Open-source AI gateway for local agent clients: publish fusion-style multi-model workflows as OpenAI/Claude-compatible virtual models with traces, tokens, latency, and cost visibility.

MemTrace: Tracing and Attributing Errors in Large Language Model Memory Systems

OpenAI Agents Tracing | Open-Source Tracing Dashboard including Costs & Usages

Evaluation of Multi-Agent Systems on Cloud Run with the GenAI Client in Vertex AI SDK

Local-first agent debugger with replay, failure memory, smart highlights, and drift detection.

Substructure is an engine for building durable, long-running AI agents using only a stateless HTTP endpoint hosted on your infrastructure, in your code.

Comprehensive agent analytics suite for AI agents built with the Google Agent Development Kit (ADK) , LangChain or other popular frameworks, powered by BigQuery Agent Analytics plugin and Grafana

Open Reflection Protocol — Turn agent failures into regression tests, reusable lessons, and measurable improvements. Built on OpenTelemetry.

Claude Code session capture and analysis. Trace tool calls, detect backtracks, analyze decisions, track edit chains, and measure plan drift. Local-first, zero-dependency observability.

Local replay debugger for Browser Use failures with screenshots, model I/O, failed-step timelines, and public-safe HTML exports.

Shared context substrate for AI agents. Retrieval that learns what's useful. Runs local or cloud.

Observability and governance SDK for AI Agents

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

ai agent trace, Open-source runtime tracing and diagnostics for AI agent execution flows

Homebrew tap for AgentTap - network-level AI agent observability

Capture and analyze Claude Code sessions locally to track every tool call, decision, and reasoning step without external dependencies.

Agent evaluation framework: run LLM agents against datasets, capture execution traces, score with rubric-based LLM judges, and view regressions in a web dashboard. Local-first, no external infra required.

A local LLM proxy tool that intercepts and visualizes all OpenAI API calls, providing a real-time web monitoring dashboard.

Execution trace schema for AI agent pipelines.

Open-source evaluation framework for AI agents. Define test suites with rubrics, run your agent, get LLM-as-judge scores against criteria, inspect full execution traces, and diff runs to catch behavioral regressions.