Show HN: Kubernetes Operator for the OpenAI Managed Agents API

Softcane released an alpha Kubernetes operator, codex-session-operator, that runs OpenAI coding agents against Git repositories inside a cluster, with OpenAI handling the agent loop and model inference while Kubernetes Agent Sandbox executes commands and PostgreSQL stores messages, results and approvals. The operator and CLI install from published release manifests (pinned via a vX.Y.Z tag) without a source checkout, Go or Make, and real tasks require OpenAI Agents API access and incur API charges. The project is alpha, and the gateway uses HTTP by default.

Run OpenAI coding agents against Git repositories in Kubernetes. Give an agent a task, let it work in an isolated workspace, and read the results through an HTTP API or CLI. Continue the conversation to keep working in the same workspace. OpenAI runs the agent loop and model inference. Your cluster runs the commands and stores repository files through Kubernetes Agent Sandbox https://agent-sandbox.sigs.k8s.io/ . The gateway saves messages, results and approvals in PostgreSQL. The project is alpha. Real tasks require OpenAI Agents API access and incur API charges. Release downloads install the operator and CLI without a source checkout, Go or Make. The commands below require a published release; replace vX.Y.Z with a tag from Releases https://github.com/softcane/codex-session-operator/releases . Latest stable release: CRDs, controller and gateway. kubectl apply -f https://github.com/softcane/codex-session-operator/releases/latest/download/install.yaml Or pin a release for production and GitOps. export VERSION=vX.Y.Z kubectl apply -f "https://github.com/softcane/codex-session-operator/releases/download/${VERSION}/install.yaml" Install Agent Sandbox separately at the tested version, then supply PostgreSQL and Secrets using the installation guide https://github.com/softcane/codex-session-operator/blob/main/docs/deployment.md . The gateway uses HTTP by default. For the CLI, download the archive for your machine. For example, on macOS with Apple Silicon: curl -fsSLO https://github.com/softcane/codex-session-operator/releases/latest/download/gateway-client darwin arm64.tar.gz tar -xzf gateway-client darwin arm64.tar.gz gateway-client sudo install -m 0755 gateway-client /usr/local/bin/gateway-client Archives are also available for darwin amd64 , linux amd64 and linux arm64 . To pin the CLI, replace latest/download with download/${VERSION} . Each release includes SHA256SUMS . Follow Run your first repository task https://github.com/softcane/codex-session-operator/blob/main/docs/getting-started.md to download the matching example manifest, configure a workspace and send a task. Source builds are covered in Contributing https://github.com/softcane/codex-session-operator/blob/main/CONTRIBUTING.md . 1. Choose a Profile. It selects the agent, workspace configuration and spending policy. 2. Send a task. The gateway saves your message and returns a conversation ID. 3. Prepare the workspace. The operator creates a Session. Agent Sandbox starts the executor and prepares the repository on persistent storage. 4. Run the agent. OpenAI directs the work; codex exec-server executes commands in your cluster. 5. Read the result. Inspect the saved turn, assistant output and command results. HTTP 202 means your message was accepted; completion comes later. 6. Continue or close. Follow-ups use the same workspace. Closing requests cleanup; the workspace policy controls whether files are deleted or retained. Saved conversation history remains in PostgreSQL. Create a SandboxTemplate and a SandboxWarmPool , then define an Agent , an Environment and a Profile in the same namespace. These examples use sandbox-v1 for the workspace setup and are available together in examples/repository-task.yaml https://github.com/softcane/codex-session-operator/blob/main/examples/repository-task.yaml . After installation https://github.com/softcane/codex-session-operator/blob/main/docs/deployment.md , include sandbox-v1 in the controller's SANDBOX POOLS setting. Use the codex-executor Secret from the Secret setup https://github.com/softcane/codex-session-operator/blob/main/docs/deployment.md 2-create-the-secrets for the restricted environment key. The template below prepares the public google/uuid repository and configures a Go executor for that checkout. Before applying it, replace the example image digest, select your node architecture and set a working StorageClass. The image must contain codex exec-server , /workspace-bootstrap and Go; the application executor Dockerfile https://github.com/softcane/codex-session-operator/blob/main/examples/my-go-project/sandbox/Dockerfile.executor builds that layer. The YAML image anchor lets both containers use the same image reference. SandboxTemplate CR: sandbox-v1 apiVersion: extensions.agents.x-k8s.io/v1beta1 kind: SandboxTemplate metadata: name: sandbox-v1 namespace: codex-session-operator-system labels: agents.softcane.io/managed: "true" spec: envVarsInjectionPolicy: Allowed service: false podTemplate: spec: automountServiceAccountToken: false restartPolicy: Always terminationGracePeriodSeconds: 10 nodeSelector: kubernetes.io/arch: arm64 securityContext: runAsNonRoot: true runAsUser: 1000 runAsGroup: 1000 fsGroup: 1000 seccompProfile: {type: RuntimeDefault} initContainers: - name: repository-prepare image: &executor image registry.example/executor@sha256:aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa imagePullPolicy: IfNotPresent command: /workspace-bootstrap args: - --storage-root - /workspace-storage - --session-uid - $ SESSION UID - --url - https://github.com/google/uuid.git - --commit - 0f11ee6918f41a04c201eceeadf612a377bc7fbc env: - name: TMPDIR value: /tmp securityContext: &restricted allowPrivilegeEscalation: false readOnlyRootFilesystem: true capabilities: {drop: ALL } resources: requests: {cpu: 100m, memory: 128Mi} limits: {cpu: "1", memory: 512Mi} volumeMounts: - {name: workspace, mountPath: /workspace-storage} - {name: tmp, mountPath: /tmp} containers: - name: executor image: executor image imagePullPolicy: IfNotPresent workingDir: /workspace command: codex, exec-server args: --remote, $ CODEX REMOTE URL , --environment-id, $ CODEX ENVIRONMENT ID env: - name: CODEX API KEY valueFrom: secretKeyRef: name: codex-executor key: CODEX API KEY securityContext: restricted resources: requests: {cpu: 250m, memory: 256Mi} limits: {cpu: "2", memory: 2Gi} volumeMounts: - {name: workspace, mountPath: /workspace, subPath: project} - {name: home, mountPath: /home/node} - {name: tmp, mountPath: /tmp} volumes: - name: home emptyDir: {sizeLimit: 128Mi} - name: tmp emptyDir: {sizeLimit: 1Gi} volumeClaimTemplates: - metadata: name: workspace spec: accessModes: ReadWriteOnce storageClassName: standard resources: requests: {storage: 1Gi} The pool selects that template. With replicas: 0 , Agent Sandbox allocates a workspace when a Session requests one. apiVersion: extensions.agents.x-k8s.io/v1beta1 kind: SandboxWarmPool metadata: name: sandbox-v1 namespace: codex-session-operator-system labels: agents.softcane.io/managed: "true" spec: replicas: 0 sandboxTemplateRef: name: sandbox-v1 Managed template and pool specifications are immutable. To change an installed recipe, create a new versioned pair and approve the new pool. The Environment selects sandbox-v1 ; the Profile combines it with the Agent and spending policy. apiVersion: agents.softcane.io/v1alpha1 kind: Agent metadata: name: sandbox-agent namespace: codex-session-operator-system spec: model: gpt-6-luna instructions: Use the prepared repository and report actual commands and results. deletionPolicy: Delete --- apiVersion: agents.softcane.io/v1alpha1 kind: Environment metadata: name: sandbox-environment namespace: codex-session-operator-system spec: mode: SelfHosted deletionPolicy: Delete selfHosted: sandboxPoolRef: name: sandbox-v1 workspace: directory: /workspace deletionPolicy: Delete --- apiVersion: agents.softcane.io/v1alpha1 kind: Profile metadata: name: sandbox namespace: codex-session-operator-system spec: agentRef: name: sandbox-agent environmentRef: name: sandbox-environment spendControl: mode: Unlimited Unlimited permits paid inference without a per-Session dollar cap. To request a cap, use mode: Limited and limitCents: 500 for US$5; this requires provider-project support. Select the sandbox Profile when sending a task https://github.com/softcane/codex-session-operator/blob/main/docs/getting-started.md 4-send-a-task . The gateway creates the Session ; applying these CRs alone starts no task Pod. Follow-ups keep that Session and workspace. With the shown Delete policy, closing removes the workspace, so retrieve any changes first. Optional Vault and VaultCredential CRs supply credentials for connected provider tools. See the resource reference https://github.com/softcane/codex-session-operator/blob/main/docs/resources.md for all six CRs, other execution modes and update rules. - Getting started https://github.com/softcane/codex-session-operator/blob/main/docs/getting-started.md — install locally and run a real task. - Deployment https://github.com/softcane/codex-session-operator/blob/main/docs/deployment.md — install and operate in your own cluster. - Conversations https://github.com/softcane/codex-session-operator/blob/main/docs/conversations.md — CLI, HTTP API, retries and approvals. - Resources https://github.com/softcane/codex-session-operator/blob/main/docs/resources.md — configuration fields and update rules. - Architecture https://github.com/softcane/codex-session-operator/blob/main/docs/architecture.md — components, state and recovery. - Contributing https://github.com/softcane/codex-session-operator/blob/main/CONTRIBUTING.md — builds, tests, simulated demo and releases. Report vulnerabilities through SECURITY.md https://github.com/softcane/codex-session-operator/blob/main/SECURITY.md . Licensed under Apache 2.0 https://github.com/softcane/codex-session-operator/blob/main/LICENSE .