Skip to main content
Platform

Private AI, operated like real infrastructure

FlexInfer is the runtime anchor for private inference and model customization. Loom coordinates MCP, context, and agent fleets around that runtime. MentatLab turns direct model/API calls into DAG workflows. fi-fhir handles healthcare ingestion, transformation, and delivery.

Open product lanesStart with readiness auditRead docs

What is running now

Reading

Read when this page rendered. Each tile names its source.

  • FactoryReading the source…
  • InferenceReading the source…
  • ClusterReading the source…
Operating model

Start with private inference

Four layers, in the order they are built, and the question each one has to settle.

  1. 01FlexInfer

    Operate private model runtimes first

    Can this model run, scale, route, and roll back inside our cluster boundary?

  2. 02Loom

    Govern the agent and tool boundary

    Which agents can reach which tools, with what context, and what audit trail?

  3. 03MentatLab

    Compose repeatable DAG workflows

    Can operators design, validate, run, and observe the workflow as a graph?

  4. 04fi-fhir

    Apply it to sensitive integration work

    Can legacy clinical data become validated, explainable, routable events?

Product boundaries

Each product owns a clear boundary

What each product keeps inside your environment, and where requests cross to another product.

  1. FlexInfer

    Private inference and model customization

    Deployment boundary
    Model runtime placement, scheduling, caching, activation, and adapter workflows stay inside your cluster boundary.
    Integration boundary
    Applications hit standard inference APIs while runtime operations stay inside your network and observability stack.
    Crosses to
    • Loom · Runtime and context boundary
    • fi-fhir · Inference and sensitive-data integration

  2. Loom

    MCP, context, and agent fleet coordination

    Deployment boundary
    Centralizes MCP server lifecycle, daemon routing, context memory, and policy boundaries for internal tools and agent access.
    Integration boundary
    Defines how agents reach internal systems with bounded context, auditable routing, and least-privilege intent.
    Crosses to
    • FlexInfer · Runtime and context boundary
    • MentatLab · Control plane and operator UX

  3. MentatLab

    DAG agent orchestration

    Deployment boundary
    UI, gateway, and orchestrator services run inside your Kubernetes footprint alongside private model and integration services.
    Integration boundary
    Workflows call direct model/API nodes and MCP-governed tools without depending on frontier coding harness semantics.
    Crosses to
    • Loom · Control plane and operator UX

  4. fi-fhir

    Healthcare ingestion and transformation

    Deployment boundary
    Data transformation pipeline runs in your controlled environment and deployment topology.
    Integration boundary
    Source Profiles, semantic events, validation, routing, and terminology mapping isolate source variability while preserving operational traceability.
    Crosses to
    • FlexInfer · Inference and sensitive-data integration
Operator tools

Workflow and fleet monitoring

Where operators watch the work: MentatLab for workflow design and runs, Loom Companion for the agent fleet.

  • Agent and DAG orchestration UI

    MentatLab

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

    Loom Core governs context routing and policy boundaries. MentatLab provides the DAG design and run-visibility layer over direct API model calls, internal services, and private FlexInfer endpoints.

    Deployment and integration boundaries
    Deployment boundary
    UI, gateway, and orchestrator services run inside your Kubernetes footprint alongside internal agent workloads.
    Integration boundary
    Connects orchestration workflows to direct model/API nodes, 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 and integration boundaries
    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 GatewayAvailable
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.
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.
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.
Operational FoundationsAvailable
OpenTelemetry tracing across the MCP server fleet, JSON log correlation, observability stack, and deployment controls.
Distributed tracing, structured logging, and deployment procedures for investigating runtime behavior.
HUD Cost DashboardIn progress
Cost monitoring integration: loom/cost-stats RPC, CostMonitor polling, SSE events, and OverviewPanel KPI tile.
Estimated agent and tool usage costs in the HUD, refreshed from runtime telemetry.
HUD RBAC + Audit VisibilityIn 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.
Industry proof

Healthcare-aligned implementation stories

The healthcare case study shows the parsing, mapping, and delivery controls implemented in fi-fhir, along with its remaining release work.

Platform | FlexInfer