
Alicloud Compute Fc Agentrun
- 273 installs
- 396 repo stars
- Updated July 18, 2026
- cinience/alicloud-skills
alicloud-compute-fc-agentrun is an AI agent skill that manages Alibaba Cloud Function Compute AgentRun resources via OpenAPI for developers who need to deploy, configure, and troubleshoot serverless AI agent runtimes.
About
alicloud-compute-fc-agentrun is a version 1.0.0 AI coding skill in cinience/alicloud-skills that guides developers through Alibaba Cloud Function Compute AgentRun OpenAPI (ROA) workflows for deploying and operating serverless AI agents. The skill bundles three Python scripts—quickstart.py, runtime_flow.py, and cleanup_runtime.py—plus four reference documents covering regional endpoints, a 56-operation API overview, and SDK guidance. A five-step workflow selects a regional agentrun.cn-*.aliyuncs.com endpoint, creates and publishes an agent runtime, provisions runtime endpoints, optionally configures sandbox templates and model services, and wires credentials and memory collections. Developers reach for alicloud-compute-fc-agentrun when they need programmatic control over AgentRun runtimes, sandboxes, model proxies, memory, and credentials instead of console-only setup, or when troubleshooting requires querying live resource status. Generated artifacts are stored under output/aliyun-fc-agentrun/ including API response summaries and py_compile validation output.
- Function Compute serverless runtime
- Agent execution orchestration
- Scalable cloud compute for AI
- Trigger and handler patterns
- AliCloud deployment integration
Alicloud Compute Fc Agentrun by the numbers
- 273 all-time installs (skills.sh)
- Ranked #418 of 1,039 Cloud & Infrastructure skills by installs in the Skillselion catalog
- Data as of Aug 5, 2026 (Skillselion catalog sync)
npx skills add https://github.com/cinience/alicloud-skills --skill alicloud-compute-fc-agentrunAdd your badge
Show developers this skill is listed on Skillselion. Paste this into your README.
| Installs | 273 |
|---|---|
| repo stars | ★ 396 |
| Last updated | July 18, 2026 |
| Repository | cinience/alicloud-skills ↗ |
How do you deploy AI agents on Alibaba Function Compute AgentRun?
Deploy and run AI agents on Alibaba Function Compute with scalable serverless execution, triggers, and runtime configuration.
Who is it for?
Backend developers deploying serverless AI agents on Alibaba Cloud who already have RAM AccessKey credentials and need OpenAPI-driven AgentRun lifecycle control.
Skip if: Developers not using Alibaba Cloud, teams wanting only local agent prototyping without serverless deployment, or projects that only need generic FC 3.0 function deploy via Serverless Devs CLI.
When should I use this skill?
A developer asks to create, publish, query, or tear down Function Compute AgentRun runtimes, endpoints, sandboxes, model services, memory collections, or credentials via OpenAPI.
What you get
Published AgentRun runtime endpoints, sandbox templates, configured model services, and API response logs under output/aliyun-fc-agentrun/
- Published AgentRun runtime endpoints
- API response evidence under output/aliyun-fc-agentrun/
- py_compile validation output for skill scripts
By the numbers
- Version 1.0.0 bundles 3 Python automation scripts
- References document 56 AgentRun OpenAPI operations across 5 resource groups
- Includes 4 reference markdown files for endpoints, API overview, SDK, and sources
Files
Category: service
Function Compute AgentRun (OpenAPI)
Use AgentRun OpenAPI (ROA) to manage runtimes, sandboxes, model services, memory, and credentials.
Prerequisites
- AccessKey via RAM user (least privilege).
- Select the correct regional endpoint (see
references/endpoints.md). If unsure, choose the most reasonable region for the task or ask the user. - Use OpenAPI Explorer or official SDK to avoid manual signing (ROA requires SignatureV1).
Workflow
1) Choose region endpoint (agentrun.cn-<region>.aliyuncs.com). 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.
API Groups
See references/api_overview.md for the full API list and grouping.
Script quickstart
python skills/compute/fc/alicloud-compute-fc-agentrun/scripts/quickstart.pyEnvironment variables:
AGENTRUN_ENDPOINTALICLOUD_ACCESS_KEY_IDALICLOUD_ACCESS_KEY_SECRETOUTPUT_DIR(optional)
Runtime flow script
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)
Cleanup script
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)
SDK Notes
See references/sdk.md for SDK acquisition guidance.
