Self-healing telemetry proxy SDK for AI Agents
Project description
AgentPulse SDK ⚡
The official, zero-dependency Python client package for connecting applications to AgentPulse—the self-healing telemetry proxy engine built specifically for autonomous AI Agent workflows.
Installation
pip install agentpulse-sdk
Quick Start Implementation
Wrap your core asynchronous API endpoint listener routines with our performance monitoring wrapper decorator:
import asyncio
from agentpulse_sdk.interceptor import monitor_agent_webhook
# The decorator automatically catches schema changes and triggers AI self-healing
@monitor_agent_webhook(provider="stripe", agentpulse_key="your_active_token_here")
async def handle_incoming_transaction(payload: dict):
print(f"Executing agent workflows safely with clean data structures: {payload}")
Resilience Architecture
If your upstream integration endpoint falls offline or returns an unexpected schema payload variant format, our SDK drops back to a native exception recovery mode. Your core execution loop will never fail.
Features
- Zero Dependencies: Only requires
httpxfor async HTTP - Fail-Safe Design: Never crashes your application
- Async-Native: Built for FastAPI, asyncio workflows
- Type-Safe: Full type hints support
- Production Ready: Battle-tested in real AI agent deployments
Documentation
For complete setup and advanced usage, visit the main repository.
License
MIT License - see LICENSE for details.
Project details
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distributions
Built Distribution
Filter files by name, interpreter, ABI, and platform.
If you're not sure about the file name format, learn more about wheel file names.
Copy a direct link to the current filters
File details
Details for the file agentpulse_telemetry-1.0.0-py3-none-any.whl.
File metadata
- Download URL: agentpulse_telemetry-1.0.0-py3-none-any.whl
- Upload date:
- Size: 4.4 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/6.2.0 CPython/3.9.6
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
ec2a82bd76c2ca25f3bc9ae67e82b5e6011777dca5ef148f1b4743d2e68523a5
|
|
| MD5 |
e574b6d486873261456880b414ca74c6
|
|
| BLAKE2b-256 |
7b351ff6037b67cbe6c7896149f7e8b9142182803f1891987ea54628e72ce79f
|