# Kimi Kimi from Moonshot AI with the OK Computer agent mode for research and documents, plus Kimi Code as a coding agent for terminal, VS Code and desktop. Canonical profile: https://ki-agentenkompass.de/en/agents/kimi/ Editor: [Michael Meierhoff](https://ki-agentenkompass.de/en/about/) Sources reviewed: 2026-11-05 Basis: provider documentation. Examples are editorial suggestions, not hands-on product tests. ## Overview This profile covers two parts of Kimi. According to the help centre, OK Computer was the first agent mode (launched 26 September 2025); the help centre now speaks of Kimi Agent. According to the product comparison, Kimi Code is the coding suite for developers. The comparison lists Kimi Work (local desktop agent) and Kimi Claw (cloud automation) as separate products. The older Python repository kimi-cli is archived and points to Kimi Code CLI. - Provider: Moonshot AI - Product family: Kimi - Profile type: Chat assistant with agent mode and coding agent suite - Environment: Web and mobile app; Kimi Code in the terminal, as a VS Code extension and as a desktop client - Connections: MCP servers, skills, ACP for editors such as Zed and JetBrains, hooks in Kimi Code - Setup: For agent mode, open kimi.com/agent or choose the K3 or K3 Swarm model in the app. You install Kimi Code CLI by script and sign in with /login. - Pricing model: The membership help page names the China plans Go to Ultra (¥49 to ¥1,399 per month). It names no free plan; prices in US dollars could not be confirmed. Kimi Code needs Plus or higher according to the help page. The Kimi Code CLI is released under the MIT licence. ## Key features ### OK Computer agent mode The agent plans tasks from research to delivery and calls tools repeatedly. Entry is through kimi.com/agent or the K3 model in the app. Source: https://www.kimi.com/en/help/agent/agent-overview ### Documents, analyses and web pages According to the help centre, the agent produces code projects, data analyses with charts, office documents such as Word, PDF and PPT, and deployed web pages, among other outputs. Source: https://www.kimi.com/en/help/agent/agent-overview ### Agent Swarm According to the help centre, Agent Swarm can coordinate up to 300 sub-agents and support more than 4,000 tool calls. Source: https://www.kimi.com/en/help/agent/agent-overview ### Kimi Code CLI Terminal agent for software tasks with plan mode, sessions and confirmation before file changes and shell commands. You sign in with a Kimi Code login or a Kimi Platform API key. Source: https://www.kimi.com/code/docs/en/kimi-code-cli/guides/getting-started.html ### Subagents, skills and hooks According to the README there are coder, explore and plan subagents in isolated contexts, skills and MCP servers from a marketplace or GitHub, and hooks that run local commands at defined points. Source: https://github.com/MoonshotAI/kimi-code ### Editor integration through ACP With kimi acp, Kimi Code can be used in Zed and JetBrains according to the README. Source: https://github.com/MoonshotAI/kimi-code ### Several Kimi products The product comparison separates Kimi (web and app), Kimi Work (local desktop agent), Kimi Code (CLI and VS Code extension) and Kimi Claw (cloud automation). Source: https://www.kimi.com/en/help/others/product-comparison ## Example workflows ### Research as a presentation - Your input: A topic and wanted sources in agent mode on kimi.com/agent. - Possible result: The agent plans and researches and, according to the help centre, delivers results as PPT, Word or PDF, among other formats. - What to check: Check figures and sources against the originals; a run usually takes 5 to 20 minutes. ### Code change with Kimi Code CLI - Your input: A repository in the terminal and a limited task, in plan mode first if needed. - Possible result: Changes to files and shell commands only after your confirmation. - What to check: Check the diff and tests before you accept. ## Requirements and limits ### Plan for Kimi Code Requirement: Kimi Code is usable from Plus on the new plans and from Andante on the older ones. The Go plan has no coding quota. Source: https://www.kimi.com/en/help/kimi-code/benefits ### Context, duration and file output Limitation: The agent has a 128K-token context window, single tasks usually take 5 to 20 minutes, and in the general agent scenario usually only one file is output at a time; multiple files need Agent Swarm. Source: