Skip to content
InovagioInovagio

OriginModels

Choose your model, and where it runs.

Open models on your hardware or a frontier model, behind one API. Switch models without rewriting a workflow.

We’ll spend 30 minutes with you on one of your workflows, and you don’t need to share any data.

A task in the Inovagio App for the City of Larkhaven, an example company with example data, asking for approval of the evidence pack for legal. The pack lists the models in use: the chat model, document reader, search model and reranker, each with open weights, its version and where it runs. No outside model is switched on.

Origin › Models: the models listed in an evidence pack for legal review, for chat, reading documents, search and reranking, each with open weights, its version and where it runs, with no outside model switched on. Sample data from Inovagio’s example companies.

Where Origin works

Lists the models you may use and scores them per task (Origin). These are the onboarding steps it works in, from your first decision to live work.

  1. Step 1 · CharterChoose the work and sign the charterRemoves: The project with no finish line.
  2. Step 7 · TestTest it, try to break it, fix itRemoves: “Trust us.”

How the ten steps work

What Origin does

Origin is Inovagio’s model layer: our own inference engine runs open models on your hardware, or routes to a frontier model, behind one API.

  • Our own inference engine

    Built from the ground up, from model format and compression to GPU code, so your models run on hardware you control.

  • Open or frontier

    Run leading open-weight model families on your own hardware, or a frontier model, through the same API.

  • Small task models

    Train compact models on your own approved results for the tasks you run most, scored on your own cases before any task switches.

  • Cost on every call

    Every request carries its cost, so you see what each task spent on models.

The products that make up Origin.

Origin

  • Inference ServerModel servingRun open models, small to large, on hardware you control.
  • ForgeModel trainingTrain task-specific models on your data, with the evidence built in.

What you get with Origin

  • Where models run

    On your hardware, in your cloud, or hosted for you.

  • Changing models

    Switch behind one API; the new model is re-scored on your approved results before it goes live.

  • Serving open models

    Built into the platform.

  • Model cost

    Cost per task, recorded on every call.

What Origin replaces

Origin does the work of these, inside one platform with one identity, one policy and one record:

  • Separate inference servers for chat, embeddings and reranking
  • Hosted model APIs for workloads that must stay private
  • Model routing and gateway layers
  • Standalone embedding and reranking services
  • Tokenizer libraries and services

The controls Origin brings

Every Inovagio product keeps the same five commitments, because regulated work needs all five at once.

  • Security

    Prompts and records stay on hardware you control; each request is bound to its tenant.

  • Governance

    Which model may serve which task is set by policy.

  • On the record

    Every call is recorded with its model, tokens and cost.

  • Monitoring

    Latency, throughput and errors per model in Panoptes.

  • Cost per task

    Small models you own take the routine work; frontier models only when you choose.

Origin in your industry

Every industry runs the same ten steps, so Origin does the same job in each, on that industry’s own work.

For developers: Origin at a glance

Interfaces
Native Inovagio API over REST with server-sent-event streaming, and gRPC
Platforms
macOS (Apple silicon), Linux and Windows servers
Deployment
One inovagio app on a laptop or workstation, a private server, or multi-GPU cloud nodes

Request the developer editionSee the architecture

Origin in the platform.

Where Origin fits

One platform
  1. Agent HarnessAgent harness

    Inovagio CLIInovagio DesktopWeb ChatInovagio SDK

  2. OpsisExperience layer

    FolioMorphe

  3. Virtual EmployeesVirtual Employee layer

    NexusErgon

  4. SynesisKnowledge layer

    PerceptionMNEMOS

  5. Origin (this layer)Model layer

    Inference ServerForge

  6. PhylaxTrust layer

    AuthInovagio SecretsGuard

  7. OperationsOperations

    PanoptesArchon

  8. Platform servicesPlatform services

    ServerAPI ManagementConnect

Where Origin fits

Questions

Origin questions

Can we run everything without sending data to a model vendor?

Yes. Origin runs open models on your own hardware, so prompts and records stay in your environment unless your policy routes a task to a frontier model you chose.

Do we lose quality with open models?

On well-defined tasks, small open models trained on your approved results often match large ones, and you see the score on your own cases before anything switches. Chosen tasks can still go to a frontier model through the same API.

Guides and posts on Origin

See Origin on one of your workflows.

Every project starts with one workflow your people know well, measured against what it costs you today.