PyRank
  • Insights
  • PyPI
  • GitHub
  • Search
  • Compare
  • Advisories
  • Ecosystem
  • About

Agent Observability Python Packages

Python packages with the GitHub topic agent-observability. Sorted by relevance, with stars and monthly downloads.
pydantic
logfire

AI observability platform for production LLM and agent systems.

19M 4K 253
liaohch3
claude-tap

Intercept and inspect Coding Agent API traffic from Claude Code, Codex CLI, Gemini CLI, Cursor CLI, OpenCode, Kimi/Kimi Code, Pi, and Hermes in a local trace viewer.

109K 2K 219
latitude-dev
latitude-sdk

Latitude is the open-source ai monitoring platform.

29K 4K 351
Siddhant-K-code
agent-strace

Observability for AI agents. See what your agent did, why it cost that much, and what to fix.

14K 74 6
valani9
valanistack

AI agents fail like junior teammates, looping on bad ideas, ignoring feedback, and escalating commitment. vstack ports 34 of the most-cited organizational-behavior frameworks so you can diagnose your agents the same way you'd diagnose your team.

13K 1 0
latitude-dev
latitude-telemetry

Latitude is the open-source ai monitoring platform.

12K 4K 351
InnerAura
hyperweave

Portable visual output layer for agents. One API call, one SVG. Zero dependencies, renders in any markdown.

6K 23 6
memodb-io
acontext

Agent Skills as a Memory Layer

5K 4K 323
dunetrace
dunetrace

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

5K 56 12
aiperceivable
apcore

A schema-driven module development framework for Python.

4K 3 1
pcguest
atb-sdk

ATB bundle reader and verifier SDK

2K 0 0
sandeep-alluru
agentdelta

Diff and regression-detect LLM agent execution traces

2K 0 0
ericelizes1
agentclip

Python SDK + CLI + MCP server for AgentClip — the open-source tool that turns AI agent runs into shareable URLs.

2K 1 0
Scaffoldic
forgesight-api

Vendor-neutral, OpenTelemetry-first telemetry for AI agents — traces, cost, budgets & a tamper-evident audit trail to any backend, no agent-code changes.

1K 4 0
Scaffoldic
forgesight-core

Vendor-neutral, OpenTelemetry-first telemetry for AI agents — traces, cost, budgets & a tamper-evident audit trail to any backend, no agent-code changes.

1K 4 0
huyn7539
agent-run-ledger

Graded repair receipts for AI coding-agent runs. Local, zero-egress, honest-abstain: 'clean' never means 'verified correct'. Reads Claude Code / Codex / OpenAI SDK session logs.

1K 0 0
agentkitai
agentlensai

Open-source observability and audit trail platform for AI agents. MCP-native, tamper-evident event logging, real-time dashboard.

1K 8 2
seclai
seclai

Official Seclai Python SDK

1K 2 0
markndg
varden

A self-hosted runtime firewall for AI agents

1K 0 0
milkoor
causetrace

AI coding agent observability and causal tracing for Claude Code, Codex CLI, and OpenCode

981 1 0
Scaffoldic
forgesight-otel

Vendor-neutral, OpenTelemetry-first telemetry for AI agents — traces, cost, budgets & a tamper-evident audit trail to any backend, no agent-code changes.

912 4 0
Scaffoldic
forgesight-datadog

Vendor-neutral, OpenTelemetry-first telemetry for AI agents — traces, cost, budgets & a tamper-evident audit trail to any backend, no agent-code changes.

855 4 0
Scaffoldic
forgesight

Vendor-neutral, OpenTelemetry-first telemetry for AI agents — traces, cost, budgets & a tamper-evident audit trail to any backend, no agent-code changes.

830 4 0
Scaffoldic
forgesight-prometheus

Vendor-neutral, OpenTelemetry-first telemetry for AI agents — traces, cost, budgets & a tamper-evident audit trail to any backend, no agent-code changes.

828 4 0
    • Data from PyPI, GitHub, ClickHouse, and BigQuery