https://www.kimi.com/en/help/agent/agent-features-and-limits ### Data storage in China and training Limitation: The privacy policy for users in mainland China stores personal data in the People’s Republic of China and does not provide it abroad without separate consent. Strictly de-identified inputs and outputs are used to optimise models; opting out goes through customer service. Source: https://www.kimi.com/user/agreement/userprivacy?version=v2 ### Older kimi-cli archived Limitation: The Python repository kimi-cli is no longer maintained according to its page and points to Kimi Code CLI. Existing installations are no longer supported. Source: https://github.com/MoonshotAI/kimi-cli ### US dollar prices and plan for agent mode Not yet confirmed: The membership page names five China plans with yuan prices and no free offer; agent credits are a shared monthly pool according to the page. US dollar prices and offers outside China could not be confirmed. Source: https://www.kimi.com/en/help/membership/membership-overview ## A good fit if … - you want to hand research and documents to agent mode as a task and collect them later - you want a coding agent in the terminal with an MIT-licensed CLI and confirmation before changes - you want to use Kimi models and accept the provider's data position for your data ## Less suitable if … - you must have data processed exclusively within the EU - you rely on a free plan or prices in US dollars - you need scheduled runs in agent mode, which the reviewed pages do not document Editorial assessment based on provider documentation. Not a product test. ## Usable AI models Open choice In web and app you use Kimi models, with K3 depending on your plan. In the Kimi Code CLI you can also add Anthropic, OpenAI and Google with your own key, or an OpenAI-compatible endpoint, for example for DeepSeek or Qwen. The docs do not cover local model servers. - Model families named: Moonshot (Kimi), Anthropic (Claude), OpenAI (GPT), Google (Gemini), DeepSeek, Alibaba (Qwen) · Other models can be connected freely - Model choice: You choose - Your own API key: Yes - Router or custom endpoint: Yes - Local models: Not stated - Depends on: Plan Documented · Sources accessed on: 2026-11-05 - [Kimi Code CLI: Providers and models](https://www.kimi.com/code/docs/en/kimi-code-cli/configuration/providers.html) - [Kimi Code CLI: Getting started](https://www.kimi.com/code/docs/en/kimi-code-cli/guides/getting-started.html) - [Kimi: Agent overview](https://www.kimi.com/en/help/agent/agent-overview) - [Kimi Code: Benefits](https://www.kimi.com/en/help/kimi-code/benefits) ## Europe & regional availability Help centre and two privacy policies reviewed. No page names a country list or availability in Europe. Reviewed scope: Kimi (web, app, agent) and Kimi Code; different privacy policies apply by region Reviewed on: 2026-11-05 ### Europe: no availability statement Availability still unclear No reviewed page names availability or a plan offer in Europe. The privacy policy on kimi.com applies to users in mainland China according to the page; it refers users outside that region to kimi.ai, which was not reviewed. Region covered: EU/EEA, United Kingdom and Switzerland Documented reason: The reviewed sources name no country release for this. Official source: https://www.kimi.com/user/agreement/userprivacy?version=v2 Official source: https://www.kimi.com/en/help/membership/membership-overview ### Data processing and storage Availability still unclear Under the policy for mainland China, personal data is stored in the People's Republic of China; the help centre names storage on servers in mainland China. The Moonshot AI PTE. LTD. policy (Kimi Claw and Kimi) instead says data may be stored outside the country of residence and names no location. No reviewed page says where data is processed. Region covered: EU/EEA, United Kingdom and Switzerland Documented reason: The pages differ by company and region; which one applies to you is open. Official source: https://www.kimi.com/user/agreement/userprivacy?version=v2 Official source: https://www.kimi.com/en/help/others/data-usage Official source: https://www.kimi.com/user/agreement/en/kimiClawPrivacy ## Accounts & permissions Based on provider documentation. Permissions depend on the account, integration and organization policies. Review the permissions actually requested before use. Configuration covered: Kimi account with