Skip to main content

Unified observability dashboard for the agent stack — metrics, audit, escalations, policy, health

Project description

agentobserve

CI PyPI Python License


agentobserve is a unified observability dashboard for the agent infrastructure stack. One view across agentplane policies, agenthooks executions, escalation events, and agent health.

Install

pip install agentobserve                    # zero-dep core
pip install "agentobserve[rich]"            # terminal dashboard
pip install "agentobserve[rich,web]"        # terminal + web dashboard

Quickstart

from agentobserve import ObserveDashboard, Collector

# Point at your audit files
collector = Collector(
    agentplane_audit="~/.agentplane/audit.jsonl",
    agenthooks_audit="~/.agenthooks/audit.jsonl",
)

dash = ObserveDashboard(collector=collector)
dash.print_snapshot()   # one-shot terminal print
dash.run()              # blocking live dashboard (Ctrl+C to exit)

With live agentplane engine

from agentplane import PolicyEngine
from agentobserve import ObserveDashboard

engine = PolicyEngine()
dash = ObserveDashboard(engine=engine)
dash.print_snapshot()

Snapshot API

snap = dash.snapshot()

snap.agent_count        # total agents seen
snap.active_count       # agents with status "active"
snap.degraded_count     # agents in degraded mode
snap.unplugged_count    # unplugged agents
snap.total_evals        # total policy evaluations
snap.block_rate         # fraction of evaluations that were blocked
snap.total_hook_executions  # total agenthooks executions

snap.to_dict()          # JSON-serializable dict

Stack

agentplane    → control plane   (runtime policy, versioning, escalation)
agenthooks    → extensibility   (hookpoints, customer hooks)
agentobserve  → observability   (unified view across all layers)  ← you are here
AgentGuard    → safety          (injection, PII, jailbreak)

Apache 2.0 · Built for production enterprise agents

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

agentobserve_py-0.1.0.tar.gz (10.0 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

agentobserve_py-0.1.0-py3-none-any.whl (7.1 kB view details)

Uploaded Python 3

File details

Details for the file agentobserve_py-0.1.0.tar.gz.

File metadata

  • Download URL: agentobserve_py-0.1.0.tar.gz
  • Upload date:
  • Size: 10.0 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.1.0 CPython/3.13.12

File hashes

Hashes for agentobserve_py-0.1.0.tar.gz
Algorithm Hash digest
SHA256 e0ec51ff2a442d1e79aeb1d506ab327e8ee2331e6a36ccc2bde9625e41c6f851
MD5 1ab9861b33da602e9e5efbc78e69e15a
BLAKE2b-256 972129dd13675587fe5c08e60a06b490bf8b20f2fe191c734a1381a525607a8c

See more details on using hashes here.

File details

Details for the file agentobserve_py-0.1.0-py3-none-any.whl.

File metadata

File hashes

Hashes for agentobserve_py-0.1.0-py3-none-any.whl
Algorithm Hash digest
SHA256 2bfb1f71390887ccc51c24abdd3bb7c92b94ecfad5de3a070a1b21bc5da4b83a
MD5 a031ff5908dbbbe3b7293b6a6743ce90
BLAKE2b-256 6ecc5c8a382f4c5be562f52046643b3c983411155d4e1982b9a512b1a6f2d5a6

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page