnswlib with graph-indexed vertex retrieval
Signed provenance and verified audit trail using C2PA, COSE and SCITT standards
Embedded library model eliminates dependency on external services or vendor lock-in
GoodMem
warm-rust