Edit the crew.py file to add tools, LLM, or other parameters to a specific agent.

This tool modifies the agent method in crew.py to include custom tools, LLM configuration, or other agent parameters that can't be set via YAML alone.

Args: project_name: Name of the project agent_name: Name of the agent method to modify (e.g., 'researcher') tools: List of tool import strings (e.g., ['SerperDevTool()', 'WebsiteSearchTool()']) llm: LLM model string (e.g., 'gpt-4o', 'claude-3-5-sonnet') function_calling_llm: Function calling LLM model string other_params: Additional parameters to pass to the Agent constructor

Generate an HTML visualization of a Flow project.

Runs crewai flow plot which outputs an interactive HTML file mapping out the flow states and transitions.

Execute a Flow project using the Python API.

This runs the flow directly using the Python API (flow.kickoff(inputs=...)) instead of the CLI, ensuring proper tool execution and avoiding interactive prompts.

Query the internal CrewAI documentation RAG engine.

Use this when you need to look up how to use a specific CrewAI feature, tool, or pattern. It searches the official documentation and returns relevant snippets with their source URIs.

Manage CrewAI memory for a specific project.

Use 'reset' to run crewai reset-memories (requires --all flag or specific options). Use 'status' to check if the project has memory enabled.

Test the crew's performance and evaluate outputs.

Runs crewai test -n {iterations} -m {model}. This helps in assessing the quality of the crew's execution.

Train the crew to improve performance.

Runs crewai train -n {iterations} -f {filename}. Agent training provides human-in-the-loop feedback to optimize prompts.

Replay a crew execution from a specific task.

Runs crewai replay -t {task_id}. Useful for debugging and retrying specific failed tasks.

Create a new CrewAI project using the official CLI.

This generates the standard scaffolding for a CrewAI project, including pyproject.toml, src directory, yaml configs, and entry points. The project is created inside the configured CrewAI workspace.

Note: The --skip_provider flag is used to avoid interactive prompts. You will need to manually configure the provider API keys in the project's .env file.

Install project dependencies.

Runs crewai install inside the project directory and optionally installs additional packages (e.g., specific crewai-tools).

Read the structure and core configurations of a CrewAI project.

Returns the pyproject.toml dependencies, available YAML configs, and Python source files to understand the current state of the project.