Monitoring & Observability

MCP server for cross-device AI conversation handoff and real-time device control via the Watcher Android app

Tamper-evident audit log for AI agent memory operations. Adapters for Anthropic Memory, Letta, Mastra, Mem0, LangChain, LangGraph, GBrain, and Hermes Agent (via psy-core-hermes).

Configure on-call alerting from an AI agent: recipients, groups, escalation policies, schedules.

Component health tracking and counters.

Open-source, self-hostable AI production-debugging agent for backend teams — turns incidents into sandbox-validated, evidence-backed merge requests. Bring your own LLM (OpenAI/Anthropic/local).

In-process MCP server adapter for the GraphMind live agent debugger: wrap your McpServer to stream tool / resource / prompt / sampling events and honour pause / step / inject / retry / abort gates.

OpenTelemetry instrumentation for the MCP TypeScript SDK v2 (protocol revision 2026-07-28): W3C Trace Context propagation through params._meta and spans that follow the OpenTelemetry semantic conventions for MCP.

The reliability layer for MCP tool calls — local-first policy, observability, and a dead-letter queue with replay for any stdio MCP server.

StillOnline MCP: uptime, status pages, checks. REST API for Cursor and Claude Code.

Context Optimizer MCP Server v1.6.0 - Advanced MCP Server with AI External Memory Features, Persistent Storage, Differential Indexing, Content Compression, and Prompt Packaging for Master/Worker AI

MCP server for IBM Concert Operate (AIOps) v2 API

Townhouse CLI, MCP server and SDKs: scan your app from any editor, agent or terminal, get proven fixes, track errors in the browser, Next.js, Node, Deno and edge runtimes, upload source maps, and meter provider calls

Flight recorder for Claude Code and coding agents — timeline dashboard with replayable agent-run drill-downs.

Local-first behavioral observability for Claude Code. See whether your AI coding agent is improving, stuck, or repeating itself - and why.

MCP server for cron job scheduling with systemd integration, retry logic, and observability

LLM observability for your AI Agent and LLM steps: send each execution to Verica as a trace with tool calls, tokens and cost.

Open-source CLI that breaks down where your AI coding agent burns tokens — per-section, per-tool, with cost & compressible-noise estimates. Reads local Claude Code / Codex session logs and refreshes pricing from LiteLLM.

MCP server for Equipment API - machine status monitoring, alarms, and state tracking

Enterprise code governance and AI audit platform. Detects AI drift, enforces organizational standards, and audits AI-generated code with continuous monitoring.

Structured error recovery for MCP agents.