{"slug": "announcing-nocobase-2-1-0", "title": "Announcing NocoBase 2.1.0", "summary": "NocoBase released version 2.1.0 with major upgrades to AI capabilities, multi-app support, and 2.0 adaptation. The new NocoBase CLI enables both humans and AI Agents to connect and manage applications, while AI-assisted building allows natural language configuration of data models, pages, permissions, and workflows. The release also introduces NocoBase Skills, a set of domain knowledge packs for AI Agents covering the full building flow.", "body_md": "NocoBase 2.1 is a major upgrade to **AI capabilities, multi-app, and 2.0 adaptation**. We’ve introduced the NocoBase CLI, making it easy for both people and AI Agents to connect to and manage NocoBase applications. From creating applications and AI-assisted building to enhanced AI Employees and an AI development plugin, it covers the full flow from environment onboarding to system building and business collaboration. We’ve also enhanced multi-app capabilities to make interaction and collaboration across apps easier. At the same time, we’ve added version control and continued to substantially round out 2.0 page support and core capabilities — more blocks, fields, actions, and plugins now support 2.0.\n\n## What’s New\n\n### Introducing the NocoBase CLI\n\nIn this release, the NocoBase CLI (`nb`\n\n) is the core entry point for both regular users and AI Agents to connect to NocoBase.\n\nThe CLI is used to initialize, connect, and manage NocoBase applications in a local workspace. It covers several scenarios:\n\n- Install a new NocoBase application via Docker, npm, or Git, then save it as a CLI env\n- Connect to an existing NocoBase application and save it as a CLI env\n- Install, create, and activate plugins\n- Operate, back up, and manage NocoBase applications\n\nWhether you want to plug AI into an existing system or spin up a new application from scratch, you can handle initialization and ongoing management through the CLI.\n\nFor teams, the CLI provides a standard entry point that AI Agents can understand and operate on — environment initialization, connection configuration, and runtime management all share the same flow.\n\nThe official release also adds a set of operations-related commands:\n\n`nb api`\n\n: Call the NocoBase API through the CLI.`nb app`\n\n: Manage application runtime state: start, stop, restart, logs, and upgrade.`nb backup`\n\n: Create a backup and download it locally, or restore a local backup file to a target env.`nb config`\n\n: Manage CLI default configuration.`nb db`\n\n: Manage the built-in database of the selected env.`nb env`\n\n: Manage NocoBase project environments, the current env, status, details, and runtime commands.`nb license`\n\n: Manage commercial licenses and licensed plugins.`nb plugin`\n\n: Manage plugins of the selected NocoBase env.`nb scaffold`\n\n: Generate a NocoBase plugin development scaffold.`nb self`\n\n: Check or update the NocoBase CLI itself.`nb source`\n\n: Manage local source projects: download, develop, build, and test.\n\nRelated documentation:\n\n### AI-assisted building: replace manual configuration with conversation\n\nAI-assisted building is one of the core experiences in this release. You can describe your business needs in natural language, and the AI helps complete data modeling, page configuration, permission setup, and workflow orchestration.\n\nCompared with traditional low-code building, AI-assisted building has several clear advantages:\n\n- A lower barrier to entry — you don’t need to be familiar with every configuration concept up front\n- A shorter path from requirement description to working prototype\n- Data, UI, and workflow configuration can be completed by the AI continuously\n\nFor example: “design a CRM data model for me”, “create a customer management page for me”, or “orchestrate a workflow that automatically deducts inventory after an order is created” — all of these can be handled by the AI within the scope of NocoBase’s capabilities.\n\nRelated documentation:\n\n### NocoBase Skills cover the full building flow\n\nTo help the AI truly understand NocoBase’s configuration system, this release ships a set of domain knowledge packs that can be installed into AI Agents — NocoBase Skills.\n\nSkills are standardized knowledge and operation wrappers organized around NocoBase’s key capability domains, helping the AI more accurately understand object models, configuration structures, and execution boundaries.