// Manage Brev instances safely from the Brev CLI. Use when a workflow needs to list, create, access, copy to, execute on, port-forward, stop, or delete Brev instances for Content Agents dependency endpoints.
| name | brev-cli |
| description | Manage Brev instances safely from the Brev CLI. Use when a workflow needs to list, create, access, copy to, execute on, port-forward, stop, or delete Brev instances for Content Agents dependency endpoints. |
| version | 0.1.0 |
| author | NVIDIA Content Agents |
| tags | ["content-agents","brev","deployment"] |
| tools | ["Shell","Filesystem","brev","ssh"] |
| compatibility | Requires an installed and authenticated Brev CLI, SSH access to created instances, and explicit user approval before commands that start spend or delete resources. |
Use this skill for generic Brev instance lifecycle operations that support Content Agents deployment skills.
deploy-ovrtx-docker, deploy-qwen-vlm-brev,
deploy-image-gen-brev, or deploy-embeddings-brev.brev ls --json, brev search --json, or
a service-specific skill's validated instance type.brev exec, brev copy, or direct
ssh.brev search --json only when a service-specific skill already gives an
exact validated instance type:brev --version
brev healthcheck
brev ls --json
brev search --json
<gb> is the Brev CLI disk-size value in GB:brev create <name> --dry-run --type <instance-type> --min-disk <gb>
brev create <name> --type <instance-type> --min-disk <gb> --timeout 1200
brev exec <name> "uname -a && nvidia-smi || true"
.env files and secrets out of bulk copies unless the user explicitly asks
for a credential-copy step:brev copy <local-path> <name>:<remote-path>
brev exec or a named SSH host. Prefer
service-specific deploy skills for container startup commands:brev exec <name> "cd <remote-path> && <command>"
brev port-forward <name> -p <local-port>:<remote-port>
brev stop when delete is delayed,
delete is not supported, or the user asks to preserve the workspace without
spend:brev stop <name>
Use brev delete only when the user wants the instance removed:
brev delete <name>
After either cleanup action, confirm state:
brev ls --json
| Goal | Command |
|---|---|
| Check auth and CLI health | brev healthcheck |
| List instances | brev ls --json |
| Find available hardware | brev search --json |
| Preview spend | brev create <name> --dry-run --type <type> --min-disk <gb> |
| Create instance | brev create <name> --type <type> --min-disk <gb> --timeout 1200 |
| Run remote command | brev exec <name> "<command>" |
| Copy files | brev copy <local-path> <name>:<remote-path> |
| Forward port | brev port-forward <name> -p <local-port>:<remote-port> |
| Stop spend when supported | brev stop <name> |
| Delete instance | brev delete <name> |
Report the instance name, instance type, current status, commands run, endpoint
or port-forward URL, any port-forward PID/session to stop, and the brev stop
or brev delete cleanup command. Mention any command that requires user
approval before running it.
brev healthcheck fails, ask the user to refresh Brev authentication and
rerun the command.brev ls --json and retry a
lightweight brev exec before starting containers.brev port-forward only binds localhost but Docker containers need the
endpoint, use a carefully scoped SSH forward bound to the host interface and
restrict access with host firewall rules.brev ls --json until the instance disappears.Deploy the full Content Agents package with a provider-neutral, endpoint-driven, multi-instance strategy. Use when the user asks to deploy all content agents, deploy material/physics/texture together, configure shared OVRTX rendering, choose VLM/LLM/image-gen/embedding endpoints, test the full package, or use Brev as an optional self-hosted dependency provider.
Deploy or smoke-test a Brev-hosted NVIDIA embedding NIM endpoint for Content Agents. Use when the user asks to deploy embeddings on Brev, host the llama-nemotron-embed-vl model, enable Material Agent prim clustering embeddings, test embedding sidecars, or create a Brev embedding endpoint for the collection deployment.
Deploy or smoke-test a Brev-hosted FLUX image-generation NIM endpoint for Content Agents. Use when the user asks to deploy image generation on Brev, host FLUX.2 Klein for Texture Agent, enable image-gen sidecars, test image-gen endpoints, or create a Brev image-gen endpoint for the collection deployment.
Deploy or smoke-test the Material Agent with Brev-hosted dependency endpoints. Use when the user asks to test material agent on Brev, deploy material agent with Brev, use RTX/L40S for rendering and A100/H100-grade GPU for VLM, run a Brev hybrid material-agent test, or recreate the Brev material-agent deployment. This workflow keeps the main pipeline local and uses Brev port-forwards to reach OVRTX and Qwen-family VLM endpoints.
Deploy the material-agent-service locally using Docker Compose with OVRTX rendering. Use when user wants to run material agent with docker, docker compose, set up local deployment, run the service locally with GPU rendering, start material agent containers, or configure VLM provider for docker deployment. Trigger phrases include "docker compose", "docker deploy", "run locally with docker", "start material agent docker", "docker up", "local deployment", "compose up".
Deploy just the OVRTX rendering API standalone via Docker Compose so one or more agent CLIs / services can point at it as a shared rendering endpoint. Use when user wants to run OVRTX standalone, deploy a shared rendering service, separate the rendering endpoint from an agent service, expose OVRTX to multiple callers, or set RENDER_ENDPOINT to a dedicated render host. Trigger phrases include "deploy ovrtx", "run ovrtx standalone", "shared rendering service", "ovrtx rendering docker", "render endpoint deploy", "ovrtx docker compose", "standalone rendering".