Kimi Formally Launches Hosted Agents for Enterprise AI Workloads

Moonshot AI’s Kimi announced the formal launch of Kimi Hosted Agents on November 5, 2026, giving enterprises and developers a managed cloud service for long-running agent tasks and multi-agent collaboration.

The service packages the agent harness—the operational layer for sessions, tool execution, sandboxes and failure recovery—as a hosted offering. The launch follows a Hosted Agents beta listed in September 2026 for domestic enterprise-verified users, so the November announcement formalizes a service that had already appeared in beta. Kimi positions it for internal business monitoring and operations response, as well as customer-facing investment-research and customer-service assistants.

Managed Runtime and Multi-Agent Execution

Hosted Agents is a prebuilt, configurable service running on Kimi’s infrastructure for long-running or asynchronous work. A direct model-inference API remains the alternative for organizations that want to build a custom harness and retain finer control. The hosted platform stores complete session history as events, runs built-in tools in isolated cloud sandboxes, and handles execution retries and scheduling. Kimi says the platform automatically takes over and resumes execution after a platform failure, with behavior consistent with its pre-interruption state; custom tools continue to run on the customer’s client.

Developers can work through a web console, REST API or kha command-line interface. Console use requires an account login, while CLI and cURL workflows use an API key. The service is stateful: session history, sandbox state and output files persist on the server. Its event stream supports resumption with a Last-Event-ID header after a disconnected client reconnects, and delivered files can be listed and downloaded as artifacts.

For multi-agent work, a coordinator agent delegates subtasks to child threads within the same session. Its delegation configuration can contain between one and 20 agent entries. Synchronous delegation waits for a child thread to report, become idle or terminate; asynchronous delegation returns as soon as the child starts, with the report delivered later. Child threads cannot create another level of child threads or communicate directly with one another. Each thread retains separate status, history and event streams, supporting inspection and auditing of individual subtasks.

Security Controls and Self-Hosting Boundaries

Independent sandboxes, network-access controls, configurable operating boundaries, session interruption, execution records and audit export form the service’s control layer. Kimi Inference Hook can connect to enterprise-built or purchased security services and inspect task inputs and tool returns before each model inference. The enterprise defines the rules, and the hook allows or rejects the content. Kimi is offering the hook selectively to enterprise-verified users.

A self-hosted environment moves sandbox tool execution to a customer-managed host, while Kimi’s platform continues to handle model calls, agent orchestration and session management. This option is also restricted to enterprise-verified users. Kimi explicitly states that self-hosting is not equivalent to private deployment because tool inputs and execution results still pass through the platform’s model-inference interface.

The self-hosted version does not support IPython, image-search tools or save_artifact. Uploaded files, skills and memory are not mounted on the worker host, and platform web search remains platform-executed and chargeable.

Templates and Usage-Based Pricing

Kimi says Hosted Agents includes more than 140 skills and more than 30 plugins covering web retrieval, professional data queries, office-document processing and content generation. Enterprises can add custom skills, plugins, MCP services and tools to connect their own systems and data sources.

The documentation lists 12 official agent templates: eight financial templates plus game-development, player-advisor, SRE incident-response and Discord community-operations examples. The financial templates cover work including modeling, deep research, morning reports, IPO tracking and portfolio reviews; enterprises can copy them into their own projects and connect internal systems and private databases.

Hosted Agents pricing combines sandbox runtime at ¥0.072 per hour, model inference charged at the selected model’s token rates, and plugin charges based on call counts and each plugin’s unit price. Usage reports are designed to show resource consumption and costs by agent project. That makes the central enterprise trade-off concrete: Kimi takes on the harness and managed infrastructure, while custom execution, security policy, data paths and continuing usage charges remain part of the customer’s operating design.