membership; Kimi Code also with an API key Sources reviewed: 2026-11-05 ### Account used Documented: Kimi Code CLI signs in with a Kimi Code login (device code) or a Kimi Platform API key; /logout clears the credentials. Other providers are entered in ~/.kimi-code/config.toml. Evidence: https://www.kimi.com/code/docs/en/kimi-code-cli/guides/getting-started.html ### Admin approval Open in reviewed sources: The reviewed pages describe no approval or restriction by an organisation's administrators for Kimi or Kimi Code. Evidence: https://www.kimi.com/code/docs/en/kimi-code-cli/guides/getting-started.html Evidence: https://www.kimi.com/en/help/membership/membership-overview Evidence: https://www.kimi.com/en/help/others/product-comparison ### Data access & team sharing Documented: The CLI runs read-only operations automatically and asks before file changes and shell commands. For the agent mode's reach, the help centre lists tools such as terminal and file system but describes no sandbox. Evidence: https://www.kimi.com/code/docs/en/kimi-code-cli/guides/getting-started.html Evidence: https://www.kimi.com/en/help/agent/agent-overview ## Prices and included usage Pricing checked: 2026-11-05 The membership help page names the China plans Go, Plus, Pro, Max and Ultra at ¥49, ¥99, ¥199, ¥699 and ¥1,399 per month. It names no free plan. Prices in US dollars could not be confirmed. ### Go ¥49 per month (China) Agent credits at base level, one parallel agent task, no Agent Swarm. Price source: https://www.kimi.com/en/help/membership/membership-overview ### Plus ¥99 per month (China) Double agent credits, two parallel tasks, Agent Swarm. Price source: https://www.kimi.com/en/help/membership/membership-overview ### Pro ¥199 per month (China) Four times the agent credits, two parallel tasks, Agent Swarm. Price source: https://www.kimi.com/en/help/membership/membership-overview ### Max ¥699 per month (China) 14 times the agent credits, four parallel tasks, Agent Swarm. Price source: https://www.kimi.com/en/help/membership/membership-overview ### Ultra ¥1,399 per month (China) 28 times the agent credits, four parallel tasks, Agent Swarm. Price source: https://www.kimi.com/en/help/membership/membership-overview The page explicitly names these as the current China plans. Prices outside China were not confirmed. Kimi Code access depends on the plan (from Plus, or Andante on older plans); credits are a shared monthly pool according to the help page. Pricing details: https://www.kimi.com/en/help/membership/membership-overview ## Operation & oversight Based on public provider documentation. Assessments are editorial inferences from the stated properties. Actual time requirements and reliability have not been measured. Deployment covered: Agent mode in the cloud and Kimi Code CLI locally Sources reviewed: 2026-11-05 ### Files and working state Documented: The CLI stores sessions locally under ~/.kimi-code/. The reviewed pages do not say how long cloud agent runs are kept. Evidence: https://www.kimi.com/code/docs/en/kimi-code-cli/guides/getting-started.html ### Sign-ins Documented: Sign-in by device code or API key; /logout clears the credentials. The page names no time limits. Evidence: https://www.kimi.com/code/docs/en/kimi-code-cli/guides/getting-started.html ### Starting further runs Documented with conditions: Agent tasks usually take 5 to 20 minutes; you can leave the page, the task continues in the background and the system notifies you when it is done. Schedules belong to separate pages and products that were not reviewed. Evidence: https://www.kimi.com/en/help/agent/agent-features-and-limits ### Human intervention Documented: The CLI asks before file changes and shell commands; read-only operations run automatically by default. Shift-Tab toggles Plan mode. Evidence: https://www.kimi.com/code/docs/en/kimi-code-cli/guides/getting-started.html ### Detecting errors Open in reviewed sources: The reviewed pages say nothing on error handling and retries. Agent mode can be interrupted with Stop output. Evidence: https://www.kimi.com/en/help/agent/agent-features-and-limits ### Resuming after failures Documented with conditions: You resume CLI sessions with /sessions or copy them with /fork. For cloud agent runs the pages describe no resuming. Evidence: https://www.kimi.com/code/docs/en/kimi-code-cli/guides/getting-started.html ### Editorial assessment The CLI asks before risky actions and