Merge branch 'main' into litebox-readme-update

Author: juanpabloCamus

.github/CODEOWNERS

@@ -1 +1 @@
-* @mme @ranst91 @ataibarkai @maxkorp @tylerslaton
+* @mme @ranst91 @ataibarkai @maxkorp @tylerslaton @NathanTarbert

CONTRIBUTING.md

@@ -1,57 +1,71 @@
-# Contributing to AG-UI
+# 👋 Contributing to AG-UI
 
-Thanks for your interest in improving **AG-UI**!
+Thanks for checking out AG-UI! Whether you’re here to fix a bug, ship a feature, improve the docs, or just figure out how things work—we’re glad you’re here.
 
-This short guide shows the fastest way to get your idea merged.
-You can find more detailed contribution guides at [ag-ui.com](ag-ui.com) 
+Here’s how to get involved:
 
 ---
 
-## 1. Start a Discussion
+## 🤔 Have a Question or Ran Into Something?
 
-Before writing code, open a new **Discussion** and briefly cover:
+Pick the right spot so we can help you faster:
 
-1. **Problem** – what you’re trying to solve.
-2. **Proposal** – how you plan to solve it (code, docs, design, etc.).
-3. **Alternatives** – other options you considered.
-
-Early feedback keeps everyone aligned and saves re-work.
+- **🐛 Bugs / Feature Ideas** → [GitHub Issues](https://github.com/ag-ui-protocol/ag-ui/issues)  
+- **❓ "How do I...?" / General Questions** → [GitHub Discussions](https://github.com/ag-ui-protocol/ag-ui/discussions)  
+- **💬 Quick chats / casual stuff** → [Discord](https://discord.gg/Jd3FzfdJa8) → `#-💎-contributing`
 
 ---
 
-## 2. Join a Bi-Weekly Working Group
+## 🧑‍💻 Want to Contribute Code?
 
-Meet the team and potential collaborators in our [bi-weekly community call](https://lu.ma/calendar/manage/cal-DBw2gK428IQbiSO).
+1. **Find Something to Work On**  
+   Browse open issues on [GitHub](https://github.com/ag-ui-protocol/ag-ui/issues).  
+   Got your own idea? Open an issue first so we can start the discussion.
 
----
+2. **Ask to Be Assigned**  
+   Comment on the issue and tag a code owner:  
+   → [Code Owners](https://github.com/ag-ui-protocol/ag-ui/blob/main/.github/CODEOWNERS)
+
+3. **Get on the Roadmap**  
+   Once approved, you'll be assigned the issue, and it'll get added to our [roadmap](https://github.com/orgs/ag-ui-protocol/projects/1).
 
-## 3. Connect with the Maintainers
+4. **Coordinate With Others**  
+   - If you're collaborating or need feedback, start a thread in `#-💎-contributing` on Discord  
+   - Or just DM the assignee directly
 
-Need a quick sync?
+5. **Open a Pull Request**  
+   - When you’re ready, submit your PR  
+   - In the description, include: `Fixes #<issue-number>`  
+     (This links your PR to the issue and closes it automatically)
 
-- **Markus:** [@mme_xyz](https://twitter.com/mme_xyz) on X (Twitter)
-- **Book a chat:** <https://calendly.com/markus-copilotkit/ag-ui>
+6. **Review & Merge**  
+   - A maintainer will review your code and leave comments if needed  
+   - Once it’s approved, we’ll merge it and move the issue to “done.”
 
 ---
 
-## 4. Useful Resources & Docs
+## 📝 Want to Contribute to the Docs?
 
-| Resource                                  | Link                                                     |
-| ----------------------------------------- | -------------------------------------------------------- |
-| Learn how to connect to AG-UI with JS     | <https://docs.ag-ui.com/quickstart/connect>              |
-| Learn how to connect to AG-UI with Python | <https://docs.ag-ui.com/quickstart/build>                |
-| Dojo reference implementation             | <https://github.com/ag-ui-protocol/ag-ui/tree/main/dojo> |
+Docs are part of the codebase and super valuable—thanks for helping improve them!
 
----
+Here’s how to contribute:
+
+1. **Open an Issue First**  
+   - Open a [GitHub issue](https://github.com/ag-ui-protocol/ag-ui/issues) describing what you’d like to update or add.  
+   - Then comment and ask to be assigned.
 
-## 5. Open Your Pull Request
+2. **Submit a PR**  
+   - Once assigned, make your edits and open a pull request.
+   - In the description, include: `Fixes #<issue-number>`  
+     (This links your PR to the issue and closes it automatically)
 
-1. **Fork** the repo and create a feature branch.
-2. Keep changes focused—one PR per feature or fix.
-3. Link back to your Discussion in the PR description.
+   - A maintainer will review it and merge if it looks good.
 
