Start locally
Run the command from the parent directory of your agent applications:--open opens http://127.0.0.1:8000 after the service is ready. Without it, Studio starts the service without opening a browser.
Volcengine credentials are used for models, cloud-resource queries, and AgentKit deployment from the workbench. In production, provide them through environment variables or a secret manager rather than project files.
Customize branding
Use--site-title to set a system name of up to six characters and --site-logo to provide a local image or HTTP(S) image URL. The logo appears in the sidebar, login page, and browser favicon, while the system name becomes the browser title. Omitting --site-title uses the default VeADK Studio name.
VEADK_SITE_TITLE and VEADK_SITE_LOGO. The deployment command accepts the same options and bundles remote images during deployment.
Create an agent
- On Add Agent, select Custom. Intelligent, template, and workflow entries are not available.
- Configure the model, instruction, tools, memory, and knowledge base, and add skills from Skill Hub, a local upload, or an AgentKit SkillSpace. Multi-agent projects can also use sequential, parallel, loop, or A2A nodes.
- Review the generated files and run them in a restricted temporary process; download a ZIP if you need to work offline.
- Select AgentKit deployment and monitor the build-image, deploy, and publish stages.
--generated-agent-test-run-ttl. Generated code can call external services or access data available to Studio, so test only trusted projects and give Studio restricted credentials.
Use smart search
Smart search provides Session, Web, Knowledge, and Memory sources. Session searches the current agent’s message history; Web calls the agent’s mountedweb_search tool; Knowledge and Memory perform semantic retrieval through the mounted knowledge base and long-term memory backend. Studio enables only sources available to the agent and labels results with their index or source name and backend type.
Deployment network modes
The deploy page lets you choose a network mode for the AgentKit runtime, which determines how it is exposed to the public network:
When you select VPC or Public + VPC, you must provide the VPC ID and subnet ID.
A private VPC runtime does not return a public data-plane address after deployment. Studio reaches it through the server-side runtime proxy, and the data-plane API key stays server-side and is never delivered to the browser. This is the same server-side runtime proxy described in “Select a cloud Runtime”.
Manage agents
Manage Agents lists AgentKit runtimes deployed through this workbench by the signed-in user. The list defaults to the Beijing region and can be switched to Shanghai. It is filtered by the user identity recorded during deployment and exposes:- Runtime name, ID, status, region, and creation time;
- Model, description, project, version, resources, and update time;
- Bound Memory, Tool, Knowledge, and MCP Toolset identifiers;
- Runtime environment variables and primary-agent information.
- Agent topology, remote traces, and global deployment-task state.
Select a cloud Runtime
In cloud mode, the agent selector in the chat sidebar lists AgentKit Runtimes that the signed-in user deployed through this workbench, paginated by region. Each Runtime exposes two independent actions:- Connect: makes the Runtime the agent for the current conversation and closes the selector after switching.
- Info: opens a tabbed preview panel that shows the Runtime’s capabilities without connecting to it or persisting the selection.
- Agent info: reads the Runtime’s name, model, description, sub-agents, tools, skills, available search sources, and mounted components with their backend types. It does not return system prompts, credentials, or environment-variable values.
- Runtime details: shows the Runtime model, description, status, region, resources, version, and environment variables available to Studio.
The Runtime details tab can display runtime environment-variable values. Restrict Studio to authorized users and prefer the platform’s secret-management features.
Use temporary sessions and Skill creation
The new-conversation view supports ordinary agent chat, temporary sessions, and Skill creation. A temporary session runs a multi-turn conversation in an independent AgentKit CodeEnv Session; exiting deletes the cloud Session without adding it to ordinary session history. Skill creation generates two candidates in parallel, which can be compared, previewed, downloaded as ZIP files, or added to AgentKit. Skill creation is available only todeveloper and admin users. Each candidate uses a separate Session, and Studio checks its SKILL.md, file count, size, and paths before packaging. Candidate Sessions expire after 30 minutes and are deleted immediately when the user starts over or leaves the task.
Local configuration
Prepare two AgentKit CodeEnv Tools in theReady state before using these modes locally:
veadk studio options
Deploy to VeFaaS
veadk studio deploy deploys Studio as a VeFaaS application protected by VeIdentity login. It creates or reuses a Serverless API Gateway. Unless you pass an IAM role, it also creates or reuses VeADKFrontendServiceRole and VeADKFrontendPolicy. After deployment, the command registers the public callback with the user-pool client and updates the application configuration.
Prepare the user-pool UID, user-pool client UID, and suitable Volcengine credentials, then run:
--region selects the Studio deployment region, defaults to cn-beijing, and also supports cn-shanghai; VeFaaS, API Gateway, and other resources are created in that region. Deployment also locates the VeIdentity user pool and client across the deployment region and the Beijing and Shanghai regions: it queries the deployment region first, then searches the other region on a miss, emitting a warning and continuing when matched cross-region. --project selects the VeFaaS function project and defaults to default.
The deployer’s long-lived access and secret keys are not written to the VeFaaS application environment. Deployed Studio uses temporary credentials from its bound IAM role.
When --sandbox-chat-codex-tool-id and --sandbox-skill-creator-tool-id are omitted, deployment creates two independent AgentKit CodeEnv Tools for temporary sessions and Skill creation. Existing suitable Tools can be reused by passing their IDs.
Deployment options
Update a deployed Studio
veadk studio update rebuilds Studio from a local VeADK source checkout, updates the existing VeFaaS Function code, and releases the original Application. Install Node.js and npm, then run the command from the VeADK source directory:
--region and --project are omitted, the command searches Beijing, Shanghai, and all visible projects. If multiple Applications have the same name, add a region or project to narrow the scope. The update preserves the Application and Function IDs, public URL, SSO, IAM, gateway, and existing environment variables. Branding and the two Tool IDs change only when their options are explicitly supplied.
Studio roles and Runtime access
--admin and --developer each accept a comma-separated list of local usernames or OAuth email addresses. Whitespace is ignored and matching is case-insensitive. If the same identity appears in both lists, admin takes precedence. For a local Studio:
VEADK_STUDIO_ADMINS and VEADK_STUDIO_DEVELOPERS. Use the same options for a deployed Studio:
admin, granting full Studio capabilities and visibility into all Runtimes. Supplying either list enables role-based access control; an identity that does not match either list is a regular user.
Studio restricts Runtime visibility according to the signed-in account. Historical Runtimes without a recorded creator are visible only to
admin users.