PkgFoundry
Catalog PyPI
Back to packageRELEASE DETAILS

0.2.2

PyPI

agentwatchx

Observability SDK for AI Agent Execution — catches hallucinations, silent failures, and missing executions

agentsaianthropicgeminigroqlangchainllmmistralobservabilityopenaitracing
Published16 Apr 2026
Direct dependencies9
Transitive dependenciesNot calculated

README

Version 0.2.2 documentation

AgentWatchX Python SDK

Observability for AI agents. Catches hallucinations, silent failures, and missing executions automatically.

Install

pip install agentwatchx

2-Line Integration

import agentwatchx
agentwatchx.init(api_key="your_api_key")

# That's it. Every OpenAI/Anthropic/Gemini/Groq/Mistral/LangChain/LlamaIndex call is now traced.
# No decorators, no wrappers, no code changes needed.

What it captures

  • Model, input, output, token usage, latency — automatically
  • Tool calls made by the LLM (function calling)
  • Hallucination detection — agent claims actions it never performed
  • Failure masking — tool errors the agent hides from users
  • Missing execution — user asks for action, agent just talks

Supported Libraries

LibraryAuto-instrumented
OpenAI✅
Anthropic✅
Gemini✅
Groq✅
Mistral✅
LangChain✅
LlamaIndex✅

Configuration

agentwatchx.init(
    api_key="your_api_key",
)

Advanced Usage

# Manual trace decorator
@agentwatchx.trace
def my_agent(query: str):
    return client.chat.completions.create(...)

# Manual logging
agentwatchx.log({"service": "my-agent", "input": "hello", "output": "world"})

# Check status
print(agentwatchx.status())
# → {"initialized": True, "instrumented": ["openai"], "buffered_traces": 0}

Links

Downloads & popularity

Awaiting observations

No metric observations yet

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

Declared dependencies 16

Native requirements
9 direct targetsNot calculated transitive count
Package / targetRequirementRelationship
httpx
Environment
{
  "extras": "",
  "marker": null,
  "requires_python": ">=3.9",
  "evaluation": "NOT_EVALUATED"
}
httpx>=0.25.0runtime
pydantic
Environment
{
  "extras": "",
  "marker": null,
  "requires_python": ">=3.9",
  "evaluation": "NOT_EVALUATED"
}
pydantic>=2.0.0runtime
openai
Environment
{
  "extras": "",
  "marker": "extra == \"openai\"",
  "requires_python": ">=3.9",
  "evaluation": "NOT_EVALUATED"
}
openai>=1.0.0; extra == "openai"runtime
anthropic
Environment
{
  "extras": "",
  "marker": "extra == \"anthropic\"",
  "requires_python": ">=3.9",
  "evaluation": "NOT_EVALUATED"
}
anthropic>=0.18.0; extra == "anthropic"runtime
google-generativeai
Environment
{
  "extras": "",
  "marker": "extra == \"gemini\"",
  "requires_python": ">=3.9",
  "evaluation": "NOT_EVALUATED"
}
google-generativeai>=0.5.0; extra == "gemini"runtime
groq
Environment
{
  "extras": "",
  "marker": "extra == \"groq\"",
  "requires_python": ">=3.9",
  "evaluation": "NOT_EVALUATED"
}
groq>=0.4.0; extra == "groq"runtime
mistralai
Environment
{
  "extras": "",
  "marker": "extra == \"mistral\"",
  "requires_python": ">=3.9",
  "evaluation": "NOT_EVALUATED"
}
mistralai>=1.0.0; extra == "mistral"runtime
langchain-core
Environment
{
  "extras": "",
  "marker": "extra == \"langchain\"",
  "requires_python": ">=3.9",
  "evaluation": "NOT_EVALUATED"
}
langchain-core>=0.1.0; extra == "langchain"runtime
llama-index-core
Environment
{
  "extras": "",
  "marker": "extra == \"llamaindex\"",
  "requires_python": ">=3.9",
  "evaluation": "NOT_EVALUATED"
}
llama-index-core>=0.10.0; extra == "llamaindex"runtime
openai
Environment
{
  "extras": "",
  "marker": "extra == \"all\"",
  "requires_python": ">=3.9",
  "evaluation": "NOT_EVALUATED"
}
openai>=1.0.0; extra == "all"runtime
anthropic
Environment
{
  "extras": "",
  "marker": "extra == \"all\"",
  "requires_python": ">=3.9",
  "evaluation": "NOT_EVALUATED"
}
anthropic>=0.18.0; extra == "all"runtime
google-generativeai
Environment
{
  "extras": "",
  "marker": "extra == \"all\"",
  "requires_python": ">=3.9",
  "evaluation": "NOT_EVALUATED"
}
google-generativeai>=0.5.0; extra == "all"runtime
groq
Environment
{
  "extras": "",
  "marker": "extra == \"all\"",
  "requires_python": ">=3.9",
  "evaluation": "NOT_EVALUATED"
}
groq>=0.4.0; extra == "all"runtime
mistralai
Environment
{
  "extras": "",
  "marker": "extra == \"all\"",
  "requires_python": ">=3.9",
  "evaluation": "NOT_EVALUATED"
}
mistralai>=1.0.0; extra == "all"runtime
langchain-core
Environment
{
  "extras": "",
  "marker": "extra == \"all\"",
  "requires_python": ">=3.9",
  "evaluation": "NOT_EVALUATED"
}
langchain-core>=0.1.0; extra == "all"runtime
llama-index-core
Environment
{
  "extras": "",
  "marker": "extra == \"all\"",
  "requires_python": ">=3.9",
  "evaluation": "NOT_EVALUATED"
}
llama-index-core>=0.10.0; extra == "all"runtime

Distribution files

2 collected
agentwatchx-0.2.2-py3-none-any.whl

bdist_wheel · 21.37 KB · Python py3

Source file
agentwatchx-0.2.2.tar.gz

sdist · 14.17 KB · Python source

Source file

Metadata history

Meaningful changes
Current collected state Current

Observed since 21 Oct, 08:56 UTC

No superseded metadata states collected. Unchanged observations do not create new revisions.

Record identity

package_version:4af47fc6c603d65bf9082cf2197349ab45b5d79f5aff065698709727bcee5a01

Other collected versions

View all collected versions →