# builderio/agent-native **Attribution required: if you use, quote, or summarise this content, you must credit and link back to [awesome-repositories.com](https://awesome-repositories.com/repository/builderio-agent-native).** _How this analysis was created: the description and tags below were written by an AI model that read this project's README and public documentation pages; stars, license and language come straight from the GitHub API. The model does not read the source code._ 7,645 stars · 704 forks · TypeScript · MIT ## Links - GitHub: https://github.com/BuilderIO/agent-native - Homepage: https://www.agent-native.com - awesome-repositories: https://awesome-repositories.com/repository/builderio-agent-native.md ## Topics `agent-framework` `agent-native` `agentic-ai` `agents` `ai` `ai-agents` `framework` `generative-ui` `mcp` `open-source` `react` `typescript` ## Description Agent-native is a TypeScript framework for building applications where AI agents and the user interface share the same actions, state, permissions, and data. Each capability is defined once as an action. Agents call it as a tool, and application code calls it as a typed function, so both work from one source of truth with the same validation and logic. The same action definitions can be served over HTTP, MCP, A2A, and the command line, which lets compatible agents and clients call them without the logic being rewritten. Work can be delegated to specialist agents that run in parallel, either in the same workspace or on connected remote agents. Agents keep reusable skills and long-term context outside any single session, so they resume with what they have learned. Tasks can also start on a schedule or in response to events, without a person launching each run. The project includes a visual editing environment. You adjust a running app's layout and styling on a canvas across device sizes, and the chosen changes are written back to the underlying source code with agent assistance. A chat interface sits inside the app so you can delegate work and review results where the work happens. Authentication and permissions control who can view or change work done by agents and users. Data is stored in PostgreSQL in production and in an embedded local database in development, with the same application code working against either. ## Tags ### Artificial Intelligence & ML - [Agent-Native Applications](https://awesome-repositories.com/f/artificial-intelligence-ml/agent-native-applications.md) — Provides a framework for building apps where AI agents and the interface share the same actions, state, permissions, and data. - [Agentic Application Frameworks](https://awesome-repositories.com/f/artificial-intelligence-ml/agentic-application-frameworks.md) — Provides a framework for building applications where agents and the interface share the same actions, state, permissions, and data. - [Multi-Agent Orchestration Platforms](https://awesome-repositories.com/f/artificial-intelligence-ml/agentic-systems-frameworks/agent-orchestration-multi-agent/coordination-and-routing/multi-agent-orchestration-platforms.md) — Delegates work to specialist agents that run in parallel in one workspace or on connected remote agents, coordinating through shared tools and memory. - [AI Agent Frameworks](https://awesome-repositories.com/f/artificial-intelligence-ml/ai-agent-frameworks.md) — Provides a TypeScript toolkit for defining each action once and exposing it as a tool to agents and a typed function to application code. - [Shared Agent-UI Action Definitions](https://awesome-repositories.com/f/artificial-intelligence-ml/shared-agent-ui-action-definitions.md) — Defines each capability once as an action that agents call as a tool and application code calls as a typed function. - [Agent-as-a-Tool Execution](https://awesome-repositories.com/f/artificial-intelligence-ml/workflow-as-a-tool-exposure/agent-as-a-tool-execution.md) — Defines each capability once as an action that agents call as a tool and interfaces call as code, with shared validation and permissions. ([source](https://github.com/builderio/agent-native#readme)) - [Long-term Memory Stores](https://awesome-repositories.com/f/artificial-intelligence-ml/agent-architectures/memory-management-systems/long-term-memory-stores.md) — Saves reusable skills and long-term context outside any single session so agents resume with prior knowledge. - [Agent Delegation](https://awesome-repositories.com/f/artificial-intelligence-ml/agent-delegation.md) — Hands work to specialist agents in the same workspace or on connected remote agents, running in parallel. - [Agent State Management](https://awesome-repositories.com/f/artificial-intelligence-ml/agent-state-management.md) — Keeps application state such as the current page or selected record in one place that both agent and interface read and act on. - [Multi-Protocol Tool Exposures](https://awesome-repositories.com/f/artificial-intelligence-ml/ai-agent-integrations/ai-agent-tool-integrations/multi-protocol-tool-exposures.md) — Serves each defined action over HTTP, MCP, A2A, and the command line so every client reuses the same validated logic. - [Event-Triggered Agent Runs](https://awesome-repositories.com/f/artificial-intelligence-ml/event-triggered-agent-runs.md) — Starts agent tasks from timers or incoming events so recurring background work runs without a person launching each run. - [Interactive Agent Chat Interfaces](https://awesome-repositories.com/f/artificial-intelligence-ml/interactive-agent-chat-interfaces.md) — Embeds a chat interface in the app to delegate work, ask questions, and review results where the work happens. ([source](https://github.com/builderio/agent-native#readme)) - [MCP Tool Servers](https://awesome-repositories.com/f/artificial-intelligence-ml/mcp-tool-servers.md) — Publishes defined actions as tools over MCP, A2A, HTTP, and command line so any compatible agent or client can call them. - [Multi-Protocol Action Servers](https://awesome-repositories.com/f/artificial-intelligence-ml/multi-protocol-action-servers.md) — Serves each defined action automatically over HTTP, MCP, A2A, and the command line from one underlying implementation. ### Web Development - [Running App Visual Editing](https://awesome-repositories.com/f/web-development/running-app-visual-editing.md) — Lets users adjust a running app's layout and styling on a canvas across device sizes and writes chosen edits back to source code. ([source](https://github.com/builderio/agent-native#readme)) ### Data & Databases - [Agent Memory Persistence](https://awesome-repositories.com/f/data-databases/data-engineering-infrastructure/data-persistence-storage/data-persistence-management/agent-memory-persistence.md) — Stores reusable skills and long-term context outside any single session so agents resume with what they have learned. ### Development Tools & Productivity - [A2A Protocol Servers](https://awesome-repositories.com/f/development-tools-productivity/agent-communication-protocol-servers/a2a-protocol-servers.md) — Exposes defined actions over HTTP, MCP, A2A, and the command line so one implementation serves every protocol. ([source](https://github.com/builderio/agent-native#readme)) - [Agent Session Persistence](https://awesome-repositories.com/f/development-tools-productivity/database-session-management/session-state-persistence/agent-session-persistence.md) — Persists reusable skills and context across separate sessions so agents continue from what they have learned. ([source](https://github.com/builderio/agent-native#readme)) ### Part of an Awesome List - [Single-Agent Frameworks](https://awesome-repositories.com/f/awesome-lists/ai/single-agent-frameworks.md) — TypeScript-first framework for building agent-first applications with shared state.