\n\nWe currently provide 8 Skills that cover the full building flow:\n\n[Environment management](https://docs.nocobase.com/ai-builder/env-bootstrap)— environment checks, install/deploy, upgrade, and troubleshooting[Data modeling](https://docs.nocobase.com/ai-builder/data-modeling)— create and manage tables, fields, and relations[UI building](https://docs.nocobase.com/ai-builder/ui-builder)— create and edit pages, blocks, popups, and interaction reactions[Workflow management](https://docs.nocobase.com/ai-builder/workflow)— create, edit, enable, and diagnose workflows[Permission configuration](https://docs.nocobase.com/ai-builder/acl)— manage roles, permission policies, user bindings, and risk assessment[Solutions](https://docs.nocobase.com/ai-builder/dsl-reconciler)— bulk-build entire business systems from YAML (still in beta, with limited stability)[Plugin management](https://docs.nocobase.com/ai-builder/plugin-manage)— view, enable, and disable plugins[Publish management](https://docs.nocobase.com/ai-builder/publish)— cross-environment publishing, backup/restore, and migration\n\nWith Skills, the AI can more accurately understand NocoBase’s configuration system and provide smarter assistance when building and managing systems.\n\n**Note**: NocoBase Skills are still being actively improved. NocoBase Skills are also installed automatically when you install and initialize the NocoBase CLI, so in most cases you don’t need to install them separately.\n\nRelated documentation:\n\n### AI development plugin\n\nThis release fills in the foundational capabilities needed for AI plugin development, so the AI can take part not only in application building but also in custom plugin development.\n\nThis shows up in three main areas:\n\n- A unified\n`rsbuild/rspack`\n\nbuild pipeline, consolidating plugin development and the frontend build system - A\n`client-v2`\n\ncapability and`/v/`\n\nrouting system aimed at AI development, preparing for the next-generation client plugin development - AI plugin development Skills that help the AI better understand plugin structure, code organization, and implementation patterns\n\nPreparation around `client-v2`\n\nincludes:\n\n`@nocobase/app`\n\nexposes the`client-v2`\n\nentry- The kernel ships a\n`@nocobase/client-v2`\n\npackage with base components, utilities, and type definitions - Each plugin gets a\n`/src/client-v2`\n\ndirectory - A new\n`/v/`\n\nroute is added — still being actively improved, available for early adopters - The kernel is gradually migrating to V2\n- Plugins are gradually migrating to V2\n\nA unified build pipeline lowers the cost of frontend plugin development and debugging. The gradual rollout of `client-v2`\n\nalso gives the AI a more stable target structure for generating and maintaining plugin code.\n\nIn practice: you can describe a plugin requirement in natural language, and the AI helps generate the frontend and backend code, data tables, APIs, permission configuration, and i18n content.\n\n**Note**: AI plugin development is only for `client-v2`\n\n-style new plugins. We will follow up with migration documentation and Skills for moving from `client-v1`\n\nplugins to `client-v2`\n\n, to help you bring existing plugins into the new system.\n\nRelated documentation:\n\n### AI Employees enhancements\n\nAI-assisted building answers “how do I use AI to build a system”; AI Employees answer “how do I let AI work inside the system to solve concrete business problems”.\n\nAI Employees existed in earlier releases, but in this release the related capabilities have been enhanced and the AI kernel has been rounded out:\n\n[MCP support](https://docs.nocobase.com/ai-employees/features/mcp)[New AI Employee Atlas](https://docs.nocobase.com/ai-employees/features/built-in-employee#default-ai-employee-atlas), playing a team-leader role and dispatching other AI Employees to complete tasks based on user intent[AI Employee workflow node](https://docs.nocobase.com/ai-employees/workflow/nodes/employee/configuration)[LLM-based web search tool](https://docs.nocobase.com/ai-employees/features/web-search)[New aggregation query tool and report generation tool](https://docs.nocobase.com/ai-employees/scenarios/business-report)for producing business analysis reports[New localization engineer Lina](https://docs.nocobase.com/ai-employees/built-in/lina), a built-in AI Employee from the localization plugin used for system localization translation, supporting incremental, selected, and full translation scopes\n\nThese improvements take AI Employees’ extensibility, orchestration, and execution capabilities inside business systems to the next level. AI Employees can understand the current business context, invoke skills to execute specific tasks, participate in automated workflows, and combine external information to deliver analysis and output.\n\nThe official release also adds support for AI Employees to load files from workflow attachment fields and to handle multiple conversations in parallel, further improving the usability of AI Employees in real business processes.