agentmetrics-crewai
AgentMetrics integration for CrewAI. Instantiate the listener once at startup and every crew.kickoff() reports back to your dashboard automatically showing latency, cost, token counts, tool calls, and errors, with zero changes to your crew code.
Install
pip install agentmetrics-crewai
Quickstart
from agentmetrics_crewai import AgentMetricsListener
# register once at startup, covers all crews in the process
AgentMetricsListener(
agent_id="my-crew",
base_url="http://localhost:8099",
)
# Run your crew as normal
result = MyCrew().kickoff()
API
AgentMetricsListener(agent_id, base_url)
| Parameter | Default | Description |
|---|---|---|
agent_id |
"crewai-agent" |
Fallback label if the crew has no crew_name |
base_url |
"http://localhost:8099" |
AgentMetrics server address |
Instantiating the class auto-registers event handlers on the global crewai_event_bus with no further setup needed, and the listener handles concurrent kickoffs correctly via source_fingerprint tracking.
.flush(timeout=10.0)
Blocks until all in-flight HTTP requests complete. Call before process exit in scripts.
What gets tracked
Each kickoff() call emits one event to /v1/events on completion or failure:
| Field | Description |
|---|---|
status |
success or failed |
duration_ms |
Wall-clock kickoff duration |
input_tokens / output_tokens |
Aggregated across all LLM calls |
cache_read_tokens / cache_write_tokens |
Cache token counts |
llm_calls |
Number of LLM requests in the kickoff |
tool_calls / tool_errors |
Tool usage counts |
tool_names |
Set of tools invoked |
model |
Model name from the first LLM call |
estimated_cost_usd |
Computed from token counts and model pricing |
error |
First 500 chars of the error message on failure |
License
Metadata
Release files for agentmetrics-crewai 0.2.0
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | |
|---|---|---|---|
| agentmetrics_crewai-0.2.0.tar.gz | 3.9 kB | Details |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Reset |
|---|---|---|---|---|
| agentmetrics_crewai-0.2.0-py3-none-any.whl | Python 3 | none | any | Details |
Total release size: 8.3 kB
Release files / agentmetrics_crewai-0.2.0.tar.gz
| Download URL | agentmetrics_crewai-0.2.0.tar.gz |
|---|---|
| Size | 3.9 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
a73122745cd66778fceb0e6c6a2ebf9cd68b053d724931865cd9693be09efc5f
|
|
BLAKE2b-256 checksum How to use checksums |
2c449a67eff16c22046737789b1c2ccd59c2f548259f096cd853ef9ff90ea833
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.2.0 CPython/3.13.5
|
Release files / agentmetrics_crewai-0.2.0-py3-none-any.whl
| Download URL | agentmetrics_crewai-0.2.0-py3-none-any.whl |
|---|---|
| Size | 4.4 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
9dea8b4f02ac4fe8d3b381cb56ee55d6cb4b131aee0a1408db5458cae0a7f651
|
|
BLAKE2b-256 checksum How to use checksums |
521a76a084d4b640cef7414dec342ee634155640fb7fa44e77b428559b3d4062
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.2.0 CPython/3.13.5
|