#2828th of 118 in Agent frameworks and SDKs
ag-ui
Event-based protocol connecting agent backends to user-facing apps
- Stars
- 17.1k
- License
- MIT
- Last commit
- Nov 2026
- Last release
- Nov 2026
- Language
- TypeScript
12,986 on 21 Apr 202617,116 on 10 Nov 2026
From GitHub's daily star counts.
Checked on GitHub.
Overview
AG-UI defines about 16 standard event types that agent backends emit during a run, plus a simple input format, so front-ends can render streaming chat, shared state, generative UI and frontend tool calls. It works over any transport (SSE, WebSockets, webhooks) and ships a reference HTTP implementation and a default connector. Integrations cover LangGraph, CrewAI, Microsoft Agent Framework, Google ADK, Mastra, Pydantic AI and others.
Who it is for: Developers wiring agent backends into web or mobile front-ends
Strengths
- Transport-agnostic: SSE, WebSockets or webhooks, with loose event format matching
- Many framework integrations: LangGraph, CrewAI, Google ADK, Mastra, Pydantic AI, Agno
- Community SDKs for Kotlin, Go, Dart, Java, Rust, Ruby, C++ and .NET
- Dojo viewer shows each building block in 50-200 lines of code
Weaknesses
- A protocol, not an agent runtime; you still need an agent framework and a UI client
- OpenAI Agents SDK, AWS Bedrock Agents, Nim, Flowise and Langflow integrations are still in progress
- Docs and many integrations are hosted under CopilotKit, tying the ecosystem to one vendor
- Non-TypeScript SDKs are listed as community-maintained
What it needs
- no GPU
- Needs Node.js (npx create-ag-ui-app), An agent framework or backend
Quick answers
Is ag-ui open source?
Yes. Its code is on GitHub under the MIT license.
Does ag-ui need a GPU?
No, it runs without one.
Also in Agent frameworks and SDKs
See all 118| Rank | Project | Score |
|---|---|---|
| 1 | ppt-masterAgent skill that turns documents into natively editable PowerPoint decks | 95 out of 100 |
| 2 | openai-agents-pythonPython SDK for multi-agent workflows with handoffs, guardrails and tracing | 91 out of 100 |
| 3 | mastraTypeScript framework for building AI agents, workflows and MCP servers | 91 out of 100 |
| #4 | browser-usePython library that lets an LLM agent control a web browser | 90 out of 100 |
| #5 | copilotkitSDK for adding agent chat, generative UI and shared state to apps | 90 out of 100 |