stores locally. For agent mode, the context limit, duration and the privacy position by region matter; before use, check which company and policy apply to you. ## Memory and conversation continuity Scope: Kimi Code CLI locally; Kimi web and app with an account Sources accessed: 2026-11-05 Kimi Code CLI stores configuration, sessions and logs locally. The reviewed pages describe no memory across sessions. ### Storage and scope Partly documented: The CLI stores configuration, session records, logs and the update cache under ~/.kimi-code/ by default; KIMI_CODE_HOME changes the location. The help centre generally names storage on servers in mainland China, without naming a domain or product. - [Kimi Code CLI: Getting started](https://www.kimi.com/code/docs/en/kimi-code-cli/guides/getting-started.html) - [Kimi data usage and sharing](https://www.kimi.com/en/help/others/data-usage) ### Selection and timing Not publicly established: Not described: what the agent keeps across sessions or when. - [Kimi Code CLI: Getting started](https://www.kimi.com/code/docs/en/kimi-code-cli/guides/getting-started.html) ### Inspect, edit and delete Partly documented: With /sessions you browse and resume sessions. According to the privacy policy, you delete chat history with the delete-conversation button in the history and the account in settings. - [Kimi Code CLI: Getting started](https://www.kimi.com/code/docs/en/kimi-code-cli/guides/getting-started.html) - [Kimi privacy policy](https://www.kimi.com/user/agreement/userprivacy?version=v2) ### Agent and channel boundaries Not publicly established: Not described: how Kimi Code, agent mode and chat share memory. The privacy policy names web, app, Kimi Work and Kimi Code as covered products. - [Kimi privacy policy](https://www.kimi.com/user/agreement/userprivacy?version=v2) ### Retrieval Partly documented: Sessions can be resumed with /sessions and copied with /fork. No automatic search across earlier sessions is described. - [Kimi Code CLI: Getting started](https://www.kimi.com/code/docs/en/kimi-code-cli/guides/getting-started.html) ### Session reset and compaction Partly documented: /compact compresses the context manually to free tokens. Agent mode has a 128K-token context window; the pages say nothing on resetting. - [Kimi Code CLI: Getting started](https://www.kimi.com/code/docs/en/kimi-code-cli/guides/getting-started.html) - [Kimi Agent features and limits](https://www.kimi.com/en/help/agent/agent-features-and-limits) ## Context The agent works with a 128K-token context; single tasks usually take 5 to 20 minutes. Under the privacy policy for users in mainland China, personal data is stored in the People's Republic of China. Provider help centre, product pages, privacy policies and repositories reviewed. Some pricing pages could not be read, so US dollar prices are missing. Example tasks are editorial; hands-on tests are pending. ## Open points Europe, availability still unclear: - Europe: no availability statement - Data processing and storage Requirements and limits, not yet confirmed: - US dollar prices and plan for agent mode ## Sources - https://www.kimi.com/ - https://www.kimi.com/en/help/others/product-comparison - https://www.kimi.com/en/help/agent/agent-overview - https://www.kimi.com/en/help/agent/agent-features-and-limits - https://www.kimi.com/code - https://www.kimi.com/code/docs/en/kimi-code-cli/guides/getting-started.html - https://github.com/MoonshotAI/kimi-code - https://github.com/MoonshotAI/kimi-cli - https://www.kimi.com/en/help/membership/membership-overview - https://www.kimi.com/en/help/kimi-code/benefits - https://www.kimi.com/code/docs/en/kimi-code/membership.html - https://www.kimi.com/en/help/others/data-usage - https://www.kimi.com/user/agreement/userprivacy?version=v2 - https://www.kimi.com/user/agreement/en/kimiClawPrivacy ## Provider The privacy policy for mainland China names Beijing Moonshot AI as operator; another policy names Moonshot AI PTE. LTD. - Operator: Moonshot AI - Organization: Provider - Website: https://www.kimi.com/ - Reviewed: 2026-11-05 - Repository: https://github.com/MoonshotAI/kimi-code - GitHub-Stars: 8143 (2026-11-05) - License: MIT - Provider source: https://www.kimi.com/ - Provider source: https://www.kimi.com/user/agreement/userprivacy?version=v2 - Provider source: https://www.kimi.com/user/agreement/en/kimiClawPrivacy [Sources and method](https://ki-agentenkompass.de/en/sources/)