mirror of
https://github.com/crewAIInc/crewAI.git
synced 2026-07-03 22:19:27 +00:00
Flow declarations can now reference full repository-backed Agent config
without duplicating it inline. The repository response is merged the same
way as `Agent(from_repository=...)`, so values like `role`, `goal`,
`backstory`, `tools`, `planning_config`, deprecated `reasoning`, `memory`,
and other Agent fields can come from the repository. Local YAML fields
still override repository values.
Standalone agent action:
```yaml
do:
call: agent
with:
from_repository: support_specialist
input: "${state.question}"
```
Inline crew agent:
```yaml
do:
call: crew
with:
name: inline_research
agents:
researcher:
from_repository: researcher
tasks:
- description: Research {topic}
expected_output: Findings about {topic}
agent: researcher
```
crewai-cli
CLI for CrewAI — scaffold, run, deploy and manage AI agent crews without installing the full framework.
Installation
pip install crewai-cli
This pulls in crewai-core (shared utilities) but not the crewai framework
itself, so commands that don't need a crew loaded — crewai version,
crewai login, crewai org list, crewai config *, crewai traces *,
crewai create, crewai template * — work standalone.
Commands that load a user's crew or flow (crewai run, crewai train,
crewai test, crewai chat, crewai replay, crewai reset-memories,
crewai deploy push, crewai tool publish) require crewai to be installed
in the project's environment. They print a clear error if it is missing.
To install both at once:
pip install crewai[cli]