Hybrid search, graph indexing, and vector-symbolic memory for AI agents
A persistent and self-learning interoperable memory layer for AI agents and tools.
Stage
Startup
Not given
Founded
2026
Not given
Based in
US
Not given
Pricing model
Open source
Freemium
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.
Living Brain API: $8 per 1M input tokens and $0.50 per 1M output tokens, pay as you go with $5 minimum top-up and no monthly minimum. Living Brain Workspace: $99 per month (most popular), includes three team seats, $80 shared monthly credits for first three cycles then $50, managed Brains and agents
Key features
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
Semantic search and connection discovery
Memory scoring and optimization
REST API, SDK, CLI and MCP support
Document extraction and storage
Audio transcription
Webhook subscriptions and integrations
Slack and Telegram capture
Scheduled briefs and page history
Markdown export and structured output
Multi-brain and team collaboration
What makes it different
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
22.6X fewer tokens per question and 95% lower cost per task vs full context baseline
warm-rust
Living Brain