# ag-ui-protocol/ag-ui

**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/ag-ui-protocol-ag-ui).**

14,395 stars · 1,296 forks · Python · MIT

## Links

- GitHub: https://github.com/ag-ui-protocol/ag-ui
- Homepage: https://ag-ui.com
- awesome-repositories: https://awesome-repositories.com/repository/ag-ui-protocol-ag-ui.md

## Topics

`ag-ui-protocol` `agent-frontend` `agent-ui` `agentic-workflow` `ai-agents`

## Description

ag-ui is an agent-frontend interoperability layer and communication protocol designed to connect AI agent backends with web and mobile user interfaces. It provides a standardized event-driven framework for exchanging messages, session state, and tool calls, utilizing a generative UI framework to render dynamic interface components and structured content triggered by an agent.

The project distinguishes itself through an SSE-based event streamer that delivers real-time incremental model responses and reasoning telemetry. It enables bi-directional state synchronization and allows remote agents to trigger local client-side tool execution for accessing device hardware or private data.

The system covers a broad range of capabilities including session and conversation context management, schema-driven tool integration, and human-in-the-loop coordination. It also provides protocol event inspection for debugging and supports API request authentication via bearer tokens, API keys, or basic authentication.

A command-line tool is available for project scaffolding to quickly establish connectivity between clients and servers.

## Tags

### Artificial Intelligence & ML

- [Agent-Frontend Integration Frameworks](https://awesome-repositories.com/f/artificial-intelligence-ml/agent-frontend-integration-frameworks.md) — Connects AI agent backends to web and mobile user interfaces using a standardized event-driven protocol.
- [Agent Communication Protocols](https://awesome-repositories.com/f/artificial-intelligence-ml/agent-communication-protocols.md) — Provides a standardized event-driven protocol connecting AI agent backends with user-facing applications. ([source](https://docs.ag-ui.com/))
- [Agent Event UI Mappings](https://awesome-repositories.com/f/artificial-intelligence-ml/agent-event-generators/agent-event-ui-mappings.md) — Maps structured agent events to dynamic frontend components to render real-time user interfaces.
- [Backend Base Frameworks](https://awesome-repositories.com/f/artificial-intelligence-ml/agent-integrations/backend-base-frameworks.md) — Provides a structured framework of base classes and message factories for building intelligent agent backends. ([source](https://github.com/ag-ui-protocol/ag-ui/blob/main/docs/sdk/java/overview.mdx))
- [Streaming Response Protocols](https://awesome-repositories.com/f/artificial-intelligence-ml/agentic-systems-frameworks/integration-deployment/agent-frameworks/agent-orchestrators/message-protocols/streaming-response-protocols.md) — Provides a mechanism to send messages to agent backends and receive real-time streaming updates on response content. ([source](https://github.com/ag-ui-protocol/ag-ui/blob/main/docs/sdk/kotlin/overview.mdx))
- [Frontend Interoperability Layers](https://awesome-repositories.com/f/artificial-intelligence-ml/ai-agent-frameworks/frontend-interoperability-layers.md) — Links custom agent backends to a standardized communication layer for seamless frontend interoperability. ([source](https://docs.ag-ui.com/))
- [Agent-Triggered UI Components](https://awesome-repositories.com/f/artificial-intelligence-ml/ai-ui-generators/agent-triggered-ui-components.md) — Creates dynamic user interface components that are triggered and updated in real time by an AI agent.
- [Client-Side Tool Execution](https://awesome-repositories.com/f/artificial-intelligence-ml/client-side-tool-execution.md) — Allows remote agents to trigger local functions on the user device for hardware or data access.
- [Context Memory Management](https://awesome-repositories.com/f/artificial-intelligence-ml/context-memory-management.md) — Manages application state and interaction history to maintain context across AI chat sessions. ([source](https://docs.ag-ui.com/quickstart/clients))
- [Conversation Context Tracking](https://awesome-repositories.com/f/artificial-intelligence-ml/conversation-context-tracking.md) — Transmits conversation history to the backend to enable context-aware multi-turn interactions. ([source](https://github.com/ag-ui-protocol/ag-ui/blob/main/docs/sdk/kotlin/overview.mdx))
- [Conversation State Management](https://awesome-repositories.com/f/artificial-intelligence-ml/conversation-state-management.md) — Synchronizes chat history and application context between frontend and backend for session continuity.
- [Event-Driven Agent Interfaces](https://awesome-repositories.com/f/artificial-intelligence-ml/event-driven-ai-workflows/event-driven-agent-interfaces.md) — Provides a framework for connecting agent backends to interfaces using unified message factories and base classes.
- [External Tool Integration](https://awesome-repositories.com/f/artificial-intelligence-ml/external-tool-integration.md) — Connects agents to functional tools with defined input and output schemas to perform real-world tasks. ([source](https://docs.ag-ui.com/quickstart/clients))
- [Local Tool Execution](https://awesome-repositories.com/f/artificial-intelligence-ml/local-ai-execution-environments/local-tool-execution.md) — Executes functions on the client device in response to agent requests to access local hardware or private data. ([source](https://github.com/ag-ui-protocol/ag-ui/blob/main/docs/sdk/kotlin/overview.mdx))
- [Model Response Streaming](https://awesome-repositories.com/f/artificial-intelligence-ml/model-response-parsers/model-response-aggregation/model-response-streaming.md) — Delivers model output through start, content, and end events for real-time user visibility. ([source](https://docs.ag-ui.com/quickstart/clients))
- [Agent Response Streams](https://awesome-repositories.com/f/artificial-intelligence-ml/multimodal-agent-capabilities/real-time-streaming/agent-response-streams.md) — Streams AI agent responses and reasoning telemetry incrementally for real-time client visibility.
- [Frontend Tool Bindings](https://awesome-repositories.com/f/artificial-intelligence-ml/external-tool-integrations/mcp-protocol-integrations/agent-tool-integrations/frontend-tool-bindings.md) — Directly connects agent capabilities to frontend-side tools to enhance the user experience. ([source](https://cdn.jsdelivr.net/gh/ag-ui-protocol/ag-ui@main/README.md))
- [Human-in-the-Loop Workflows](https://awesome-repositories.com/f/artificial-intelligence-ml/human-in-the-loop-workflows.md) — Coordinates interactions where humans provide real-time feedback or approval for automated agent actions. ([source](https://cdn.jsdelivr.net/gh/ag-ui-protocol/ag-ui@main/README.md))
- [Agent Activity Synchronization](https://awesome-repositories.com/f/artificial-intelligence-ml/mcp-servers/remote-connectivity/server-connections/agent-activity-synchronization.md) — Enables real-time event streaming from remote servers to synchronize agent activity with a local application. ([source](https://github.com/ag-ui-protocol/ag-ui/blob/main/docs/sdk/java/overview.mdx))

