Bluebricks
Also known as: Bricks
Context and control layer that lets AI agents operate cloud infrastructure safely, grounding them in a live cloud graph and routing every change through governed plan, approve, and apply orchestration.
Bluebricks is a context and control layer that lets AI agents operate cloud infrastructure safely. It ingests a team's infrastructure as code, configs, and live cloud state from repositories and clouds and turns them into a structured, schema driven cloud graph, complete with dependency maps, history, and allowed actions, so agents act with full context rather than assumptions. Changes flow through governed orchestration: a plan, approve, and apply workflow with cost, operational, and security risk analysis, configurable owner approvals, and fully auditable run history. Reusable, versioned blueprints form a certified catalog, and the platform runs across AWS, GCP, and Azure, multi region, with a self hosted runner and role based access control, single sign on, and vulnerability remediation. Bluebricks exposes an official MCP server, a REST API, a Bricks CLI, and a Claude Code plugin so any MCP compatible agent can drive infrastructure through it. Built on its Atomic Infrastructure approach as an alternative to traditional IaC tooling, it targets DevOps and platform teams enabling agentic cloud operations. The autonomous agent itself is in early access.
Vendor details
Canonical URL
https://bluebricks.co
Category
SRE / DevOps agent
Funding status
Venture backed (Seed stage)
Company status
private
Use cases & customers
Primary use cases
Target customers
Deployment options
Integrations
Integrates Terraform, OpenTofu, Helm, Ansible, GitHub, GitLab, Azure DevOps, Slack, and Backstage, connects AWS, GCP, and Azure clouds, and exposes an official MCP server, REST API, Bricks CLI, and a Claude Code plugin.
Sources & related URLs
Related / legacy domains
Capability coverage
11.5 / 14 capabilities · 82%
| Integrations & Tool Callingintegrates Terraform, OpenTofu, Helm, Ansible, GitHub, GitLab, Azure DevOps, Slack, Backstage, and AWS, GCP, and Azure clouds (bluebricks.co, aws marketplace) | Full |
|---|---|
| Workflow Orchestrationgoverned orchestration runs a plan, approve, and apply workflow with DAG based execution across environments and collections (bluebricks.co) | Full |
| Knowledge Grounding & RAGa context layer ingests IaC, configs, and live cloud state into a structured cloud graph so agents act grounded in dependencies, history, and allowed actions (bluebricks.co) | Full |
| Human Oversight & Guardrailschanges require plan review and configurable owner approval before apply, enforcing permissions and policies (bluebricks.co) | Full |
| Security, Identity & Governancerole based access control, single sign on, a self hosted runner, policy enforcement, and security vulnerability remediation (bluebricks.co) | Full |
| Observability & Auditabilityevery run is fully tracked with plan output, apply logs, inputs, outputs, and state changes for a complete auditable history (bluebricks.co) | Full |
| Memory & State Persistencemaintains persistent infrastructure state, deployment history, and versioned blueprints as durable context; agent session memory is not separately detailed (bluebricks.co) | Partial |
| Deployment & Data Residencysupports multi cloud and multi region operations with a self hosted runner and customer hosted infrastructures (bluebricks.co, aws marketplace) | Full |
| Prebuilt Agents / Templates / Packsreusable, versioned blueprints and packages form a certified blueprint catalog for agents (bluebricks.co) | Full |
| Triggers & Channel Coverageruns are triggered via MCP, CLI, API, webhooks, CI/CD pipelines, and Git pushes and pull requests (bluebricks.co) | Full |
| Model Flexibility & Routingthe platform is model agnostic and can be driven by any MCP compatible agent, including via a Claude Code plugin; it does not itself route models (bluebricks.co) | Partial |
| APIs / SDKs / MCP Extensibilityan official MCP server, REST API, Bricks CLI, and Claude Code plugin extend the platform (bluebricks.co) | Full |
| Testing, Debugging & Optimizationthe plan phase previews all changes with cost, operational, and security risk analysis and posts check runs on pull requests before apply; a formal agent evaluation framework is not detailed (bluebricks.co) | Partial |
| Browser / Computer-useno browser or computer use capability documented (bluebricks.co) | Unable to verify |
Pricing
Enterprise pricing; not publicly listed (direct or AWS Marketplace)
Enterprise engagements available directly and via AWS Marketplace, where recurring usage fees appear on the AWS bill.
Cost watchouts
Purchased via AWS Marketplace, additional AWS infrastructure costs apply; cost scales with managed cloud environments and usage.
Variable cost rationale
Available via AWS Marketplace where additional AWS infrastructure costs apply on top of the subscription, and cost scales with managed environments and cloud footprint. No public list price is available.
Sales call required
Yes — required for paid access
Free / trial
Try now; the AI agent is in early access. No public price.
Lowest paid plan
Not publicly listed.
Key ambiguities
No public list price; available directly and through AWS Marketplace with recurring usage fees on the AWS bill.
Related vendors
- Alertd — Agentic AI SRE and DevOps platform for AWS that analyzes cost,…
- Avesha — Autonomous AI SRE platform whose coordinated agent swarm monitors,…
- Cased — AI infrastructure automation with pre configured agents, agent first…
- Causely — Causal reasoning engine that infers the single root cause of an…
- Chamber — AIOps agent for ML teams that puts GPU infrastructure on autopilot:…
- Cleric — Safety first AI SRE that investigates alerts read only and delivers…