Back to packageRELEASE DETAILS

0.3.0

PyPI

agentsec-agentwatch

Execution traces for agent behavior - OpenTelemetry-style observability for AI agent workflows

Published12 Oct 2026

Direct dependencies15

Transitive dependenciesNot calculated

README

Version 0.3.0 documentation

agentwatch

Instrumentation SDK for AI agents — turn agent behavior into OpenTelemetry GenAI spans and validated, redacted execution records. Part of agentwatch.

Installation

pip install agentsec-agentwatch

Optional extras:

pip install "agentsec-agentwatch[langgraph]"   # LangGraph adapter
pip install "agentsec-agentwatch[otlp]"        # OTLP export
pip install "agentsec-agentwatch[signing]"     # cryptographic signing helpers

Requires Python 3.10+.

Quickstart

Trace a plain Python agent — no framework required:

from agentwatch.raw import trace_agent
from agentwatch.spans import plan_span, execute_tool_span

@trace_agent("support-bot", agent_version="v0.1.0", model="gpt-4o", provider="openai")
def answer(request: str) -> str:
    with plan_span("decide next action"):
        ...
    with execute_tool_span("search", arguments={"q": request}):
        ...
    return "done"

Or drive the run context explicitly:

from agentwatch.config import default_config
from agentwatch.tracer import configure_tracing
from agentwatch.context import RunContext
from agentwatch.instrument import invoke_agent

configure_tracing(default_config())          # once at startup
with invoke_agent(RunContext(agent_name="request-triage")):
    ...

LangGraph:

from agentwatch.langgraph import trace_graph

graph = trace_graph(compiled_graph, agent_name="planner")

Privacy

Records are redacted by default. Four privacy modes are available per span/tool call:

Mode	What is stored
`truncated` (default)	Content-safe truncated values
`metadata-only`	Names, timings, and counts; no content
`hashed`	One-way digests of content
`full`	Raw content (opt-in)

Record, replay, verify

The same package installs the CLI:

agentsec-agentwatch init            # install Claude Code hooks + start the local daemon
agentsec-agentwatch sessions        # list recorded sessions
agentsec-agentwatch replay <id>     # reconstruct a session's action timeline
agentsec-agentwatch verify-store    # verify the hash chain

Records are written to a local-first, hash-chained JSONL store; OTLP export is opt-in and gated on a redaction self-test.

Documentation

License

Apache-2.0 — see LICENSE.

Downloads & popularity

Awaiting observations

No metric observations yet

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

Declared dependencies 18

Native requirements

15 direct targetsNot calculated transitive count

Package / target	Requirement	Relationship
opentelemetry-api Environment { "extras": "", "marker": null, "requires_python": ">=3.10", "evaluation": "NOT_EVALUATED" }	`opentelemetry-api>=1.24`	runtime
opentelemetry-sdk Environment { "extras": "", "marker": null, "requires_python": ">=3.10", "evaluation": "NOT_EVALUATED" }	`opentelemetry-sdk>=1.24`	runtime
tomli Environment { "extras": "", "marker": "python_version < \"3.11\"", "requires_python": ">=3.10", "evaluation": "NOT_EVALUATED" }	`tomli>=2; python_version < "3.11"`	runtime
langgraph Environment { "extras": "", "marker": "extra == \"langgraph\"", "requires_python": ">=3.10", "evaluation": "NOT_EVALUATED" }	`langgraph>=1.0; extra == "langgraph"`	runtime
zstandard Environment { "extras": "", "marker": "python_version < \"3.14\" and extra == \"codex\"", "requires_python": ">=3.10", "evaluation": "NOT_EVALUATED" }	`zstandard>=0.22; python_version < "3.14" and extra == "codex"`	runtime
cryptography Environment { "extras": "", "marker": "extra == \"signing\"", "requires_python": ">=3.10", "evaluation": "NOT_EVALUATED" }	`cryptography>=41; extra == "signing"`	runtime
opentelemetry-exporter-otlp-proto-grpc Environment { "extras": "", "marker": "extra == \"otlp\"", "requires_python": ">=3.10", "evaluation": "NOT_EVALUATED" }	`opentelemetry-exporter-otlp-proto-grpc>=1.24; extra == "otlp"`	runtime
pytest Environment { "extras": "", "marker": "extra == \"dev\"", "requires_python": ">=3.10", "evaluation": "NOT_EVALUATED" }	`pytest>=8; extra == "dev"`	runtime
pytest-cov Environment { "extras": "", "marker": "extra == \"dev\"", "requires_python": ">=3.10", "evaluation": "NOT_EVALUATED" }	`pytest-cov>=5; extra == "dev"`	runtime
ruff Environment { "extras": "", "marker": "extra == \"dev\"", "requires_python": ">=3.10", "evaluation": "NOT_EVALUATED" }	`ruff>=0.9; extra == "dev"`	runtime
mypy Environment { "extras": "", "marker": "extra == \"dev\"", "requires_python": ">=3.10", "evaluation": "NOT_EVALUATED" }	`mypy>=1.13; extra == "dev"`	runtime
build Environment { "extras": "", "marker": "extra == \"dev\"", "requires_python": ">=3.10", "evaluation": "NOT_EVALUATED" }	`build>=1.2; extra == "dev"`	runtime
jsonschema Environment { "extras": "", "marker": "extra == \"dev\"", "requires_python": ">=3.10", "evaluation": "NOT_EVALUATED" }	`jsonschema>=4.20; extra == "dev"`	runtime
tomli Environment { "extras": "", "marker": "extra == \"dev\"", "requires_python": ">=3.10", "evaluation": "NOT_EVALUATED" }	`tomli>=2; extra == "dev"`	runtime
opentelemetry-exporter-otlp-proto-grpc Environment { "extras": "", "marker": "extra == \"dev\"", "requires_python": ">=3.10", "evaluation": "NOT_EVALUATED" }	`opentelemetry-exporter-otlp-proto-grpc>=1.24; extra == "dev"`	runtime
hypothesis Environment { "extras": "", "marker": "extra == \"dev\"", "requires_python": ">=3.10", "evaluation": "NOT_EVALUATED" }	`hypothesis>=6.100; extra == "dev"`	runtime
zstandard Environment { "extras": "", "marker": "extra == \"dev\"", "requires_python": ">=3.10", "evaluation": "NOT_EVALUATED" }	`zstandard>=0.22; extra == "dev"`	runtime
cosmic-ray Environment { "extras": "", "marker": "extra == \"mutation\"", "requires_python": ">=3.10", "evaluation": "NOT_EVALUATED" }	`cosmic-ray>=8.7; extra == "mutation"`	runtime