Agent Observability Python Packages

logfire

AI observability platform for production LLM and agent systems.

agenta

Agenta is a workspace where you and your team build agents and automations.

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.

latitude-sdk

Open-source observability for AI agents. Find where your agents fail, dispatch your coding agent to fix it, and verify the fix against real traces.

agentacct

See what your coding agents did and what it cost. Breaks each task down into work steps — tools used, files changed, tests run, time and tokens spent. Local-first dashboard for Claude Code, Codex, OpenCode, and more. No login, no telemetry.

latitude-telemetry

Open-source observability for AI agents. Find where your agents fail, dispatch your coding agent to fix it, and verify the fix against real traces.

isnad

Grade every agent, scraper and model in a claim's chain — provenance, trust scoring and audit evidence for LLM pipelines

superbased-observer

Local-first control plane for AI coding agents — launch browser terminals, run and remotely control sessions, and track files, tokens & cost across Claude Code, Codex, Cursor, Gemini CLI and 20+ more. 100% local, no telemetry.

agentic-coding-harness

Run, watch, and meter Claude Code, Codex CLI, Gemini CLI, OpenCode, and Kiro from one CLI. Normalized events, cache-aware token usage, cost accounting verified against each agent's own records, budget caps, OpenTelemetry gen_ai spans, Langfuse traces, and a live web dashboard + MCP server.

atmem

Local-first, auditable memory for AI agents, with governed retrieval, delegated context delivery, and verifiable execution evidence. Works with OpenClaw, MCP, Pydantic AI, and LangChain/LangGraph. No external API required for local memory. Install with pip: pip install atmem

tracely-ai

Tracely Python SDK: automatic + manual agent tracing, exported to Tracely over OTLP.

agent-strace

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

crewplane

Run reviewable, resumable coding-agent workflows across Claude Code, Codex, Gemini, GitHub Copilot CLI, or any CLI. You define the stages in Markdown; Crewplane runs the workflow, agents do the work, and every handoff stays on disk.

failecho-autoreport

When a tool or model call fails, your agent learns what fixed it for other agents, or that nothing has. Plugins for Claude Code and OpenCode, an MCP proxy, a Python wrapper. Open source, metadata only.

fathom-read

Catch the step where an AI agent contradicts its own earlier decision. CLI and adapters for LangGraph, CrewAI, Letta, OpenInference, DBOS and multi-agent logs, plus an expiry read for long-running agents.

acontext

Agent Skills as a Memory Layer

failecho-mcp

When a tool or model call fails, your agent learns what fixed it for other agents, or that nothing has. Plugins for Claude Code and OpenCode, an MCP proxy, a Python wrapper. Open source, metadata only.

apcore

A schema-driven module development framework for Python.

atmem-atbot

Local-first, auditable memory for AI agents, with governed retrieval, delegated context delivery, and verifiable execution evidence. Works with OpenClaw, MCP, Pydantic AI, and LangChain/LangGraph. No external API required for local memory. Install with pip: pip install atmem

failproofai-sdk

Observability and enforcement for AI agent harnesses. Capture every run and runtime reliability with policy enforcement.

hyperweave

Visual CLI for agents. Deterministic SVG diagrams, tables, and charts with embedded structured metadata. Zero JavaScript. Renders anywhere markdown does.

aetnamem

Local-first, auditable memory for AI agents, with governed retrieval, delegated context delivery, and verifiable execution evidence. Works with OpenClaw, MCP, Pydantic AI, and LangChain/LangGraph. No external API required for local memory. Install with pip: pip install atmem

yoetz

Yoetz — local-first structured work evidence, deterministic checks, and honest verification receipts.

watch-skill

Give AI agents eyes, ears, and verifiable results. Watch Skill turns video, audio and screen activity into searchable, timestamped evidence and proves work with deterministic contracts, not model opinion. DeepWatch is the agent workspace built on DeepSeek Harness. Python + npm, MCP, CLI, REST, Web.