#observability

OpenTelemetry instrumentation for @imqueue — every RPC traced, with no changes to service or client code

Trace Pi coding agent sessions with Langfuse — agent turns, model generations, token usage with cache and reasoning splits, cost, tool calls, and nested subagents.

OpenTelemetry middleware for Go MCP servers (go-sdk)

Typed building blocks for everything around your LLM call.

Go library implementing the Policy specification.

The functional, composable, and typescript-first AI Agent framework for real-world LLM Apps.

Standard diagnostics-channel convention (aviary:<lib>:<event>) for NestJS + a single generic Telescope watcher. Emit once, observe everywhere.

Pre-action evidence revalidation for AI agents. Detect stale reasoning before agents write, send, update, or delete.

Observability engine for AI coding agents. Custom columnar log store, MCP-native, self-hosted on a $4/mo VM. No dashboards — your AI assistant sees production.

Laritor is a Laravel-native observability platform that helps you monitor, debug, and optimize your application in production.

Collector-free telemetry for Laravel: Prometheus metrics, OTLP traces and events. No C extension, no protobuf, no sidecar — metrics that actually work under FPM.

Various static analysis and testing tools for managing PromQL compatible monitoring stacks

SDK for Convergent's agent optimization package

OpenTelemetry integration for Langfuse observability

The incident engine for UniFi: keeps the history your controller throws away and turns it into tracked, root-caused issues with revertible fixes.

Baton SDK — structured signal capture for agent-mediated tool use. MCP middleware, library API, and (coming) customer-side plugins emit the same event envelope to any sink.

The open standard AI gateway — PII protection, audit, reliability & cost control as composable interceptors. Same API in Python, Java & JavaScript.

Local-only observability for AI agents on your machine. One timeline across coding and non-coding agents.

Self-hosted error-monitoring for Python pipelines: capture exceptions, deduplicate, diagnose root causes with LLMs, route alerts (Telegram/Slack/email/GitHub/S3), and auto-generate fix PRs — from a logging handler or one report() call.

OpenAIDR — session collection for AI coding agents. Reads what agents write to disk and normalises it into one session model.

GCP-native structured logging for Go (slog) microservices on Cloud Run, with built-in gRPC interceptors.

Session viewer for coding agents — browse, search, trace, and export Claude Code, Codex, and Grok conversations

Verification runtime and execution observability for AI-generated web apps.

该仓库未发布描述。