AgentWatch Python SDK
Production monitoring for AI agents: rule-based checks on every trace, optional LLM judge analysis when a step is flagged, plus async delivery to your AgentWatch API.
Install
pip install agentwatch-io
From a clone of this repo (editable / dev):
pip install -e ./agentwatch-sdk
Import name is always agentwatch after either install.
Quick start
import agentwatch
import openai
agentwatch.init(
api_key="aw_...", # Dashboard → API Keys
server_url="http://localhost:8000",
agent_name="my-agent",
)
client = agentwatch.watch(openai.OpenAI())
response = client.chat.completions.create(
model="gpt-4o-mini",
messages=[{"role": "user", "content": "Hello"}],
)
init alone does not trace calls — you must use watch(client) (or a patched default client) so requests go through the wrapper.
LLM analysis (optional judge)
When rule checks flag a trace, the server can call your OpenAI, Anthropic, or Groq API with a judge prompt. Enable in init:
import os
agentwatch.init(
api_key="aw_...",
server_url="https://your-api.example.com",
agent_name="my-agent",
deep_analysis=True,
llm_provider="openai",
llm_api_key=os.environ["OPENAI_API_KEY"],
llm_model="gpt-4o-mini",
)
Your LLM key is sent only to your provider from the API process; AgentWatch does not log or store it.
Parameters
| Parameter | Description |
|---|---|
api_key |
AgentWatch key (aw_...). |
server_url |
FastAPI base URL. |
agent_name |
Shown in dashboard. |
deep_analysis |
Enable LLM judge on flagged traces. |
llm_provider |
"openai", "anthropic", or "groq". |
llm_api_key |
Provider key for judge (including Groq). |
groq_api_key |
Optional; same as putting the Groq key in llm_api_key. |
llm_model |
Optional model override. |
content_mode |
If True, server runs extra content-creation checks (repetition, length, injection phrases, off-topic heuristic). |
redact_fields |
Field names to redact in trace text. |
silent |
Suppress stdout from init. |
Anthropic
import anthropic
agentwatch.init(api_key="aw_...", server_url="...", agent_name="bot")
client = agentwatch.watch(anthropic.Anthropic())
client.messages.create(model="claude-3-5-haiku-20241022", max_tokens=256, messages=[...])
Groq
Install Groq’s Python SDK (pip install groq). The client is OpenAI-compatible for chat.completions:
import os
import agentwatch
from groq import Groq
agentwatch.init(
api_key="aw_...",
server_url="http://localhost:8000",
agent_name="content-generator",
deep_analysis=True,
llm_provider="groq",
llm_api_key=os.environ["GROQ_API_KEY"],
llm_model="llama-3.3-70b-versatile",
)
client = agentwatch.watch(Groq())
client.chat.completions.create(
model="llama-3.3-70b-versatile",
messages=[{"role": "user", "content": "Write a short paragraph about Python."}],
)
Full documentation
See the Documentation page in the AgentWatch dashboard (/docs) for architecture, runs, alerts, and dashboard setup.
Metadata
Release files for agentwatch-io 0.1.0
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | Provenance | Actions |
|---|---|---|---|---|
| agentwatch_io-0.1.0.tar.gz | 6.6 kB | With provenance | Details for agentwatch_io-0.1.0.tar.gz |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Actions Reset |
|---|---|---|---|---|
| agentwatch_io-0.1.0-py3-none-any.whl | Python 3 | none | any | Details for agentwatch_io-0.1.0-py3-none-any.whl |
Total release size: 14.2 kB
Release files / agentwatch_io-0.1.0.tar.gz
| Download URL | agentwatch_io-0.1.0.tar.gz |
|---|---|
| Size | 6.6 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
8b9a321b03670235490ed9c774cd4afab6519c7a48d71e2093d4e178a36ba045
|
|
BLAKE2b-256 checksum How to use checksums |
ae470fae744745c3266677973d76816130640219ec5851cb0bd037eed478f413
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
twine/6.1.0 CPython/3.13.7
|
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
PyPI Publish Attestation
PyPI verified that this artifact, at this checksum, originated from the publisher listed below.
Signed by GitHub Actions, verified by PyPI on Apr 6, 2026.
Transparency logRelease files / agentwatch_io-0.1.0-py3-none-any.whl
| Download URL | agentwatch_io-0.1.0-py3-none-any.whl |
|---|---|
| Size | 7.7 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
8bec3bb7be9996ba4d875098e65b590306ba6bc786b8b0f9d9b21d973be8fb2f
|
|
BLAKE2b-256 checksum How to use checksums |
1bfb93f241187679c23ab1d6cf7954e00170313eacad1df10866a97e246bf9c6
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
twine/6.1.0 CPython/3.13.7
|
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
PyPI Publish Attestation
PyPI verified that this artifact, at this checksum, originated from the publisher listed below.
Signed by GitHub Actions, verified by PyPI on Apr 6, 2026.
Transparency logSecurity for agentwatch-io 0.1.0
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
Full provenance
Both files in this release have been uploaded with provenance metadata.
Attestation for agentwatch_io-0.1.0.tar.gz
PyPI Publish Attestation
PyPI verified that this artifact, at this checksum, originated from the publisher listed below.
Signed by GitHub Actions, verified by PyPI on Apr 6, 2026.
Transparency logA note on package security
PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.
To learn more about protecting yourself from malicious actors, visit our package security documentation.