Vector & Graph Engine Coming soon Open-Core + Commercial

Hypertensor GraphRAG & SIMD Vectors

Coming soon Hypertensor GraphRAG is not yet released. Details on this page may change before launch.

An in-memory typed property-graph and vector store for autonomous developer agents. It keeps the graph in RAM and serves agents over REST and MCP. That removes disk-bound lookups and external database round-trips.

0.15โ€“1.95 ms 2-hop traversal 1k nodes up to 25k nodes / 100k edges, measured
128-d default SIMD vectors per-store dimension is configurable; .NET SIMD, AVX2/AVX-512
In-Memory residency RAM-resident graph with bidirectional adjacency indices and a BM25 index
FastMCP MCP connectivity stdio, SSE and Streamable HTTP; 65+ tools
TAPE + Grounding Verifier grounding action-perception planning plus claim-to-graph verification
Core Substrates

Engine Architecture & Substrates

Built for low-latency agent workloads where a disk-bound or networked vector database adds too much per-query overhead.

โšก

Low-latency in-memory traversal

The graph store is RAM-resident. Measured 2-hop traversal is about 0.15 ms at ~1,000 nodes and 0.16 ms at ~10,000 nodes. It rises to about 1.95 ms at 25,000 nodes / 100,000 edges. A thread-safe worker pool serves concurrent queries.

๐Ÿ“

SIMD vector search

Dense cosine similarity runs on .NET TensorPrimitives with hardware SIMD. Vectors are 128-dimensional by default and configurable per store. It is combined with BM25 for hybrid retrieval. Level Zero GPU offload is available in the High-Assurance tier.

๐Ÿ”Œ

FastMCP protocol server

A Python FastMCP layer bridges MCP clients to the .NET server. It supports stdio, SSE and Streamable HTTP. Agents can query codebase topology, dependency graphs and symbol call-graphs.

๐Ÿ›ก๏ธ

Offline signed licensing and MLS

Licenses are verified offline against an issuer public key (RSA), so air-gapped deployments work. High-Assurance adds Bell-LaPadula multi-level security (MLS) clearance enforcement and FIPS-approved HMAC-SHA256 clearance tokens.

๐Ÿงฌ

Graph-grounded verification

The Grounding Verifier checks claims against graph memory, validates citations and flags hallucinated edges. TAPE (Task-Adaptive Prediction & Explanation) plans exploration and reasoning as action-perception DAGs.

๐Ÿ”„

Sharded, hardware-aware memory

The BESS partitioner shards graphs. A hardware-topology model covers NUMA nodes, fabric links and pinned host memory. The largest benchmarked configuration is 1,000,000 nodes / 5,000,000 edges.

SPATIAL SUBGRAPH MAP 51 ARCHITECTURAL TILES

51 FEATURE SUB-GRAPHS

Hypertensor GraphRAG โ€” 10 FREE | 14 PRO | 27 HIGH ASSURANCE

17 tiles generated from the spatial map in this pass

FREE TIER โ€” 10 SUB-GRAPHS

AGENT MEMORY
CODEBASE TOPOLOGY
๐Ÿ›ก๏ธ
GITHUB PROVENANCE
CONTINUOUS TASKS
WORKSPACE TOPOLOGY
WORKSPACE FORMS & LAYOUT
WORKSPACE CLASSES & ER
WORKSPACE AGGREGATE
WORKSPACE SNAPSHOT
CROSS-GRAPH CONSISTENCY

PRO TIER โ€” 14 SUB-GRAPHS

AGENT BLENDER
CODE SEMANTICS
AGENT A
AGENT B
DIRECTIVE SYNC
SKILL
SKILL BLENDER
COMMUNITY DETECTION
HIERARCHICAL CLUSTERING
BELIEF DESIRE INTENTION AGENT BDI
STACK L0 - TOPOLOGY BASELINE
STACK L1 - TARGET MINDMAP
STACK L2 - PROJECT GROUPINGS
STACK L3 - RULES GRAPH
STACK L4 - CHANGES GRAPH
PATTERN COMPOSITION
FEATURE INTERACTION MAP

HIGH ASSURANCE โ€” 27 SUB-GRAPHS

NUMA 0
PCIe Gen5
NUMA 1
HARDWARE TOPOLOGY
LEVEL 0
LEVEL 0 ACCELERATION
MULTI-DOMAIN ONTOLOGY
BESS SHARDING
PROOF CONTRACT
โˆ€x โˆˆ G: Inv(x) โ‡’ โ–กValid
FORMAL INVARIANTS
PIXIE SWARM MESH
DYNAMIC WORLD MODEL
r = t - h KGE LINK PREDICTION
MULTIHOP REASONING
CHECKPOINT GATE [LOCKED & AUDITED] INVARIANT CHECKPOINTS
100% GROUNDED GROUNDING VERIFIER
BESS REASONING
TAPE PLANNING
INTERGRAPH FEDERATION
UNCLASSIFIED SECRET TOP SECRET
SOVEREIGN AIR-GAP
โœ“ SPDX-2.3
โœ“ CYCLONEDX
โœ“ SHA256 ROOT
SBOM PROVENANCE
SECCOMP
CAPABILITY SANDBOX
THREAT SURFACE
AST โ†’ MLIR โ†’ LLVM
COMPILER & MLIR
DRIFT: 0.002%
COGNITIVE BIAS
limtโ†’โˆž V(x) = 0
||x - x*|| < ฮต
FORMULAIC REASONING
12 gCO2/kWh
COST & CARBON
ISO 26262 DO-178C EU AI ACT NIST 800-53
REGULATORY COMPLIANCE
AGENTIC ORCHESTRATION
AGENT BLACKBOARD
AGENT SAFETY & GOVERNANCE
AGENT LEDGER & QUOTAS
โ„น๏ธ

