BuilderIO/agent-native
Agent Native
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.
