alicloud-compute-fc-agentrunManage Function Compute AgentRun resources via OpenAPI (runtime, sandbox, model, memory, credentials). Use for creating runtimes/endpoints, querying status, and troubleshooting AgentRun workflows.
Install via ClawdBot CLI:
clawdbot install cinience/alicloud-compute-fc-agentrunCategory: service
Use AgentRun OpenAPI (ROA) to manage runtimes, sandboxes, model services, memory, and credentials.
references/endpoints.md). If unsure, choose the most reasonable region for the task or ask the user.1) Choose region endpoint (agentrun.cn-).
2) Create runtime → publish version → create runtime endpoint.
3) Create sandbox/template if needed.
4) Configure credentials and model services as required.
5) Query resources for troubleshooting.
See references/api_overview.md for the full API list and grouping.
python skills/compute/fc/alicloud-compute-fc-agentrun/scripts/quickstart.pyEnvironment variables:
AGENTRUN_ENDPOINTALICLOUD_ACCESS_KEY_IDALICLOUD_ACCESS_KEY_SECRETOUTPUT_DIR (optional)AGENTRUN_RUNTIME_NAME="my-runtime" \\
AGENTRUN_RUNTIME_ENDPOINT_NAME="my-runtime-endpoint" \\
python skills/compute/fc/alicloud-compute-fc-agentrun/scripts/runtime_flow.pyEnvironment variables:
AGENTRUN_ENDPOINTALICLOUD_ACCESS_KEY_IDALICLOUD_ACCESS_KEY_SECRETAGENTRUN_RUNTIME_NAMEAGENTRUN_RUNTIME_ENDPOINT_NAMEAGENTRUN_RUNTIME_DESC (optional)OUTPUT_DIR (optional)AGENTRUN_RUNTIME_ID="runtime-id" \\
AGENTRUN_RUNTIME_ENDPOINT_ID="endpoint-id" \\
python skills/compute/fc/alicloud-compute-fc-agentrun/scripts/cleanup_runtime.pyEnvironment variables:
AGENTRUN_ENDPOINTALICLOUD_ACCESS_KEY_IDALICLOUD_ACCESS_KEY_SECRETAGENTRUN_RUNTIME_IDAGENTRUN_RUNTIME_ENDPOINT_IDOUTPUT_DIR (optional)See references/sdk.md for SDK acquisition guidance.
If you store any generated files or responses, write them under:
output/compute-fc-agentrun/.
references/api_overview.mdreferences/endpoints.mdreferences/sdk.mdreferences/sources.mdGenerated Mar 1, 2026
Deploy machine learning models as serverless endpoints for real-time inference. Create runtime environments with specific compute resources, publish model versions, and expose endpoints for applications to consume predictions without managing infrastructure.
Build scalable data transformation workflows using Function Compute AgentRun. Configure sandboxes for data preprocessing, run ETL jobs with custom runtimes, and manage credentials for secure access to data sources and storage systems.
Develop and deploy microservices as serverless functions with managed runtimes. Create isolated runtime endpoints for different services, configure memory and compute resources per service, and implement versioning for gradual deployments.
Process real-time IoT device data streams using Function Compute AgentRun. Create lightweight runtimes to handle device telemetry, implement data validation and transformation, and expose endpoints for device management and monitoring dashboards.
Deploy AI-powered content generation models for text, image, or video creation. Configure specialized runtimes with GPU support for model inference, manage multiple model versions for A/B testing, and scale endpoints based on demand fluctuations.
Offer AI/ML capabilities as a service using Function Compute AgentRun. Build multi-tenant platforms where customers can deploy their models, manage runtimes, and pay based on compute usage and endpoint invocations.
Provide implementation and optimization services for organizations adopting Function Compute AgentRun. Help clients design serverless architectures, migrate existing workloads, and optimize runtime configurations for cost and performance.
Operate and maintain Function Compute AgentRun environments for clients. Handle runtime deployments, endpoint management, monitoring, troubleshooting, and security compliance as a fully managed service offering.
💬 Integration Tip
Start with the quickstart script to validate credentials and endpoint connectivity before implementing complex workflows. Use environment variables consistently across scripts to maintain configuration.
Automatically update Clawdbot and all installed skills once daily. Runs via cron, checks for updates, applies them, and messages the user with a summary of what changed.
Full desktop computer use for headless Linux servers. Xvfb + XFCE virtual desktop with xdotool automation. 17 actions (click, type, scroll, screenshot, drag,...
Essential Docker commands and workflows for container management, image operations, and debugging.
Tool discovery and shell one-liner reference for sysadmin, DevOps, and security tasks. AUTO-CONSULT this skill when the user is: troubleshooting network issues, debugging processes, analyzing logs, working with SSL/TLS, managing DNS, testing HTTP endpoints, auditing security, working with containers, writing shell scripts, or asks 'what tool should I use for X'. Source: github.com/trimstray/the-book-of-secret-knowledge
Deploy applications and manage projects with complete CLI reference. Commands for deployments, projects, domains, environment variables, and live documentation access.
Monitor topics of interest and proactively alert when important developments occur. Use when user wants automated monitoring of specific subjects (e.g., product releases, price changes, news topics, technology updates). Supports scheduled web searches, AI-powered importance scoring, smart alerts vs weekly digests, and memory-aware contextual summaries.