RatioCore Book a demo
RatioCore
Book a demo

Deployment · Fully cloud

All in the cloud. Still under your control.

Run the Core, the database and the models in your own cloud account. Serve open-weight models on cloud GPUs, call managed model APIs, or route different agents to each.

YOUR ENVIRONMENT
RatioCore Core services
Managed PostgreSQL + pgvector
Cloud GPUs or model APIs
Audit records
Identity & roles
Outbound: only the model APIs, channels and connectors you approve

What your users see

Same experience, wherever it runs.

Your people work with agents in the messaging apps you approve, Microsoft Teams in this example. Where RatioCore runs is your choice. Each channel you enable is an outbound path, so review it like any other connector.

When it fits

Cloud operations. Your account, your rules.

Fully cloud suits teams that run on a hyperscaler already and want managed databases, automated infrastructure and elastic GPU capacity. Agents still act only through RatioCore's identity, policy and approval checks, whichever model answers.

  • Everything in your own cloud account
  • Managed PostgreSQL with pgvector
  • Self-served models, managed APIs or both
  • Model routes per agent

Reference stack

Managed where it helps, governed everywhere.

RatioCore keeps the agent layer separate from model serving. The same three tiers apply on every path; only where each one runs changes.

  1. 01

    Core services on a VM

    The control plane, agent runtimes and gateways run on a Linux virtual machine in a private subnet, behind your load balancer and TLS.

    • Linux with systemd, Python 3.12
    • Private subnet, no public runtime ports
  2. 02

    Managed PostgreSQL

    Each major cloud offers managed PostgreSQL with pgvector. Enable the extension, keep the database private, and use the provider's backups and point-in-time recovery.

    • PostgreSQL 17 with pgvector
    • Provider backups and recovery
  3. 03

    Models: self-served or managed

    Serve open-weight models on GPU instances behind an OpenAI-compatible server, or call managed model APIs that offer OpenAI-compatible chat completions.

    • Per-agent model routes
    • Model routes never carry authority to act
  4. 04

    Cloud identity and secrets

    Keep credentials in your secret manager and reference them from RatioCore; use cloud logging and monitoring around the platform.

    • Secrets held by reference
    • Cloud logs, metrics and alerts

Managed database

PostgreSQL with pgvector on every major cloud.

CloudServicepgvectorNotes
AWSAmazon RDS for PostgreSQL / Aurora PostgreSQLAvailable on PostgreSQL 17Extension version does not upgrade automatically with the engine
Microsoft AzureAzure Database for PostgreSQL flexible serverAvailable on PostgreSQL 13 to 18Add vector to the allowed extensions first
Google CloudCloud SQL for PostgreSQL / AlloyDBAvailableAlloyDB also offers ScaNN indexes
Oracle CloudOCI Database with PostgreSQLAvailable on PostgreSQL 14 to 17Enable through a custom configuration

Sources: Amazon RDS, Aurora, Azure, Cloud SQL, AlloyDB, OCI

Cloud GPUs

Self-serve open models on cloud GPUs.

Examples of GPU instances for open-weight models behind vLLM, SGLang or another OpenAI-compatible server.

CloudNVIDIA examplesAMD examples
AWSP5 (H100, 80 GB), P5e/P5en (H200), P6 (B200, B300)—
Microsoft AzureND H100 v5, ND H200 v5, ND GB200 v6, ND GB300 v6ND MI300X v5 (8x MI300X, 192 GB each)
Google CloudA3 (H100, H200), A4 (B200), A4X (GB200, GB300), G4 (RTX PRO 6000), G2 (L4)—
Oracle CloudH100, H200, B200, B300, GB200, GB300 and L40S shapesBM.GPU.MI300X.8, BM.GPU.MI355X.8

Smaller instances such as single-GPU H100 or L4 suit pilots and embeddings; 8-GPU nodes suit large models and high concurrency. Sources: AWS P5, AWS P6, Azure ND family, Google Cloud GPUs, OCI shapes

Managed model APIs

Or call a model API, with the same governance.

Managed APIs remove GPU operations. RatioCore still decides what each agent may do; the model only proposes.

ServiceOpenAI-compatible accessPublished data commitments
Azure OpenAI in Microsoft Foundryv1 API works with the standard OpenAI clientPrompts and outputs not used to train foundation models without permission; processing stays in your geography unless you choose Global or DataZone deployments
Amazon BedrockOpenAI Chat Completions endpoint per regionModel providers have no access to customer prompts and completions
Google Vertex AIOpenAI-compatible Chat Completions for Gemini and Model Garden vLLM deploymentsCustomer data not used to train models without permission; regional endpoints keep cached data in the chosen location

Each managed API adds an outbound data path. Review the provider's terms, regions and retention settings before routing an agent to it. Sources: Azure OpenAI API, Azure data privacy, Bedrock chat completions, Bedrock data protection, Vertex AI OpenAI, Vertex AI data governance

Choosing a model path

Self-served, managed, or both.

01

Self-served open models

Most control over model versions and data paths. You size and operate the GPU instances.

02

Managed model APIs

No GPUs to run and fast access to frontier models. Data leaves your network under the provider's terms.

03

Mixed routes

Route sensitive agents to self-served models and others to a managed API. Each agent keeps its own route, budget and approvals.

These are reference patterns, not turnkey or certified cloud packages. Infrastructure templates, quotas and service compatibility are confirmed per project, along with security, backup and restore tests.

FAQ

Deployment questions.

Still deciding? Bring your questions to a walkthrough.

Can RatioCore use API models instead of our own GPUs?

Yes. Any approved model that offers an OpenAI-compatible chat endpoint can be registered as a route, including managed services such as Azure OpenAI, Amazon Bedrock and Vertex AI. Model routes never carry authority to execute actions.

Can different agents use different models?

Yes. Each agent maps to its own model route, so a sensitive workflow can use a self-served model while another uses a managed API.

Is fully cloud less secure than on premises?

Not by itself. The same identity, policy and approval checks apply. What changes is where data is processed, so review each outbound path, region and retention setting.

See it on your business

Which function would you reinvent first?

Bring a process your team runs today. In a demo we show how agents could run it, where your people stay in charge, and what a focused pilot could prove.

See it on your workflowBook a demo