| What it does | Hybrid search, graph indexing, and vector-symbolic memory for AI agents
| The AI agent hosting platform
|
|---|
| Stage | Startup
| MVP
|
|---|
| Founded | 2026
| Not given
|
|---|
| Based in | US
| Not given
|
|---|
| Pricing model | Open source
| Free trial
|
|---|
| 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.
| Free 7-day trial per app. Paid plans are per app: Starter $49/mo (1,200 generations/month, $20/mo managed-LLM credit, XS-SM agent sizes, email support); Pro $129/mo (3,500 generations/month, $50/mo managed-LLM credit, XS-MD agent sizes, priority support); Scale $299/mo (9,000 generations/month, $100
|
|---|
| 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
| - One script tag integration for landing pages
- SDK for app embedding
- Generative UI for agent responses
- Pricing question answering
- Calendar link handoff for serious leads
- Visitor inquiry reporting
- Isolated pod runtime per deployed agent
- Always-on runtime without cold-starts
- Bring your own LLM key option
|
|---|
| 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
| - Metered billing with spending caps, no surprise costs
- Per-app billing rather than per-account, so you upgrade only apps that take off
- Generative UI adapts interface to each request
- No cold-starts on deployed agents, always-on runtime
|
|---|
| Free plan | Not given
| Not given
|
|---|
| Open source | Not given
| Not given
|
|---|
| Platforms | Not given
| Not given
|
|---|
| Public API | Not given
| Not given
|
|---|
| Community votes | 0 | 0 |
|---|
| DR (Domain Rating by Ahrefs) | 26 ● no change since last check | 13 ● no change since last check |
|---|
| Trust Flow (Majestic) | 12 | 0 |
|---|
| Citation Flow (Majestic) | 24 | 18 |
|---|
| Referring domains (Majestic) | 56 | 32 |
|---|
warm-rust
Guuey