agentwatch-observe 0.1.0

Lightweight observability SDK for AI agents — wrap any agent framework, get anomaly detection, guardrails, and cost tracking.

agentwatch-observe

Lightweight observability for AI agents. Wrap any local or cloud model call, stream steps to AgentWatch, and get cost tracking, anomaly detection, and guardrails on the dashboard at agentwatch.in.

Privacy: Your model credentials (OpenAI, Gemini, Ollama, etc.) stay on your machine. AgentWatch only receives telemetry — tokens, cost estimates, tool names, timing, and step metadata — never your API keys or raw model weights.

Install

pip install agentwatch-observe

Optional LangChain integration:

pip install "agentwatch-observe[langchain]"

Quickstart (under 10 lines)

import agentwatch

agentwatch.init(
    api_key="YOUR_AGENTWATCH_API_KEY",
    base_url="https://api.agentwatch.in",  # or http://localhost:8000 for local dev
)

with agentwatch.run("my-agent") as run:
    run.log_llm(
        model="gpt-4o-mini",
        input_tokens=120,
        output_tokens=40,
        output="Hello from AgentWatch!",
    )

Open the AgentWatch dashboard → Runs to see the trace.

Local model example (Ollama)

import requests
import agentwatch

agentwatch.init(api_key="YOUR_AGENTWATCH_API_KEY", base_url="http://localhost:8000")

def call_local_model(prompt: str) -> str:
    response = requests.post(
        "http://localhost:11434/api/generate",
        json={"model": "llama3", "prompt": prompt, "stream": False},
        timeout=60,
    )
    response.raise_for_status()
    return response.json()["response"]

with agentwatch.run("my-local-agent") as run:
    prompt = "Summarize observability in one sentence."
    reply = call_local_model(prompt)
    run.log_tool(
        "ollama:llama3",
        input_data={"prompt": prompt},
        output_data={"reply": reply},
    )

Framework-agnostic API

• agentwatch.run(...) — context manager
• run.log_llm(...) — LLM step with token/cost tracking
• run.log_tool(...) — tool call step
• agentwatch.track(...) — decorator
• agentwatch.instrument_openai(client) — auto-log OpenAI calls

See the full docs at agentwatch.in.

Releasing a new version

PyPI never allows re-uploading the same version number.

1. Bump version in pyproject.toml and agentwatch/__init__.py
2. cd sdk && python -m build
3. twine check dist/*
4. Upload to TestPyPI first: twine upload --repository testpypi dist/*
5. After verification, upload to PyPI: twine upload dist/*

See CONTRIBUTING.md for details.