-We review PRs weekly. Feel free to nudge us in your Discussion if you haven’t heard back in a few days.
+That’s it! Simple and appreciated.
 
 ---
 
-**Thank you for making AG-UI better!**
+## 🙌 That’s It!
+
+AG-UI is community-built, and every contribution helps shape where we go next.  
+Big thanks for being part of it!

README.md

@@ -44,12 +44,12 @@ It also ships with a **reference HTTP implementation** and **default connector**
 AG-UI was developed based on real-world requirements and practical experience building in-app agent interactions.
 
 
-
 ## Where does AGUI fit in the agentic protocol stack?
 AG-UI is complementary to the other 2 top agentic protocols
 - MCP gives agents tools
 - A2A allows agents to communicate with other agents
 - AG-UI brings agents into user-facing applications
+
 
 ## 🚀 Features
 

python-sdk/README.md

@@ -1,5 +1,57 @@
-# Agent User Interaction Protocol Documentation
+# ag-ui-protocol
 
-The Python SDK for the [Agent User Interaction Protocol](https://ag-ui.com).
+Python SDK for the **Agent-User Interaction (AG-UI) Protocol**.
 
-For more information visit the [official documentation](https://docs.ag-ui.com/).
+`ag-ui-protocol` provides Python developers with strongly-typed data structures and event encoding for building AG-UI compatible agent servers. Built on Pydantic for robust validation and automatic camelCase serialization for seamless frontend integration.
+
+## Installation
+
+```bash
+pip install ag-ui-protocol
+poetry add ag-ui-protocol
+pipenv install ag-ui-protocol
+```
+
+## Features
+
+- 🐍 **Python-native** – Idiomatic Python APIs with full type hints and validation
+- 📋 **Pydantic models** – Runtime validation and automatic JSON serialization
+- 🔄 **Streaming events** – 16 core event types for real-time agent communication
+- ⚡ **High performance** – Efficient event encoding for Server-Sent Events
+
+## Quick example
+
+```python
+from ag_ui.core import TextMessageContentEvent, EventType
+from ag_ui.encoder import EventEncoder
+
+# Create a streaming text event
+event = TextMessageContentEvent(
+    type=EventType.TEXT_MESSAGE_CONTENT,
+    message_id="msg_123",
+    delta="Hello from Python!"
+)
+
+# Encode for HTTP streaming
+encoder = EventEncoder()
+sse_data = encoder.encode(event)
+# Output: data: {"type":"TEXT_MESSAGE_CONTENT","messageId":"msg_123","delta":"Hello from Python!"}\n\n
+```
+
+## Packages
+
+- **`ag_ui.core`** – Types, events, and data models for AG-UI protocol
+- **`ag_ui.encoder`** – Event encoding utilities for HTTP streaming
+
+## Documentation
+
+- Concepts & architecture: [`docs/concepts`](https://docs.ag-ui.com/concepts/architecture)
+- Full API reference: [`docs/sdk/python`](https://docs.ag-ui.com/sdk/python/core/overview)
+
+## Contributing
+
+Bug reports and pull requests are welcome! Please read our [contributing guide](https://docs.ag-ui.com/development/contributing) first.
+
+## License
+
+MIT © 2025 AG-UI Protocol Contributors

python-sdk/pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "ag-ui-protocol"
-version = "0.1.7"
+version = "0.1.8"
 description = ""
 authors = ["Markus Ecker <[email protected]>"]
 readme = "README.md"

typescript-sdk/integrations/agno/README.md

@@ -0,0 +1,36 @@
+# @ag-ui/agno
+
+Implementation of the AG-UI protocol for Agno.
+
+Connects Agno agents to frontend applications via the AG-UI protocol using HTTP communication.
+
+## Installation
+
+```bash
+npm install @ag-ui/agno
+pnpm add @ag-ui/agno
+yarn add @ag-ui/agno
+```
+
+## Usage
+
+```ts
+import { AgnoAgent } from "@ag-ui/agno";
+
+// Create an AG-UI compatible agent
+const agent = new AgnoAgent({
+  url: "https://your-agno-server.com/agent",
+  headers: { Authorization: "Bearer your-token" },
+});
+
+// Run with streaming
+const result = await agent.runAgent({
+  messages: [{ role: "user", content: "Hello from Agno!" }],
+});
+```
+
+## Features
+
+- **HTTP connectivity** – Direct connection to Agno agent servers
+- **Multi-agent support** – Works with Agno's multi-agent system architecture
+- **Streaming responses** – Real-time communication with full AG-UI event support

