Skip to main content
Platform

Private AI Platform for Sensitive Workloads

Run Kubernetes-native inference in private or hybrid environments with explicit runtime control, auditable context access, and operational surfaces designed for production teams.

Portfolio lanes

How the portfolio fits together

FlexInfer anchors the runtime layer with model lifecycle, serverless activation, routing, and GPU-aware operations, while Loom Core and fi-fhir extend context and integration boundaries around it.

Runtime and inference control plane

FlexInfer

Kubernetes-native model lifecycle, OpenAI-compatible routing, and GPU-aware runtime controls for predictable private or hybrid inference.

Deployment boundary
Model runtime placement, scheduling, caching, and activation stay inside your cluster boundary.
Integration boundary
Applications hit standard inference APIs while runtime operations stay inside your network and observability stack.
Context and orchestration control plane

Loom Core

Registry-driven MCP config generation, daemon routing, and enterprise context controls roadmap (gateway, RBAC, executor).

Deployment boundary
Centralizes MCP server lifecycle and policy boundaries for internal tools and agent access.
Integration boundary
Defines how agents reach internal systems with auditable routing and least-privilege intent.
Sensitive-data integration plane

fi-fhir

Healthcare-focused ingestion and transformation workflows (HL7v2 to FHIR) with profile-driven, testable data handling.

Deployment boundary
Data transformation pipeline runs in your controlled environment and deployment topology.
Integration boundary
Profile-driven mapping and validation isolate source variability while preserving operational traceability.
Operational surfaces

Operator mission-control surfaces

Loom Core governs context and policy boundaries. MentatLab adds the operator-facing orchestration UX for DAG design and run visibility.

Agent and DAG orchestration UI

MentatLab

Mission Control interface for building, monitoring, and executing DAG-based agent workflows in private environments.

Loom Core governs context routing and policy boundaries; MentatLab provides the operator UX for DAG design and run visibility.

Deployment boundary
UI, gateway, and orchestrator services run inside your Kubernetes footprint alongside internal agent workloads.
Integration boundary
Connects orchestration workflows to internal MCP-governed tools and runtime services without moving data to shared SaaS control planes.
Mobile fleet monitoring (iOS/iPad)

Loom Companion

SwiftUI app for fleet monitoring, session management, real-time alerts, and lightweight operator control from iPhone and iPad.

Loom Core exposes a frozen v1 mobile API (18 endpoints) with OAuth PKCE auth; Companion consumes it for on-the-go visibility into agents, sessions, and infrastructure.

Deployment boundary
Connects via LAN (trusted network) or Gateway (zero-trust with mandatory TLS) to your Loom Core HUD instance.
Integration boundary
Read-only fleet access with scope-gated mutations. Mobile tokens are isolated from internal agent routes with per-actor rate limiting and structured audit logging.
Enterprise capability map

Current foundations and in-progress controls

4 controls are available today. 2 controls are currently in progress.

MCP Gateway
Available
Centralized MCP routing via loom proxy with streamable HTTP transport, bearer/OIDC/mTLS auth, and hub failover.
Single context ingress with controlled routing, auditing, and automatic local fallback.
Explore →
Role-based Access Control (RBAC)
Available
Role-aware permissions for MCP tool access with audit trail, cost tracking, and OAuth 2.1.
Enforces least-privilege context access with auditable decision logs across teams and environments.
Explore →
Sandbox Executor (Docker + K8s)
Available
mcp-devbox sandbox runtime with Docker and Kubernetes backends for isolated agent execution.
Runs builds, tests, and automation in controlled containers with consistent isolation and audit trails.
Explore →
Operational Foundations
Available
OTel tracing across all 59 MCP servers, JSON log correlation, observability stack, and deployment controls.
Full production observability with distributed tracing, structured logging, and repeatable deployment workflows.
Explore →
HUD Cost Dashboard
In progress
Cost monitoring integration: loom/cost-stats RPC, CostMonitor polling, SSE events, and OverviewPanel KPI tile.
Real-time visibility into agent and tool usage costs directly in the HUD command center.
Explore →
HUD RBAC + Audit Visibility
In progress
RBAC config RPC, denied-calls ring buffer, ServersPanel RBAC sub-tab, and OverviewPanel badge.
Surfaces access control decisions and denied actions in the HUD for operational awareness.
Explore →
Industry proof

Healthcare-aligned implementation stories

A healthcare-first proof path demonstrates how this portfolio handles sensitive data transformations and operational reliability in private environments.

Healthcare

fi-fhir healthcare integration workflows

Profile-driven parsing and transformation for HL7v2 and FHIR in production-oriented workflows.

Healthcare

Operationalizing healthcare API integrations

Reliability patterns for long-lived, partner-facing integration surfaces under operational pressure.

Next step

Move from positioning to execution

Start with a readiness audit to baseline risk, cost, and deployment constraints. Then scope architecture work for your environment.