Output Policy
If you store any generated files or responses, write them under: output/compute-fc-agentrun/.
Validation
mkdir -p output/alicloud-compute-fc-agentrun
for f in skills/compute/fc/alicloud-compute-fc-agentrun/scripts/*.py; do
python3 -m py_compile "$f"
done
echo "py_compile_ok" > output/alicloud-compute-fc-agentrun/validate.txtPass criteria: command exits 0 and output/alicloud-compute-fc-agentrun/validate.txt is generated.
Output And Evidence
- Save artifacts, command outputs, and API response summaries under
output/alicloud-compute-fc-agentrun/. - Include key parameters (region/resource id/time range) in evidence files for reproducibility.
References
- API overview and operation list:
references/api_overview.md - Regional endpoints:
references/endpoints.md - SDK guidance:
references/sdk.md
- Source list:
references/sources.md
interface:
display_name: "Alibaba Cloud Compute FC Agentrun"
short_description: "FC AgentRun runtime and endpoint ops"
default_prompt: "Use $alicloud-compute-fc-agentrun to complete this compute/fc task on Alibaba Cloud."
AgentRun OpenAPI 概览
以下操作来自 AgentRun OpenAPI 概览页,按功能分组。
Agent 运行时
- CreateAgentRuntime
- GetAgentRuntime
- UpdateAgentRuntime
- DeleteAgentRuntime
- ListAgentRuntimes
- CreateAgentRuntimeEndpoint
- ListAgentRuntimeEndpoints
- GetAgentRuntimeEndpoint
- UpdateAgentRuntimeEndpoint
- DeleteAgentRuntimeEndpoint
- PublishRuntimeVersion
- ListAgentRuntimeVersions
Sandbox 沙箱
沙箱模板管理:
- CreateTemplate
- GetTemplate
- ListTemplates
- UpdateTemplate
- DeleteTemplate
- StopTemplateMCP
- ActivateTemplateMCP
沙箱实例管理:
- CreateSandbox
- GetSandbox
- ListSandboxes
- StopSandbox
- DeleteSandbox
模型管理
- CreateModelService
- UpdateModelService
- GetModelService
- DeleteModelService
- ListModelServices
- CreateModelProxy
- UpdateModelProxy
- GetModelProxy
- DeleteModelProxy
- ListModelProxies
记忆存储
- GetMemoryCollection
- UpdateMemoryCollection
- DeleteMemoryCollection
- CreateMemoryCollection
- ListMemoryCollections
其他
- GetCredential
- UpdateCredential
- ListCredentials
- CreateCredential
- DeleteCredential
- GetAccessToken
- CreateKnowledgeBase
- UpdateKnowledgeBase
- DeleteKnowledgeBase
- GetKnowledgeBase
- ListKnowledgeBases
- ListModelProviders
- DeleteCustomDomain
- ListCustomDomains
- CreateCustomDomain
- GetCustomDomain
- UpdateCustomDomain
待下线
浏览器沙箱:
- CreateBrowser
- ListBrowsers
- GetBrowser
- DeleteBrowser
代码解释器:
- CreateCodeInterpreter
- ListCodeInterpreters
- GetCodeInterpreter
- DeleteCodeInterpreter
AgentRun OpenAPI 服务地址
来自官方文档的 AgentRun OpenAPI 服务地址(公网与 VPC):
| Endpoint | Region Id |
|---|---|
| agentrun.cn-beijing.aliyuncs.com | cn-beijing |
| agentrun.cn-shanghai.aliyuncs.com | cn-shanghai |
| agentrun.cn-hangzhou.aliyuncs.com | cn-hangzhou |
| agentrun.cn-shenzhen.aliyuncs.com | cn-shenzhen |
| agentrun.ap-southeast-1.aliyuncs.com | ap-southeast-1 |
| agentrun-vpc.cn-beijing.aliyuncs.com | cn-beijing (VPC) |
| agentrun-vpc.cn-shanghai.aliyuncs.com | cn-shanghai (VPC) |
| agentrun-vpc.cn-hangzhou.aliyuncs.com | cn-hangzhou (VPC) |
| agentrun-vpc.cn-shenzhen.aliyuncs.com | cn-shenzhen (VPC) |
| agentrun-vpc.ap-southeast-1.aliyuncs.com | ap-southeast-1 (VPC) |
AgentRun SDK 说明
- 建议使用 OpenAPI Explorer 生成 SDK 或示例代码。
- 通过 Explorer 选择接口后可下载多语言 SDK 调用示例。
官方文档来源(用于后续更新) ============================
- (暂无外部文档链接)
import os
import sys
import json
from pathlib import Path
def get_env(name: str, default: str | None = None) -> str:
value = os.getenv(name, default)
if not value:
print(f"Missing env var: {name}", file=sys.stderr)
sys.exit(1)
return value
def main() -> None:
"""Delete runtime endpoint then delete runtime."""
