> ## Documentation Index
> Fetch the complete documentation index at: https://amd-gaia.ai/docs/llms.txt
> Use this file to discover all available pages before exploring further.

# Specialized

<Info>
  **Source Code:** [`hub/agents/python/chat/gaia_agent_chat/`](https://github.com/amd/gaia/blob/main/hub/agents/python/chat/gaia_agent_chat/), [`hub/agents/python/docker/gaia_agent_docker/`](https://github.com/amd/gaia/blob/main/hub/agents/python/docker/gaia_agent_docker/), [`hub/agents/python/jira/gaia_agent_jira/`](https://github.com/amd/gaia/blob/main/hub/agents/python/jira/gaia_agent_jira/), [`hub/agents/python/blender/gaia_agent_blender/`](https://github.com/amd/gaia/blob/main/hub/agents/python/blender/gaia_agent_blender/)
</Info>

<Note>
  **Import:** `from gaia_agent_chat.agent import ChatAgent`
</Note>

***

## 12.1 ChatAgent (Conversational AI with RAG)

**Detailed Spec:** [spec/chat-agent](/docs/spec/chat-agent)

**Purpose:** General-purpose conversational agent with file operations, RAG, and shell command capabilities.

```python theme={null}
from gaia_agent_chat.agent import ChatAgent, ChatAgentConfig

# Configure the chat agent (use ChatAgentConfig; ChatAgent takes a single
# `config` argument rather than loose kwargs)
config = ChatAgentConfig(
    rag_documents=["./docs/user_manual.pdf"],  # Auto-index these paths
    silent_mode=False,
)
agent = ChatAgent(config)

# Agent has built-in tools:
# - File operations (read/write/list)
# - Document search (RAG)
# - Shell commands

result = agent.process_query(
    "What does the user manual say about configuration? "
    "Then create a config.yaml file with those settings."
)

# Agent automatically:
# 1. Searches indexed documents
# 2. Extracts configuration info
# 3. Creates the file with proper settings
```

***

## 12.2 DockerAgent (Containerization)

**Import:** `from gaia_agent_docker.agent import DockerAgent`

**Detailed Spec:** [spec/docker-agent](/docs/spec/docker-agent)

**Purpose:** Intelligent Docker assistance for containerizing applications with LLM-generated Dockerfiles.

```python theme={null}
from gaia_agent_docker.agent import DockerAgent
from pathlib import Path

# Create Docker agent
agent = DockerAgent(
    model_id="Qwen3.5-35B-A3B-GGUF",
    max_steps=10,
    allowed_paths=["/home/user/projects"]  # Security: restrict access
)

# Analyze app and generate Dockerfile
result = agent.process_query(
    "Analyze this Python Flask app and create an optimized Dockerfile"
)

# Agent:
# 1. Analyzes app structure (finds requirements.txt, main.py, etc.)
# 2. Detects dependencies and runtime needs
# 3. Generates production-ready Dockerfile
# 4. Suggests best practices (multi-stage builds, security)

# Build and run
result = agent.process_query(
    "Build the Docker image and run it on port 5000"
)
```

***

## 12.3 JiraAgent (Issue Tracking)

**Import:** `from gaia_agent_jira.agent import JiraAgent`

**Detailed Spec:** [spec/jira-agent](/docs/spec/jira-agent)

**Purpose:** Natural language interface to Jira with automatic configuration discovery and JQL generation.

```python theme={null}
from gaia_agent_jira.agent import JiraAgent
import os

# Set credentials
os.environ["ATLASSIAN_SITE_URL"] = "https://company.atlassian.net"
os.environ["ATLASSIAN_API_KEY"] = "your-api-token"
os.environ["ATLASSIAN_USER_EMAIL"] = "you@company.com"

# Create Jira agent with auto-discovery
agent = JiraAgent()
config = agent.initialize()  # Discovers projects, issue types, etc.

# Natural language queries
result = agent.process_query(
    "Show me all high priority bugs assigned to me"
)

# Create issues
result = agent.process_query(
    "Create a new story called 'Add user authentication' in the AUTH project"
)

# Update issues
result = agent.process_query(
    "Update PROJ-123 status to In Progress and add comment 'Working on it'"
)

# Agent features:
# - Automatic Jira instance discovery
# - Natural language to JQL translation
# - Handles project names, issue types, statuses
# - Robust error handling
```

***

## 12.4 BlenderAgent (3D Graphics)

**Import:** `from gaia_agent_blender.agent import BlenderAgent`

**Detailed Spec:** [spec/blender-agent](/docs/spec/blender-agent)

**Purpose:** Natural language interface for Blender 3D modeling, scene creation, and rendering.

```python theme={null}
from gaia_agent_blender.agent import BlenderAgent

# Create Blender agent
agent = BlenderAgent(
    model_id="Qwen3.5-35B-A3B-GGUF"
)

# Natural language 3D modeling
result = agent.process_query(
    "Create a blue sphere at position (0, 0, 5) with radius 2"
)

# Complex scenes
result = agent.process_query(
    "Create a simple room with a table and chair. "
    "Add a camera looking at the table. "
    "Render the scene with good lighting."
)

# Agent capabilities:
# - Object creation (cubes, spheres, meshes)
# - Material/texture application
# - Camera and lighting setup
# - Scene composition
# - Rendering operations
```

***

## Related Topics

* [Core Agent System](../core/agent-system) - Learn about the base Agent class
* [Routing Agent](./routing) - Multi-agent orchestration
* [Tool Mixins](../mixins/tool-mixins) - Reusable tool collections
* [Code Development Mixins](../mixins/code-mixins) - Code-specific tools

***

<small style="color: #666;">
  **License**

  Copyright(C) 2024-2026 Advanced Micro Devices, Inc. All rights reserved.

  SPDX-License-Identifier: MIT
</small>