Directory DevOps & Platform EngineeringInfrastructure as Codekagent

kagent

Open Source

About kagent

kagent runs agents on Kubernetes clusters alongside existing workloads. The product allows deployment, observation, and governance of AI agents using platform tools already in use. It is open source and described as production grade. It is a CNCF Sandbox project and works with any LLM. Agents are defined as Kubernetes custom resource definitions.

Products

Agent Substrate: A Kubernetes-native runtime for running declarative agents with fast startup and sandboxed execution.
NemoClaw: Provides built-in security and privacy guardrails and can run Nemotron locally or route to cloud models.

Used for

Triaging alerts, correlating traces, drafting runbooks, and opening rollback PRs for incident response.
Filing GitOps pull requests for platform self-service requests like namespaces, databases, or CI pipelines.
Performing retrieval-augmented generation over runbooks, ADRs, and Slack history.
Messaging agents through Telegram, WhatsApp, Slack, or Discord.

Who it is for

Used by platform engineering organizations.

From kagent's own website, read 2026-10-23. How we build listings.

How to evaluate Infrastructure as Code

This is how the CIOPages Research Team evaluates this category. It is not an assessment of kagent. It comes from our Infrastructure as Code (IaC) Platforms buyer guide.

25%

Language & Authoring Model

Declarative DSL (HCL) vs. general-purpose language (TypeScript, Python, Go, C#); readability for reviewers vs. expressive power (loops, conditionals, abstractions); module/component reuse and registry maturity; testing and IDE support; learning curve for the people who will actually write infrastructure

20%

State Management & Drift

Where state is stored, remote-state locking to prevent concurrent-apply corruption, state encryption and secret handling, plan/preview fidelity, drift detection and continuous reconciliation, import of existing resources, and blast-radius controls on apply

20%

Policy-as-Code & Governance

OPA/Rego and Sentinel support, pre-apply guardrails (block non-compliant resources, mandatory tags, region/cost limits), RBAC and SSO/SAML/SCIM, audit logging, approval workflows, and integration with cost-estimation and security scanning in the pipeline

15%

Provider Ecosystem & Portability

Breadth and quality of providers/resource coverage, day-one support for new cloud services, multi-cloud and on-prem reach, third-party SaaS providers, and how locked-in the resulting code is to one vendor or one cloud

10%

Collaboration & Workflow (TACOS)

Run orchestration and queuing, VCS/PR-driven plans, stack dependencies, self-service environments with TTL/ephemeral teardown, drift remediation workflows, and whether you self-host in CI (Atlantis-style) or buy a managed platform

10%

Licensing & Project Health

License (open-source MPL/Apache vs. source-available BUSL vs. proprietary), governance and ownership after recent M&A, release cadence and roadmap, community/foundation backing (CNCF, Linux Foundation), and how easily you could exit or fork

Other Infrastructure as Code Vendors

CIOPages put this listing together from public sources. It’s information, not an endorsement. How we build listings. Work here? Claim this listing or .