Back to packageRELEASE DETAILS

0.3.0

PyPI

agentrx-sdk

Production recovery layer for AI agents — classifies tool failures and returns actionable recovery instructions.

Published29 Apr 2026

Direct dependencies7

Transitive dependenciesNot calculated

README

Version 0.3.0 documentation

agentrx-python

Make your AI agents bulletproof in two lines.

Installation

pip install agentrx-sdk

Quick Start

from agentrx import with_recovery

@with_recovery(api_key="your_key", agent_id="my_agent") async def call_my_tool(payload: dict) -> dict: return await some_api.call(payload)

When call_my_tool raises an exception, AgentRx diagnoses it and automatically retries, corrects the payload, or tells you exactly what went wrong.

Environment Variables

AGENTRX_API_KEY — Your API key (required) AGENTRX_BASE_URL — AgentRx server URL (default: http://localhost:8000) OTEL_TRACE_ID — OpenTelemetry trace ID (optional) LANGSMITH_RUN_ID — LangSmith run ID (optional)

License

MIT

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>=0.27.0`	runtime
pydantic Environment { "extras": "", "marker": null, "requires_python": ">=3.10", "evaluation": "NOT_EVALUATED" }	`pydantic>=2.0.0`	runtime
pytest Environment { "extras": "", "marker": "extra == \"dev\"", "requires_python": ">=3.10", "evaluation": "NOT_EVALUATED" }	`pytest>=8.0.0; extra == "dev"`	runtime
pytest-asyncio Environment { "extras": "", "marker": "extra == \"dev\"", "requires_python": ">=3.10", "evaluation": "NOT_EVALUATED" }	`pytest-asyncio>=0.23.0; extra == "dev"`	runtime
respx Environment { "extras": "", "marker": "extra == \"dev\"", "requires_python": ">=3.10", "evaluation": "NOT_EVALUATED" }	`respx>=0.21.0; extra == "dev"`	runtime
langchain-core Environment { "extras": "", "marker": "extra == \"langchain\"", "requires_python": ">=3.10", "evaluation": "NOT_EVALUATED" }	`langchain-core>=0.1.0; extra == "langchain"`	runtime
crewai Environment { "extras": "", "marker": "extra == \"crewai\"", "requires_python": ">=3.10", "evaluation": "NOT_EVALUATED" }	`crewai>=0.1.0; extra == "crewai"`	runtime
langchain-core Environment { "extras": "", "marker": "extra == \"all\"", "requires_python": ">=3.10", "evaluation": "NOT_EVALUATED" }	`langchain-core>=0.1.0; extra == "all"`	runtime
crewai Environment { "extras": "", "marker": "extra == \"all\"", "requires_python": ">=3.10", "evaluation": "NOT_EVALUATED" }	`crewai>=0.1.0; extra == "all"`	runtime