Tier assignment reflects the launch baseline (sales gate 0); features cascade to lower tiers at commercial milestones. Internal bundles are omitted.

HT GraphRAG Commercial & Open-Core Licensing

Coming soon Hypertensor GraphRAG is not yet released. Tiers and terms may change before launch.

Licensing Tiers

Choose the tier that fits your workload: free single-developer use, per-seat Pro, or team-level High-Assurance.

Individual / Workstation

Free

Free single-developer workstation use

$0 / mo

Runtime Bounds & Capacity

  • Validated Bound 25,000 nodes / 100,000 edges
  • SIMD Vectors 128-d SIMD vectors, CPU only
  • 2-Hop Traversal 2-hop traversal โ‰ˆ 1.95 ms
  • Worker Pool 16 workers

Included Subsystems

  • โœ“ Codebase Topology
  • โœ“ Continuous Tasks DAG queue
  • โœ“ GitHub Provenance
  • โœ“ Agent Memory (local single-developer store)
  • โœ“ Developer Workspace scanning
  • โœ“ Graph Consistency linting
  • โœ“ Directive/Playbook symlink sync
Per-Seat Pro

Pro

Commercial developers & scaling engineering teams

$20 / mo per user seat

Runtime Bounds & Capacity

  • Validated Bound 100,000 nodes / 500,000 edges
  • 2-Hop Traversal 2-hop traversal โ‰ˆ 1.47 ms
  • Worker Pool 64 workers (parallel acceleration enabled)

Included Subsystems

  • โœ“ Everything in Free tier
  • โœ“ Roslyn AST blast-radius analysis (CodeSemantics)
  • โœ“ Skill and Agent Blender
  • โœ“ Hierarchical Louvain/Leiden clustering
  • โœ“ Repository Restructuring
  • โœ“ Pattern Composition
  • โœ“ Test Verification
  • โœ“ Feature Interaction Matrix
Team High-Assurance

High-Assurance

Mission-critical, defense, regulated enterprise, and sovereign teams

$1,250 / mo per team

Runtime Bounds & Capacity

  • Validated Bound 1,000,000 nodes / 5,000,000 edges
  • 2-Hop Traversal 2-hop traversal < 12 ms at that scale
  • Worker Pool Worker ceiling of 75,000 (auto-scaled to hardware)

Included Subsystems

  • โœ“ Everything in Pro tier
  • โœ“ Level Zero GPU vector-search acceleration
  • โœ“ Pixie Swarm mesh reasoning
  • โœ“ BESS sharding and reasoning
  • โœ“ Hardware Topology
  • โœ“ Formal Invariants (proof contracts)
  • โœ“ World Model
  • โœ“ TAPE Planning & Grounding Verifier
  • โœ“ Sovereign Air-Gap with MLS enforcement
  • โœ“ Capability Sandbox
  • โœ“ Regulatory Compliance (ISO 26262, DO-178C, EU AI Act, HIPAA)
  • โœ“ Multi-Agent Governance and Decision Ledger
Licensing Procurement

Ready to Deploy Hypertensor GraphRAG?

Developer Pro trial keys are provisioned within 24 hours. High-Assurance Enterprise contracts include cryptographic license generator tooling, custom NUMA build optimization, and air-gapped installation bundles.

Direct Contact: alix@hflabs.dev
Developer Quickstart

Runtime Launch Commands

Run Hypertensor GraphRAG as an embedded .NET daemon, CLI query engine, or Python FastMCP bridge.

1. Dedicated Server Daemon gRPC / In-Memory
dotnet run --project src/HFLabs/Products/HypertensorGraphRAG/Server/Server.csproj -c Release

Spins up the in-memory graph store and binds zero-copy IPC socket interfaces.

2. Headless Topological Query CLI CLI / SIMD
dotnet run --project src/HFLabs/Products/HypertensorGraphRAG/App/App.csproj -c Release -- --headless --query "Director"

Executes 2-hop graph reasoning with SIMD cosine scoring and outputs JSON results.

3. FastMCP SSE Agent Bridge Python / MCP
python -m mcp_graphrag.server --transport sse --port 8000

Exposes HT GraphRAG traversal primitives as Model Context Protocol tools for AI agents.