#observability

Unified observability gateway for AI agents — one MCP server for Prometheus, Loki, and any backend, with cross-signal anomaly detection and a built-in Web UI.

The official Treblle SDK for Laravel. Seamlessly integrate Treblle to manage communication with your dashboard, send errors, and secure sensitive data.

The implementation of Model Context Protocol (MCP) server for VMAnomaly

Find what broke in your agent calls. Pin it so it never ships again. Local voice-agent call forensics and regression guards.

Agent-native TypeScript framework for building MCP servers. Declarative definitions with auth, multi-backend storage, OpenTelemetry, and first-class support for Bun/Node/Cloudflare Workers.

🦖Know why your AI-built app broke — plain-English diagnosis + ready fix, in your editor. Open source. Sentry optional.

Predict rate-limit cutoffs inside your AI agent. Local MCP server + CLI that tracks Claude Max, ChatGPT Plus/Pro/Team, GitHub Copilot, Cursor plan windows and warns before you hit the cap.

Local-first Rust TUI/CLI for auditing AI coding-agent sessions: cost, tokens, latency, failures, and health｜本地优先 Rust TUI/CLI，审计 AI 编程 Agent 会话的成本、Token、延迟、失败与健康度

An ops AI Agent that understands your infrastructure, finds the root cause, and fixes it — right from Slack, Telegram, Lark or DingTalk.

CNCF sandbox project, an open source distributed time-series database with high concurrency, high performance, and high scalability

Local execution trees for TypeScript AI agents. agent-inspect helps you understand what happened inside an AI agent run — locally. It turns manual steps, tool calls, LLM calls, structured logs, failures, durations, and run metadata into readable execution trees you can inspect from the terminal. It is built for TypeScript/Node.js developers..

Error tracking and logging from PHP to Rollbar

🪢 Langfuse Ruby SDK - Instrument your LLM app and get detailed tracing/observability. Works with any LLM or framework

LangSmith C# SDK based on official LangSmith OpenAPI specification

Drop-in Prometheus / Loki / Tempo HTTP gateway for ClickHouse. Translate PromQL, LogQL, and TraceQL into optimized CH SQL — keep Grafana, swap the backend.

Read-only PostgreSQL diagnostic collector. No AI, no cloud, no write operations. Collects statistics from pg_stat views and packages them as portable snapshots.

Documentation-discovery telemetry for Claude Code — heat/cold maps, health grade, evidence-backed router fixes. 100% local, zero tokens. /tt

A high-performance, composable file system watcher for Go. Built on fsnotify with automatic recursion, 17+ filters, 18 middleware, and production-grade resilience.

该仓库未发布描述。

Streaming metrics compression engine. 100M events → 93 KB.

A framework agnostic healthcheck handler

Governed, provider-agnostic Python agent SDK: cost budgets, tamper-evident audit, and PII redaction built in.

A collection of class libraries which implement useful patterns that can be used in .NET

A command-line tool to scaffold and manage enterprise-ready AI Agents powered by the A2A (Agent-to-Agent) protocol

Write once, observe everywhere

Zipkin is a distributed tracing system

AI-powered engineering workflows — Learn from any source, Act through any tool, Report through any channel

A Python client to interact with Arize API

Full Portkey Admin API MCP server

.NET framework for A/B testing, feature flags, trial fallback, and observability.