\n\nRelated documentation:\n\n[AI Employees](https://docs.nocobase.com/ai-employees/)[Lina: Localization engineer](https://docs.nocobase.com/ai-employees/built-in/lina)[Translate localization terms with Lina and a local HY-MT1.5-1.8B model](https://docs.nocobase.com/ai-employees/scenarios/localization-hy-mt)\n\n### Version control\n\nVersion control helps you better manage your application’s version iterations and change history. You can create, view, and restore different versions of an application, making it easy to switch versions and recover from issues during development and operations. **Note: This feature requires the Professional edition or above.**\n\nRelated documentation:\n\n### Multi-app enhancements\n\nIn this release, we have made some important enhancements to multi-app deployments, mainly in three areas:\n\n[New app block and app switcher](https://docs.nocobase.com/multi-app/multi-app/app-block-and-switcher), which let you surface entry points to other sub-applications on a page, making it easy for users to switch between the main app and sub-apps.\n\n[New app single sign-on](https://docs.nocobase.com/multi-app/multi-app/app-sso). When a user enters a sub-app from the main app, or switches between sub-apps, the system attempts to automatically sign them in to the target sub-app using the currently logged-in user. Users no longer need to re-enter their credentials in each sub-app.\n\n[Calling sub-app APIs](https://docs.nocobase.com/multi-app/multi-app/sub-app-api). In multi-app scenarios, each sub-app has its own independent API, distinguished by path prefix, parameters, and so on, making it easy to call a sub-app’s API.\n\nThese enhancements are very practical for users running multi-app deployments, making it easier to exchange data and operate across multiple applications and improving the overall collaboration efficiency of multi-app systems.\n\nRelated documentation:\n\n### Workflow enhancements\n\nThis release enhances the **controllability and observability** of workflows:\n\n- Added timeout control — workflows that run too long are automatically terminated (subflows also support timeout configuration)\n- Added created-by and updated-by fields\n- Added a log field to node jobs, making it easier to view node logs while debugging\n- The Webhook trigger (synchronous mode) returns a 408 response status on timeout\n\nRelated documentation:\n\n### Handwritten signature field\n\nAdded a handwritten signature field that lets you draw and save a signature in a form, suitable for approvals, confirmation sheets, receipts, and similar scenarios.\n\nRelated documentation:\n\n### JS Item action\n\nAdded the JS Item action, which lets you run custom logic in an action by writing JS, working together with event flows to meet more flexible interaction needs.\n\nRelated documentation:\n\n### 2.0 adaptation and new features\n\nBeyond AI, this release continues to migrate key feature modules to 2.0, while also rolling out new features for real-world business scenarios.\n\nNew features\n\n2.0 adaptation\n\n[Custom request](https://docs.nocobase.com/interface-builder/actions/types/custom-request)[Tree filter block](https://docs.nocobase.com/interface-builder/blocks/filter-blocks/tree)[Calendar block](https://docs.nocobase.com/data-sources/calendar/)[Kanban block](https://docs.nocobase.com/interface-builder/blocks/data-blocks/kanban)[Gantt block](https://docs.nocobase.com/plugins/@nocobase/plugin-gantt)[List block](https://docs.nocobase.com/interface-builder/blocks/data-blocks/list)[Grid card block](https://docs.nocobase.com/interface-builder/blocks/data-blocks/grid-card)[Map block](https://docs.nocobase.com/plugins/@nocobase/plugin-map)[Markdown block](https://docs.nocobase.com/interface-builder/blocks/other-blocks/markdown)[iframe block](https://docs.nocobase.com/integration/embed)[Chart block / Data visualization](https://docs.nocobase.com/data-visualization)\n\n## Multilingual documentation\n\n- Added Indonesian and Vietnamese documentation", "url": "https://wpnews.pro/news/announcing-nocobase-2-1-0", "canonical_source": "https://www.nocobase.com/en/blog/2.1.0", "published_at": "2026-06-15 01:34:43+00:00", "updated_at": "2026-06-16 01:53:19.496899+00:00", "lang": "en", "topics": ["ai-agents", "developer-tools", "artificial-intelligence"], "entities": ["NocoBase", "NocoBase CLI", "NocoBase Skills"], "alternates": {"html": "https://wpnews.pro/news/announcing-nocobase-2-1-0", "markdown": "https://wpnews.pro/news/announcing-nocobase-2-1-0.md", "text": "https://wpnews.pro/news/announcing-nocobase-2-1-0.txt", "jsonld": "https://wpnews.pro/news/announcing-nocobase-2-1-0.jsonld"}}