| What it does | Hybrid search, graph indexing, and vector-symbolic memory for AI agents
| Cloud sandboxes and services for builders and agents
|
|---|
| Stage | Startup
| Not given
|
|---|
| Founded | 2026
| Not given
|
|---|
| Based in | US
| FR
|
|---|
| 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.
| Hobby (Free): 5 sandboxes & services at once, 16 GB of memory, pico/micro/nano/small/medium sizes, 10 GB disk. Pro (€20/month): €20 usage included monthly, 50 sandboxes & services, 80 GB memory, 5 members, all sizes, 250 GB disk, always-on briqs. Team (€100/month): €100 usage included monthly, 200 s
|
|---|
| 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
| - Linux sandbox with shell, persistent files and development tools
- Multiple services: Postgres, Redis, DuckDB, custom OCI images
- MCP integration with Claude, Cursor, VS Code
- Environment forking with data preservation
- Idle workload sleep mode with compute billing pause
- Private networks with public endpoint selection
- Spend caps, size limits and concurrency controls per credential
- Audit log for reviewing all actions
|
|---|
| 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
| - Built specifically for AI agents with native MCP protocol support
- Open-source runtime in public development with Rust and Firecracker
- Integrated services ecosystem with private networking
|
|---|
| 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 | 18 ▼ −1 (down) since last check |
|---|
| Trust Flow (Majestic) | 12 | 0 |
|---|
| Citation Flow (Majestic) | 24 | 20 |
|---|
| Referring domains (Majestic) | 56 | 24 |
|---|
warm-rust
briq