Hybrid search, graph indexing, and vector-symbolic memory for AI agents
Stage
Not given
Startup
Founded
Not given
2026
Based in
US
US
Pricing model
Freemium
Open source
Pricing
Free plan with pay-as-you-go model usage, 5M TPM / 100 RPM rate limits. Growth plan: $25/month with $25 in token credits included, 15M TPM / 3,000 RPM rate limits. Enterprise plan: custom, volume-based pricing with BYOC, SSO/SAML, custom SLAs, VPC and private deployments.
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
Managed Skills with instant deployment to all agents
Agent observability and debugging across all decisions
Globally distributed inference with low latency
Safety guardrails and agent evaluation
Multi-agent orchestration with stateful memory
Centralized security and access control
Support for multiple frontier LLM models
Real-time cost and performance insights
Agent Insights dashboard
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
Ship agent improvements in minutes instead of release cycles
Centralized skill management without requiring redeploy
Complete visibility into agent decisions for fast debugging
Proven safe releases with guardrails before production
No infrastructure expertise required to deploy agents at scale
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
Vivgrid
warm-rust