Bluebricks
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 an AI agent operate cloud infrastructure. It ingests a team's infrastructure as code, configs and live cloud state into a cloud graph of every resource, relationship and dependency across AWS, Google Cloud and Azure, whether managed by code or not, and its agent reasons over that graph to discover resources, detect drift, codify unmanaged infrastructure, recommend right sizing and remediate security findings from Wiz, Prisma Cloud and CrowdStrike.
Changes run through governed orchestration: plans and applies follow each blueprint's dependency graph, with packages executed in parallel and outputs passed between them. The agent never auto-approves; it presents the plan and waits for confirmation, collection policies add owner approvals, cost limits and blueprint allowlists, and the agent inherits the user's role permissions. Every approval, rejection and agent action is recorded, and each run keeps plan output, apply logs, inputs, outputs and state changes. Alerts from monitoring tools (Coralogix today) open shared integration threads the agent investigates on its own, and GitOps environments plan from git pushes.
Bluebricks runs as SaaS or with a self hosted runner in the customer's own cloud account, supports SSO and role based access, and exposes a REST API, the Bricks CLI and an MCP server. Pricing is not published.
Vendor details
Canonical URL
https://bluebricks.co
Category
SRE / DevOps agent
Funding status
Venture backed (Seed stage)
Company status
independent
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
Agentic Index coverage score
10.5 / 14 capabilities · 75%
| Integrations & Tool Calling | Full |
|---|---|
|
The agent's write tools open pull requests, run deployments and handle approvals across AWS, Google Cloud and Azure from IaC in the customer's repositories, and remediation integrates with Wiz, Prisma Cloud and CrowdStrike findings. Sourcebluebricks.co/docs/agent/agents-overviewread 2026-09-29 |
|
| Workflow Orchestration | Full |
|
Runs plan and apply across a blueprint's directed acyclic graph, executing packages in parallel by dependency and passing each package's outputs to the next, across collections and environments with promotion between them. Sourcebluebricks.co/docs/orchestration/runsread 2026-09-29 |
|
| Knowledge Grounding & RAG | Full |
|
A context layer and cloud graph cover 'every resource, relationship, and dependency in your connected cloud accounts, whether managed by code or not', built from IaC, configs and live cloud state, which the agent reasons over. Sourcebluebricks.co/docs/agent/agents-overviewread 2026-09-29 |
|
| Human Oversight & Guardrails | Full |
|
'The agent never auto-approves': it presents each plan and waits for confirmation before applying, collection policies add owner approvals, cost limits and blueprint allowlists, and the agent inherits the user's permissions and cannot bypass role restrictions. Sourcebluebricks.co/docs/agent/governanceread 2026-09-29 |
|
| Security, Identity & Governance | Full |
|
A deep control surface: role based access with per role permissions, SSO setup, collection policies and owner approvals, and audit logs of every agent action. No attestation is published; the homepage names none and the trust center at trust.bluebricks.co is empty. SourceBluebricks docs, Agent Governance and llms.txt index (Roles and Permissions, SSO); bluebricks.co/docs/agent/governanceread 2026-09-29 |
|
| Observability & Auditability | Full |
|
'Every approval, rejection, and action taken through the agent is recorded', task history keeps the plans, decisions and outcomes, and each run records plan output, apply logs, inputs, outputs and state changes. Sourcebluebricks.co/docs/orchestration/runsread 2026-09-29 |
|
| Memory & State Persistence | Partial |
|
Every message and action is kept in task history and a task can be resumed where it left off, which is conversation state, but no memory the agent carries across tasks is documented; infrastructure state and deployment history are the application's record. Sourcebluebricks.co/docs/agent/agents-overviewread 2026-09-29 |
|
| Deployment & Data Residency | Full |
|
SaaS or a self hosted runner: the Bluebricks Deployments Controller runs as a Kubernetes operator 'to run IaC tasks in your own cloud account', with an Orchestrator in a Box option and self hosted cloud guidance, across AWS, Google Cloud and Azure. SourceBluebricks homepage and docs llms.txt index; bluebricks.coread 2026-09-29 |
|
| Prebuilt Agents / Templates / Packs | Partial |
|
Blueprints are reusable templates customers create from their own code, and the agent's prebuilt workflows (discovery, drift detection, codification, right sizing) are capabilities of one agent; no vendor shipped blueprint catalog is published. SourceBluebricks docs, Agent Overview and llms.txt index; bluebricks.co/docs/agent/agents-overviewread 2026-09-29 |
|
| Triggers & Channel Coverage | Full |
|
An alert sent by a monitoring tool (Coralogix today) opens an integration thread in which the agent starts investigating on its own; GitOps environments trigger plans from git pushes, and drift detection runs automatically. SourceBluebricks docs, Integration threads and llms.txt index; bluebricks.co/docs/agent/integration-threadsread 2026-09-29 |
|
| Model Flexibility & Routing | Not documented |
|
The models behind the Bluebricks agent are not disclosed and no customer choice is documented. The agent can be driven from Claude Code or any MCP client, but that does not let the customer pick its model. Sourcebluebricks.co/docs/agent/agents-overviewread 2026-09-29 |
|
| APIs / SDKs / MCP Extensibility | Full |
|
A documented REST API at api.bluebricks.co/api/v1 with long lived API tokens or JWT bearer authentication, managing collections, blueprints, environments and their logs and cloud account connections, plus the Bricks CLI with a full command reference and a Bluebricks MCP server to provision, plan and deploy. SourceBluebricks docs, API overview and llms.txt index; bluebricks.co/docs/api/readmeread 2026-09-29 |
|
| Testing, Debugging & Optimization | Partial |
|
The plan phase reports resources to create, update and destroy before apply, and policies check cost and allowlists; that validates an infrastructure change rather than evaluating the agent's behavior, and no agent evaluation harness is documented. Sourcebluebricks.co/docs/orchestration/runsread 2026-09-29 |
|
| Browser / Computer-use | Not documented |
|
Acts through IaC tools, cloud APIs, a CLI, an API and an MCP server; no browser, desktop or computer control is documented. Sourcebluebricks.co/docs/agent/agents-overviewread 2026-09-29 |
|
The Agentic Index coverage score grades every vendor Full, Partial or Not documented against the same 14 buyer facing capabilities, from public evidence only. Each capability links to how all vendors in the index score on it. How this evidence is graded
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
Not published; no public price or trial terms on the site
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 — AI agents for AWS operations that run read only in the customer's…
- Anyshift — AI SRE built on a versioned knowledge graph of infrastructure, apps…
- Avesha — Obliq, Avesha's autonomous AI SRE for Kubernetes and agentic…
- Better Stack — Better Stack offers incident management with built in on call,…
- Cased — AI workflows for infrastructure and platform engineers: default and…
- Causely — Causal reasoning platform that infers root cause and blast radius…
Alternatives to Bluebricks
The closest documented capability profiles to Bluebricks among SRE and DevOps agents tracked by Agentic Index, ordered by similarity on the same 14 point evidence the rankings use. No vendor pays for placement.
- PagerDuty11.0 / 14Fuller documented coverage on Prebuilt Agents, Templates & Packs
- Better Stack9.5 / 14A lighter documented profile than Bluebricks
- Chamber9.5 / 14A lighter documented profile than Bluebricks
- Doctor Droid11.5 / 14Adds documented Model Flexibility & Routing
- Metoro9.5 / 14A lighter documented profile than Bluebricks
- Anyshift8.5 / 14A lighter documented profile than BluebricksBluebricks vs Anyshift →
Similarity is computed from each vendor's Agentic Index coverage score evidence, axis by axis, not from the totals. How this evidence is graded