Back to packageRELEASE DETAILS

0.1.0

PyPI

agentpulse

AI Agent Observability SDK - Auto-instrument your AI agents with one line of code

Published2 Feb 2026

Direct dependencies7

Transitive dependenciesNot calculated

README

Version 0.1.0 documentation

AgentPulse

Open-source observability SDK for AI agents. Auto-instrument CrewAI, LangGraph, and more with one line of code.

Install

pip install agentpulse

With framework extras:

pip install agentpulse[crewai]
pip install agentpulse[langgraph]
pip install agentpulse[all]

Quick Start

import agentpulse
agentpulse.init()  # Auto-detects and instruments CrewAI, LangGraph

from crewai import Agent, Task, Crew
# Your existing code works unchanged — fully traced

What it captures

Agent steps: Which agent ran, with what goal
Task execution: Task descriptions, expected vs actual output
Tool calls: Tool name, input, output
LLM calls: Model, tokens, cost, latency
Decisions: Agent routing and choices

Manual instrumentation

from agentpulse import trace, tool

@trace(name="my-agent-step")
def process_data(data):
    ...

@tool(name="search")
def search_web(query: str):
    ...

Dashboard

AgentPulse comes with a full web dashboard. See the main repo for setup instructions.

License

Apache 2.0

Downloads & popularity

Awaiting observations

No metric observations yet

Download counts and popularity will appear here as the collector receives them.

Declared dependencies 9

Native requirements

7 direct targetsNot calculated transitive count

Package / target	Requirement	Relationship
httpx Environment { "extras": "", "marker": null, "requires_python": ">=3.10", "evaluation": "NOT_EVALUATED" }	`httpx>=0.27`	runtime
pydantic Environment { "extras": "", "marker": null, "requires_python": ">=3.10", "evaluation": "NOT_EVALUATED" }	`pydantic>=2.0`	runtime
wrapt Environment { "extras": "", "marker": null, "requires_python": ">=3.10", "evaluation": "NOT_EVALUATED" }	`wrapt>=1.16`	runtime
crewai Environment { "extras": "", "marker": "extra == \"all\"", "requires_python": ">=3.10", "evaluation": "NOT_EVALUATED" }	`crewai>=0.80; extra == "all"`	runtime
langgraph Environment { "extras": "", "marker": "extra == \"all\"", "requires_python": ">=3.10", "evaluation": "NOT_EVALUATED" }	`langgraph>=0.2; extra == "all"`	runtime
crewai Environment { "extras": "", "marker": "extra == \"crewai\"", "requires_python": ">=3.10", "evaluation": "NOT_EVALUATED" }	`crewai>=0.80; extra == "crewai"`	runtime
pytest Environment { "extras": "", "marker": "extra == \"dev\"", "requires_python": ">=3.10", "evaluation": "NOT_EVALUATED" }	`pytest; extra == "dev"`	runtime
pytest-asyncio Environment { "extras": "", "marker": "extra == \"dev\"", "requires_python": ">=3.10", "evaluation": "NOT_EVALUATED" }	`pytest-asyncio; extra == "dev"`	runtime
langgraph Environment { "extras": "", "marker": "extra == \"langgraph\"", "requires_python": ">=3.10", "evaluation": "NOT_EVALUATED" }	`langgraph>=0.2; extra == "langgraph"`	runtime