try:
from alibabacloud_agentrun20250910.client import Client as AgentRunClient
from alibabacloud_agentrun20250910 import models as agentrun_models
from alibabacloud_tea_openapi import models as open_api_models
except Exception:
print(
"Missing AgentRun SDK. Generate or install SDK from OpenAPI Explorer.",
file=sys.stderr,
)
sys.exit(1)
endpoint = get_env("AGENTRUN_ENDPOINT")
access_key_id = get_env("ALICLOUD_ACCESS_KEY_ID")
access_key_secret = get_env("ALICLOUD_ACCESS_KEY_SECRET")
security_token = os.getenv("ALICLOUD_SECURITY_TOKEN") or os.getenv("ALIBABA_CLOUD_SECURITY_TOKEN")
config = open_api_models.Config(
access_key_id=access_key_id,
access_key_secret=access_key_secret,
endpoint=endpoint,
)
if security_token:
config.security_token = security_token
client = AgentRunClient(config)
runtime_id = get_env("AGENTRUN_RUNTIME_ID")
runtime_endpoint_id = get_env("AGENTRUN_RUNTIME_ENDPOINT_ID")
delete_endpoint_req = agentrun_models.DeleteAgentRuntimeEndpointRequest(
runtime_id=runtime_id,
endpoint_id=runtime_endpoint_id,
)
delete_endpoint_resp = client.delete_agent_runtime_endpoint(delete_endpoint_req)
delete_runtime_req = agentrun_models.DeleteAgentRuntimeRequest(runtime_id=runtime_id)
delete_runtime_resp = client.delete_agent_runtime(delete_runtime_req)
output_dir = Path(os.getenv("OUTPUT_DIR", "output")) / "compute-fc-agentrun" / "responses"
output_dir.mkdir(parents=True, exist_ok=True)
out_file = output_dir / "cleanup_runtime.json"
payload = {
"delete_endpoint": delete_endpoint_resp.to_map(),
"delete_runtime": delete_runtime_resp.to_map(),
}
with out_file.open("w", encoding="utf-8") as f:
json.dump(payload, f, ensure_ascii=False, indent=2)
print(f"Saved: {out_file}")
if __name__ == "__main__":
main()
import os
import sys
from pathlib import Path
import json
def get_env(name: str, default: str | None = None) -> str:
value = os.getenv(name, default)
if not value:
print(f"Missing env var: {name}", file=sys.stderr)
sys.exit(1)
return value
def main() -> None:
"""Quickstart for AgentRun OpenAPI (ListAgentRuntimes)."""
try:
from alibabacloud_agentrun20250910.client import Client as AgentRunClient
from alibabacloud_agentrun20250910 import models as agentrun_models
from alibabacloud_tea_openapi import models as open_api_models
except Exception:
print(
"Missing AgentRun SDK. Generate or install SDK from OpenAPI Explorer "
"or install the package if available.",
file=sys.stderr,
)
sys.exit(1)
endpoint = get_env("AGENTRUN_ENDPOINT")
access_key_id = get_env("ALICLOUD_ACCESS_KEY_ID")
access_key_secret = get_env("ALICLOUD_ACCESS_KEY_SECRET")
security_token = os.getenv("ALICLOUD_SECURITY_TOKEN") or os.getenv("ALIBABA_CLOUD_SECURITY_TOKEN")
config = open_api_models.Config(
access_key_id=access_key_id,
access_key_secret=access_key_secret,
endpoint=endpoint,
)
if security_token:
config.security_token = security_token
client = AgentRunClient(config)
request = agentrun_models.ListAgentRuntimesRequest()
response = client.list_agent_runtimes(request)
output_dir = Path(os.getenv("OUTPUT_DIR", "output")) / "compute-fc-agentrun" / "responses"
output_dir.mkdir(parents=True, exist_ok=True)
out_file = output_dir / "list_agent_runtimes.json"
with out_file.open("w", encoding="utf-8") as f:
json.dump(response.to_map(), f, ensure_ascii=False, indent=2)
print(f"Saved: {out_file}")
if __name__ == "__main__":
main()
import os
import sys
import json
from pathlib import Path
def get_env(name: str, default: str | None = None) -> str:
value = os.getenv(name, default)
if not value:
print(f"Missing env var: {name}", file=sys.stderr)
sys.exit(1)
return value
def main() -> None:
"""Create runtime -> publish version -> create endpoint."""
