Hybrid search, graph indexing, and vector-symbolic memory for AI agents
Stage
Not given
Startup
Founded
Not given
2026
Based in
Not given
US
Pricing model
Freemium
Open source
Pricing
Dues: sliding scale starting at $5/month. All members receive $15/month credit for chat and API. Additional credits available for purchase; credits never expire and carry over month to month.
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
Web search built into chat
File uploads and document support
OpenAI-compatible developer API
Personal API keys
Encrypted enclave privacy option
100% renewable energy option
Member governance participation
Shared monthly credit allowance
Publicly developed models
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
Member-governed cooperative structure where users help decide the direction and choices
Equal membership with sliding-scale pricing based on ability to pay
Choice of AI models by values including privacy and renewable energy
No data lock-in; members own their data and can cancel anytime
Credits never expire and carry over month to month
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
Inference Cooperative
warm-rust