Skip to main content
Source Code: src/gaia/agents/chat/, src/gaia/agents/docker/, src/gaia/agents/jira/, src/gaia/agents/blender/
Import: from gaia.agents.chat.agent import ChatAgent

​
12.1 ChatAgent (Conversational AI with RAG)

Detailed Spec: spec/chat-agent Purpose: General-purpose conversational agent with file operations, RAG, and shell command capabilities. 
from gaia.agents.chat.agent import ChatAgent

# Create chat agent with RAG enabled
agent = ChatAgent(
    documents_path="./docs",  # Auto-index PDFs in this directory
    silent_mode=False
)

# 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.agents.docker.agent import DockerAgent Detailed Spec: spec/docker-agent Purpose: Intelligent Docker assistance for containerizing applications with LLM-generated Dockerfiles. 
from gaia.agents.docker.agent import DockerAgent
from pathlib import Path

# Create Docker agent
agent = DockerAgent(
    model_id="Qwen3-Coder-30B-A3B-Instruct-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.agents.jira.agent import JiraAgent Detailed Spec: spec/jira-agent Purpose: Natural language interface to Jira with automatic configuration discovery and JQL generation. 
from gaia.agents.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.agents.blender.agent import BlenderAgent Detailed Spec: spec/blender-agent Purpose: Natural language interface for Blender 3D modeling, scene creation, and rendering. 
from gaia.agents.blender.agent import BlenderAgent

# Create Blender agent
agent = BlenderAgent(
    model_id="Qwen3-Coder-30B-A3B-Instruct-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