try:
from alibabacloud_agentrun20250910.client import Client as AgentRunClient
from alibabacloud_agentrun20250910 import models as agentrun_models
from alibabacloud_tea_openapi import models as open_api_models
except Exception:
print(
"Missing AgentRun SDK. Generate or install SDK from OpenAPI Explorer.",
file=sys.stderr,
)
sys.exit(1)
endpoint = get_env("AGENTRUN_ENDPOINT")
access_key_id = get_env("ALICLOUD_ACCESS_KEY_ID")
access_key_secret = get_env("ALICLOUD_ACCESS_KEY_SECRET")
security_token = os.getenv("ALICLOUD_SECURITY_TOKEN") or os.getenv("ALIBABA_CLOUD_SECURITY_TOKEN")
config = open_api_models.Config(
access_key_id=access_key_id,
access_key_secret=access_key_secret,
endpoint=endpoint,
)
if security_token:
config.security_token = security_token
client = AgentRunClient(config)
runtime_name = get_env("AGENTRUN_RUNTIME_NAME")
runtime_desc = os.getenv("AGENTRUN_RUNTIME_DESC", "created-by-skill")
runtime_endpoint_name = get_env("AGENTRUN_RUNTIME_ENDPOINT_NAME")
# Create runtime
create_runtime_req = agentrun_models.CreateAgentRuntimeRequest(
name=runtime_name,
description=runtime_desc,
)
create_runtime_resp = client.create_agent_runtime(create_runtime_req)
runtime_id = create_runtime_resp.body.runtime_id
# Publish runtime version
publish_req = agentrun_models.PublishRuntimeVersionRequest(
runtime_id=runtime_id,
description="initial",
)
publish_resp = client.publish_runtime_version(publish_req)
version_id = publish_resp.body.version_id
# Create runtime endpoint
create_endpoint_req = agentrun_models.CreateAgentRuntimeEndpointRequest(
runtime_id=runtime_id,
version_id=version_id,
name=runtime_endpoint_name,
)
create_endpoint_resp = client.create_agent_runtime_endpoint(create_endpoint_req)
output_dir = Path(os.getenv("OUTPUT_DIR", "output")) / "compute-fc-agentrun" / "responses"
output_dir.mkdir(parents=True, exist_ok=True)
out_file = output_dir / "runtime_flow.json"
payload = {
"create_runtime": create_runtime_resp.to_map(),
"publish_version": publish_resp.to_map(),
"create_endpoint": create_endpoint_resp.to_map(),
}
with out_file.open("w", encoding="utf-8") as f:
json.dump(payload, f, ensure_ascii=False, indent=2)
print(f"Saved: {out_file}")
if __name__ == "__main__":
main()
Related skills
How it compares
Choose alicloud-compute-fc-agentrun for AgentRun-specific OpenAPI resource lifecycle (runtimes, sandboxes, model services); use the sibling Serverless Devs skill for CLI-based FC 3.0 function project scaffolding and depl
FAQ
What does alicloud-compute-fc-agentrun manage?
alicloud-compute-fc-agentrun manages Alibaba Cloud Function Compute AgentRun resources via OpenAPI, including agent runtimes, runtime endpoints, sandbox templates, model services, memory collections, and credentials across regional agentrun.cn-*.aliyuncs.com endpoints.
What scripts ship with alicloud-compute-fc-agentrun?
alicloud-compute-fc-agentrun ships three Python scripts: quickstart.py for initial setup, runtime_flow.py to create and publish runtimes with endpoints, and cleanup_runtime.py to delete runtime and endpoint resources using environment variables like AGENTRUN_ENDPOINT.
What credentials does AgentRun OpenAPI require?
alicloud-compute-fc-agentrun requires a RAM user AccessKey with least-privilege permissions, set via ALIBABACLOUD_ACCESS_KEY_ID and ALIBABACLOUD_ACCESS_KEY_SECRET, plus a regional AGENTRUN_ENDPOINT before calling AgentRun ROA APIs.