--- title: "Clone an agent" method: POST path: "/v1/fleet/agents/{agent_id}/clone" tags: ["agents"] --- # Clone an agent `POST /v1/fleet/agents/{agent_id}/clone` Creates a new agent that mirrors the source agent's behaviour but is owned by the calling identity. Creation is atomic — the clone is either fully created or no state is persisted. What is copied from the source: * `description` * `runtime` (model configuration) * `backend` (backend type + sandbox configuration) * `system_prompt`, `tools`, `subagents`, `skills` * any leftover files outside the typed fields above (e.g. `docs/README.md` attached via the escape `files` field) What the caller can override (sent in the request body): * `name` — defaults to `" (Copy)"` * `permissions` — defaults to the source's `identity` with `visibility=user` and `tenant_access_level=read`. When supplied the object fully replaces the default; PATCH-style merging does not apply. What is always reset for the clone (you cannot override these): * agent ID, agent version, owner, timestamps * stamped user context (`user_email`, `user_name`, `user_timezone` — taken from the calling identity + the `X-User-Timezone` header) What is never copied (start fresh on the clone): * `extras` (caller-defined metadata bag, e.g. icon customisations, template IDs) * caller-defined `configurable` bag entries * sharing state, tokens, triggers, and schedules Cloning a built-in system template returns 422. ## Path parameters - `agent_id` string, uuid, required ## Query parameters - `include_files` boolean ## Request body - AgentsCloneAgentRequest - `name` string - `permissions` AgentsAgentPermissions - `identity` 'personal' | 'shared' - `shared_users` AgentsSharedUsers - `read` string[] — User IDs allowed to read the agent. - `run` string[] — User IDs allowed to run the agent. - `update` string[] — User IDs allowed to update the agent. - `tenant_access_level` 'read' | 'run' | 'write' - `visibility` 'tenant' | 'user' ## Response `201` Created - AgentsAgent - `access_level` 'READ' | 'RUN' | 'WRITE' - `backend` AgentsAgentBackend - `sandbox` AgentsSandboxConfig - `delete_after_stop_seconds` integer — Time after a sandbox is stopped before it is deleted, in seconds. - `idle_ttl_seconds` integer — Idle timeout after which an unused sandbox is paused, in seconds. - `policy_ids` string[] — Sandbox policies governing tool execution. - `snapshot_id` string — Snapshot used when creating new sandbox-backed computers. - `type` 'default' | 'thread_scoped_sandbox' | 'agent_scoped_sandbox' — Execution backend type. Use a scoped sandbox backend for sandbox-backed agents. - `created_at` string, date-time - `description` string - `extras` object - `files` object — Raw file map. Returned only when `include_files=true`. - `id` string, uuid - `instructions` string — Deprecated: use `system_prompt`. Echoed alongside `system_prompt` with the same value for backwards compatibility. - `is_owner` boolean - `name` string - `owner_id` string, uuid - `permissions` AgentsAgentPermissions - `identity` 'personal' | 'shared' - `shared_users` AgentsSharedUsers - `read` string[] — User IDs allowed to read the agent. - `run` string[] — User IDs allowed to run the agent. - `update` string[] — User IDs allowed to update the agent. - `tenant_access_level` 'read' | 'run' | 'write' - `visibility` 'tenant' | 'user' - `revision` string - `runtime` AgentsAgentRuntime - `model` AgentsAgentModelConfig - `model_id` string — Model ID used to run the agent. - `skills` AgentsSkillSpec[] — Skills parsed from `skills//SKILL.md` and supporting files. - `description` string — Short human-readable description shown to the agent. - `files` object — Supporting files keyed by relative path. Each path becomes `skills//`. Paths must be relative — no leading `/`, no `..` segments. - `instructions` string — Skill body. Written to `skills//SKILL.md`. - `name` string — Skill slug. Becomes `skills//SKILL.md`. - `type` 'inline' — Skill discriminator. Only `inline` is supported today. - `subagents` AgentsSubagentSpec[] — Subagents parsed from `subagents//AGENTS.md` + `subagents//tools.json`. - `description` string — Short human-readable description. - `instructions` string — Subagent system prompt. Written to `subagents//AGENTS.md`. - `model_id` string — Model ID for this subagent. Inherits the parent runtime when empty. - `name` string — Subagent slug. Becomes `subagents//AGENTS.md`. - `tools` AgentsToolsConfig - `interrupt_config` object — Per-tool interrupt rules keyed by tool name. Use `{}` for no interrupts. - `tools` AgentsToolSpec[] — MCP tools available to the agent. Serialised to `tools.json`. - `display_name` string — Display name for the tool. Defaults to the tool name when empty. - `mcp_server_name` string — Display name for the MCP server. Defaults to the URL when empty. - `mcp_server_url` string — URL of the MCP server hosting this tool. - `name` string — Tool name as exposed by the MCP server. - `system_prompt` string — Agent system prompt parsed from `AGENTS.md`. - `tools` AgentsToolsConfig - `interrupt_config` object — Per-tool interrupt rules keyed by tool name. Use `{}` for no interrupts. - `tools` AgentsToolSpec[] — MCP tools available to the agent. Serialised to `tools.json`. - `display_name` string — Display name for the tool. Defaults to the tool name when empty. - `mcp_server_name` string — Display name for the MCP server. Defaults to the URL when empty. - `mcp_server_url` string — URL of the MCP server hosting this tool. - `name` string — Tool name as exposed by the MCP server. - `updated_at` string, date-time ## Other responses - `400` — Bad Request - `401` — Unauthorized - `403` — Forbidden - `404` — Not Found - `422` — Unprocessable Entity - `500` — Internal Server Error - `502` — Bad Gateway - `503` — Service Unavailable --- [API](https://skmtc.net/langchain-ai/apis/langsmith.md) · [All operations](https://skmtc.net/langchain-ai/apis/langsmith/llms.txt) · [OpenAPI document](https://skmtc-service-staging.skmtc.workers.dev/v1/apis/langchain-ai/langsmith/versions/a0acb3a6a101/schema)