### Networking & Communication

- [Agent-Client Communication Protocols](https://awesome-repositories.com/f/networking-communication/agent-client-communication-protocols.md) — Implements a standardized event-driven communication protocol for connecting user applications to AI agent backends. ([source](https://docs.ag-ui.com/quickstart/clients))
- [Bi-Directional State Synchronizations](https://awesome-repositories.com/f/networking-communication/bi-directional-state-synchronizations.md) — Maintains consistent application state between the backend agent and frontend UI through a continuous event stream.
- [SSE-Based](https://awesome-repositories.com/f/networking-communication/communication-protocols-architectures/communication-protocols-standards/transport-protocols/http-transports/sse-based.md) — Uses Server-Sent Events to stream real-time model responses and agent telemetry from server to client.
- [Real-time Event Streams](https://awesome-repositories.com/f/networking-communication/real-time-event-streams.md) — Implements bidirectional event streaming between backends and frontends for exchanging messages and state. ([source](https://github.com/ag-ui-protocol/ag-ui/blob/main/docs/sdk/java/overview.mdx))
- [Server-Sent Events](https://awesome-repositories.com/f/networking-communication/server-sent-events.md) — Uses Server-Sent Events to deliver real-time streaming updates and incremental model responses.
- [Agent SSE Connection Management](https://awesome-repositories.com/f/networking-communication/sse-session-management/sse-connection-lifecycle-events/agent-sse-connection-management.md) — Provides SSE connectivity with automatic reconnection, timeout handling, and authentication for agent connections. ([source](https://github.com/ag-ui-protocol/ag-ui/blob/main/docs/sdk/go/overview.mdx))

### Data & Databases

- [Agent Event Schemas](https://awesome-repositories.com/f/data-databases/data-processing-pipelines/stream-processing-systems/data-streaming/structured-event-streams/agent-event-schemas.md) — Establishes common event structures for text messages and tool calls to ensure consistent interactions. ([source](https://cdn.jsdelivr.net/gh/ag-ui-protocol/ag-ui@main/README.md))
- [Structured Event Streams](https://awesome-repositories.com/f/data-databases/data-processing-pipelines/stream-processing-systems/data-streaming/structured-event-streams.md) — Delivers rich, event-driven structured data from agent backends to clients for real-time interaction. ([source](https://docs.ag-ui.com/quickstart/applications))

### Development Tools & Productivity

- [Client-Side Tool Execution Bridges](https://awesome-repositories.com/f/development-tools-productivity/terminal-shell-cli/cli-tooling-frameworks/cli-tooling/agent-integration-interfaces/agent-to-server-bridges/client-side-tool-execution-bridges.md) — Synchronizes application state and executes local client-side tools in response to remote agent requests.
- [Session Context Provisioning](https://awesome-repositories.com/f/development-tools-productivity/code-completion-tools/ai-context-completions/session-context-provisioning.md) — Injects current application state and user data into the agent context during active sessions. ([source](https://cdn.jsdelivr.net/gh/ag-ui-protocol/ag-ui@main/README.md))

### Software Engineering & Architecture

- [Tool Schema Mappings](https://awesome-repositories.com/f/software-engineering-architecture/schema-mapping-tools/tool-schema-mappings.md) — Translates function signatures into JSON schemas to connect agent backends with executable tools.
- [Event-Driven Architectures](https://awesome-repositories.com/f/software-engineering-architecture/event-driven-architectures.md) — Implements a standardized system of typed events that synchronizes agent state and user interactions.

### User Interface & Experience

- [Agent Protocol Client Interfaces](https://awesome-repositories.com/f/user-interface-experience/agent-protocol-client-interfaces.md) — Provides the interface compatibility layer for web and mobile applications to consume standardized agent event protocols. ([source](https://docs.ag-ui.com/))
- [Generative UI](https://awesome-repositories.com/f/user-interface-experience/state-management/generative-ui.md) — Renders dynamic user interface components and structured content triggered by the AI agent. ([source](https://cdn.jsdelivr.net/gh/ag-ui-protocol/ag-ui@main/README.md))

### Web Development

- [Generative UI Frameworks](https://awesome-repositories.com/f/web-development/generative-ui-frameworks.md) — Offers a system for rendering dynamic user interface components triggered by an AI agent during conversation.

### System Administration & Monitoring

- [Reasoning Chain Visualizers](https://awesome-repositories.com/f/system-administration-monitoring/reasoning-chain-visualizers.md) — Captures and displays internal thinking process events to visualize the agent's reasoning steps in real time. ([source](https://github.com/ag-ui-protocol/ag-ui/blob/main/docs/sdk/kotlin/overview.mdx))