Agent Monitoring Python Packages

latitude-sdk

Latitude is the open-source ai monitoring platform.

latitude-telemetry

Latitude is the open-source ai monitoring platform.

dos-kernel

Catch your AI agents when they lie about what they shipped — verifies claims against git instead of believing the agent.

agenttrace-io

Open source AI agent observability. Trace tokens, tools, latency, and cost. Local dashboard. Zero cloud dependency. Privacy-first.

helicone-helpers

🧊 Open source LLM observability platform. One line of code to monitor, evaluate, and experiment. YC W23 🍓

dunetrace

Real-time monitoring of production AI agents. No raw content transmitted.

agent-driftwatch

Real-time memory health monitor for AI agents. Detect context rot before your agent goes off the rails

helicone-async

🧊 Open source LLM observability platform. One line of code to monitor, evaluate, and experiment. YC W23 🍓

agent-panorama

See what your AI agents do, whether it's worth it, and what it costs - a manager-readable report + local dashboard from Langfuse/LangSmith traces (or a one-line live callback). Open source, runs locally.

traccia

OpenTelemetry-native observability, governance, and compliance for AI agents and LLM applications

helicone

🧊 Open source LLM observability platform. One line of code to monitor, evaluate, and experiment. YC W23 🍓

agent-pd

A police department for your Claude Code agents — a logging-only hook + CLI that audits the main agent and every subagent and reports rule offenses (permission bypass, out-of-scope & credential access, self-permissioning, disallowed tools, redundant, off-task) with quoted evidence. Catch-and-report, never blocks.

agentos-platform

"The Operating System for AI Agents. Build, Test, Deploy, Monitor, Govern."

agentminds

Python SDK for AgentMinds — cross-site collective intelligence for production AI agents. Auto-capture errors + push/pull patterns from the network pool.

observeco

Self-healing observability for AI agents. Discover, monitor, and auto-recover multi-agent systems — without a cloud dependency.

latitude-telemetry-hermes

Latitude is the open-source ai monitoring platform.

agentliveness

agentvitals — a small, dependency-free reliability harness for scheduled/autonomous AI agents: persist state across runs, prove liveness (not just freshness), fail loud.

llm-sentry

Unified AI reliability platform. One install, 12 diagnostic engines. Continuous monitoring, fault diagnosis, and compliance for LLM pipelines.

cursor-agent-beacon

Monitor Cursor Agent activity via native hooks — GNOME panel, status CLI, and ESP32 bridge

cogniguardai

Flight recorder for AI agents — every prompt, tool call, file, and dollar. Made by CogniGuard AI.

gripe-mcp

Agent complaint box — one-tool MCP for logging bugs and improvement requests

langgraph-sfm

Causal intent monitoring for LangGraph agents.

tethral-acr

Python SDK for the ACR (Agent Composition Records) network. Register agents, log interactions, and query behavioral profiles through lenses: friction, coverage, stable corridors, failure registry, and trend. Raw signals, no synthetic labels.

unworldly-recorder

The flight recorder for AI agents. Record, replay, and audit everything AI agents do on your system.