Documentation Index
Fetch the complete documentation index at: https://docs.praison.ai/llms.txt
Use this file to discover all available pages before exploring further.
Claude Code Integration
PraisonAI provides seamless integration with Anthropic’s Claude Code CLI, supporting both subprocess-based execution and the official Python SDK.
Installation
CLI Installation
# Install Claude Code CLI
curl -fsSL https://claude.ai/install.sh | bash
# Verify installation
claude --version
SDK Installation (Optional)
# Install the Python SDK for enhanced features
pip install claude-agent-sdk
Quick Start
from praisonai.integrations import ClaudeCodeIntegration
# Create integration
claude = ClaudeCodeIntegration(
workspace="/path/to/project",
output_format="json",
skip_permissions=True
)
# Execute a coding task
result = await claude.execute("Refactor the auth module")
print(result)
Configuration Options
| Option | Type | Default | Description |
|---|
workspace | str | ”.” | Working directory for CLI execution |
timeout | int | 300 | Timeout in seconds |
output_format | str | ”json” | Output format: “json”, “text”, “stream-json” |
skip_permissions | bool | True | Skip permission prompts |
system_prompt | str | None | Custom system prompt to append |
allowed_tools | list | None | List of allowed tools |
disallowed_tools | list | None | List of disallowed tools |
use_sdk | bool | False | Use SDK instead of subprocess |
model | str | None | Model to use (e.g., “sonnet”, “opus”) |
Examples
Basic Execution
from praisonai.integrations import ClaudeCodeIntegration
claude = ClaudeCodeIntegration(workspace="/project")
# Simple task
result = await claude.execute("Add error handling to main.py")
print(result)
With System Prompt
claude = ClaudeCodeIntegration(
workspace="/project",
system_prompt="You are a Python expert. Follow PEP 8 guidelines."
)
result = await claude.execute("Refactor the utils module")
claude = ClaudeCodeIntegration(
workspace="/project",
allowed_tools=["Read", "Write"], # Only allow file operations
disallowed_tools=["Bash"] # Disable shell commands
)
result = await claude.execute("Update the config file")
Session Continuation
claude = ClaudeCodeIntegration(workspace="/project")
# First request
result1 = await claude.execute("Read main.py and understand the structure")
# Continue the session
result2 = await claude.execute(
"Now refactor the function we discussed",
continue_session=True
)
# Reset session
claude.reset_session()
Using the SDK
claude = ClaudeCodeIntegration(
workspace="/project",
use_sdk=True # Use claude-agent-sdk if available
)
# Check if SDK is available
print(f"SDK available: {claude.sdk_available}")
result = await claude.execute("Complex refactoring task")
Streaming Output
claude = ClaudeCodeIntegration(workspace="/project")
async for event in claude.stream("Add comprehensive tests"):
event_type = event.get("type")
if event_type == "assistant":
print(f"Assistant: {event.get('content')}")
elif event_type == "tool_use":
print(f"Using tool: {event.get('name')}")
elif event_type == "result":
print(f"Result: {event.get('content')}")
from praisonai import Agent
from praisonai.integrations import ClaudeCodeIntegration
claude = ClaudeCodeIntegration(
workspace="/project",
skip_permissions=True
)
# Create tool
tool = claude.as_tool()
# Use with agent
agent = Agent(
name="Code Assistant",
role="Software Developer",
goal="Help with coding tasks",
tools=[tool]
)
result = agent.start("Refactor the authentication module")
Environment Variables
# API Key (required)
export ANTHROPIC_API_KEY=your-key
# or
export CLAUDE_API_KEY=your-key
# Optional: Set default workspace
export PRAISONAI_CODE_REPO_PATH=/path/to/project
CLI Flags Used
The integration uses the following Claude Code CLI flags:
| Flag | Description |
|---|
-p | Print mode (headless) |
--output-format json | JSON output for parsing |
--continue | Continue previous session |
--dangerously-skip-permissions | Skip permission prompts |
--append-system-prompt | Add custom system prompt |
--allowedTools | Restrict available tools |
--disallowedTools | Disable specific tools |
--model | Select model (sonnet, opus) |
Error Handling
from praisonai.integrations import ClaudeCodeIntegration
claude = ClaudeCodeIntegration(timeout=60)
try:
result = await claude.execute("Complex task")
except TimeoutError:
print("Task timed out after 60 seconds")
except Exception as e:
print(f"Error: {e}")
Best Practices
- Use JSON output for programmatic processing
- Set appropriate timeouts for complex tasks
- Use tool restrictions for security
- Enable SDK for enhanced features when available
- Use session continuation for multi-step tasks
