BuilderIO/agent-native

A framework for building agentic apps

What it solves

Agent-Native addresses the disconnect between autonomous AI agents and the human-facing applications they serve. It provides a unified framework where the agent's capabilities and the application's user interface are built from the same shared logic, ensuring that both the AI and the user interact with the same data, permissions, and tools.

How it works

The framework uses "Shared Actions" as its core building block. You define a capability once in TypeScript, and it automatically becomes available as a tool for the AI agent to call, a function for the UI to trigger, and an endpoint for HTTP, CLI, or other integrations. Because the agent and the UI share the same application state and database (PostgreSQL), any work performed by the agent is immediately visible and editable in the UI, and vice versa.

Who it’s for

This framework is for developers who want to build sophisticated, agentic applications that require a robust, purpose-built UI for human oversight, collaboration, and interaction, rather than relying solely on text-based chat interfaces.

Highlights

  • Unified Action Layer: Define capabilities once to power UI, agents, CLI, and HTTP endpoints.
  • Shared State & Data: Seamless synchronization between agent actions and the application's database and UI state.
  • Built-in Agent Features: Includes support for agent chat, authentication, permissions, memory, and multi-agent team delegation.
  • Developer-Friendly: Supports local development with PGlite and production deployment on Nitro-compatible hosts.

Related

  • Project
    cloudflare/agents

    Cloudflare Agents is a TypeScript SDK that turns Cloudflare Durable Objects into persistent, stateful “agents” with built‑in real‑time sync, scheduling, AI chat, tool execution, voice, email, payments, and more. It provides decorators for RPC, React hooks for the frontend, and a suite of packages for chat, code‑generation, and dynamic Workers. Ideal for per‑user assistants, collaborative apps, voice bots, and workflow engines.

  • Project
    codeany-ai/open-agent-sdk-typescript

    An open-source TypeScript SDK for running autonomous AI agents in-process, featuring a vast library of built-in tools and support for multiple LLM providers.

  • Project
    framerslab/agentos

    AgentOS is a TypeScript framework for building LLM‑driven AI agents with persistent, neuroscience‑inspired memory, optional HEXACO personality, runtime tool‑forging, and full‑runtime “Generalized Mind Instances.” It supports 13 LLM providers, multi‑agent orchestration, RAG pipelines, guardrails, voice/telephony, and a large extension ecosystem, and it reports top open‑source memory benchmark scores.

  • Project
    rajudandigam/agent-inspect

    A local-first observability and testing toolkit for TypeScript AI agents that enables debugging, CI/CD trajectory validation, and secure evidence sharing without external dependencies.

  • Project
    luoguoxiong/aipack

    aipack is a TypeScript‑first, lightweight AI‑agent framework. It includes its own runtime, a Tapable‑based plugin system, and built‑in adapters for 13+ LLM providers. Features include streaming vs. batch execution, persistent session storage, permission‑based tool approval, hybrid BM25 + vector long‑term memory, five‑stage context compression, multi‑agent orchestration (graph, pipeline, router, debate, map‑reduce), two‑way MCP integration, full observability (metrics, dashboard), and an offline evaluation suite. The project ships a CLI assistant, a library for embedding in apps, and example apps demonstrating real‑world use cases.