typescript-sdk/integrations/agno/package.json

@@ -1,13 +1,14 @@
 {
   "name": "@ag-ui/agno",
   "author": "Manu Hortet <[email protected]>",
-  "version": "0.0.1",
+  "version": "0.0.2",
   "main": "./dist/index.js",
   "module": "./dist/index.mjs",
   "types": "./dist/index.d.ts",
   "sideEffects": false,
   "files": [
-    "dist/**"
+    "dist/**",
+    "README.md"
   ],
   "private": false,
   "publishConfig": {

typescript-sdk/integrations/crewai/README.md

@@ -1,13 +1,44 @@
-# Server Starter
+# @ag-ui/crewai
 
-This starter kit demonstrates sending the minimal set of events that are needed to stream data from the agent to the frontend.
+Implementation of the AG-UI protocol for CrewAI.
 
-## Running the server
+Connects CrewAI Flows and Crews to frontend applications via the AG-UI protocol. Supports both TypeScript HTTP clients and Python FastAPI server integration with streaming crew execution.
 
-To run the server:
+## Installation
 
 ```bash
-cd typescript-sdk/integrations/server-starter/server/python
+npm install @ag-ui/crewai
+pnpm add @ag-ui/crewai
+yarn add @ag-ui/crewai
+```
+
+## Usage
+
+```ts
+import { CrewAIAgent } from "@ag-ui/crewai";
+
+// Create an AG-UI compatible agent
+const agent = new CrewAIAgent({
+  url: "http://localhost:8000/crew-endpoint",
+  headers: { "Content-Type": "application/json" },
+});
+
+// Run with streaming
+const result = await agent.runAgent({
+  messages: [{ role: "user", content: "Execute the research crew" }],
+});
+```
+
+## Features
+
+- **HTTP connectivity** – Connect to CrewAI FastAPI servers
+- **Flow & Crew support** – Works with both CrewAI Flows and traditional Crews
+- **Step tracking** – Real-time crew execution progress
+- **Python integration** – Full FastAPI server implementation included
 
+## To run the example server in the dojo
+
+```bash
+cd typescript-sdk/integrations/crewai/python
 poetry install && poetry run dev
 ```

typescript-sdk/integrations/crewai/package.json

@@ -1,13 +1,14 @@
 {
   "name": "@ag-ui/crewai",
   "author": "Markus Ecker <[email protected]>",
-  "version": "0.0.1",
+  "version": "0.0.2",
   "main": "./dist/index.js",
   "module": "./dist/index.mjs",
   "types": "./dist/index.d.ts",
   "sideEffects": false,
   "files": [
-    "dist/**"
+    "dist/**",
+    "README.md"
   ],
   "private": false,
   "publishConfig": {

typescript-sdk/integrations/crewai/python/README.md

@@ -0,0 +1,59 @@
+# ag-ui-crewai
+
+Implementation of the AG-UI protocol for CrewAI.
+
+Provides a complete Python integration for CrewAI flows and crews with the AG-UI protocol, including FastAPI endpoint creation and comprehensive event streaming.
+
+## Installation
+
+```bash
+pip install ag-ui-crewai
+```
+
+## Usage
+
+```python
+from crewai.flow.flow import Flow, start
+from litellm import completion
+from ag_ui_crewai import (
+    add_crewai_flow_fastapi_endpoint,
+    copilotkit_stream,
+    CopilotKitState
+)
+from fastapi import FastAPI
+
+class MyFlow(Flow[CopilotKitState]):
+    @start()
+    async def chat(self):
+        response = await copilotkit_stream(
+            completion(
+                model="openai/gpt-4o",
+                messages=[
+                    {"role": "system", "content": "You are a helpful assistant."},
+                    *self.state.messages
+                ],
+                tools=self.state.copilotkit.actions,
+                stream=True
+            )
+        )
+        self.state.messages.append(response.choices[0].message)
+
+# Add to FastAPI
+app = FastAPI()
+add_crewai_flow_fastapi_endpoint(app, MyFlow(), "/flow")
+```
+
+## Features
+
+- **Native CrewAI integration** – Direct support for CrewAI flows, crews, and multi-agent systems
+- **FastAPI endpoint creation** – Automatic HTTP endpoint generation with proper event streaming
+- **Predictive state updates** – Real-time state synchronization between backend and frontend
+- **Streaming tool calls** – Live streaming of LLM responses and tool execution to the UI
+
+## To run the dojo examples
+
+```bash
+cd python/ag_ui_crewai
+poetry install
+poetry run dev
+```