Monitoring middleware
-
@opentelemetry/instrumentation-openai
OpenTelemetry instrumentation for the `openai` OpenAI client library
-
@pm2/js-api
PM2.io API Client for Javascript
-
@posthog/ai
PostHog Node.js AI integrations
-
Actual-sync
Automated bank sync service for Actual Budget - scheduled synchronization, real-time monitoring, and multi-budget management with Telegram notifications
-
Adrian
Monitor and control AI agent behavior with open-source runtime security tools.
-
agent-monitor-for-claude
Local Windows desktop monitor for your running Claude Code agents - live status, estimated cost, model, host and one-click focus, grouped by project. Read-only and fully offline.
-
Agent-Playbook
⚗️ AI Agent 生态每天海量资讯，99% 是噪音。这个仓库只做一件事：把最新碎片信号提纯为你能直接用的架构导轨、设计模式和工程实践。
-
agent-quota
Local-first CLI and Rust library for Codex and Claude Code quota, rate-limit windows, multi-account profiles, and JSON status. Cross-platform, no telemetry.
-
AgenticLedger
Local-first flight recorder for AI agents: every LLM call, tool call, cost, and loop captured by a transparent proxy. Zero code changes.
-
ai-intel
A self-writing AI intel wiki — Claude routines write twice-daily briefs to a markdown vault, with ntfy alerts, CI health checks, and a desktop reader (dashboard · graph · files).
-
ai-intel
A self-writing AI intel wiki — Claude routines write twice-daily briefs to a markdown vault, with ntfy alerts, CI health checks, a mobile-optimized hosted web app, and a desktop reader (dashboard · graph · files).
-
AI-Metadata-Inspector
Extract AI generation metadata and prompts from image and video files directly through the Windows context menu.
-
aileron
Tamper-evident flight recorder for AI agents - hash-chained, signed audit log of every tool call, with MCP proxy policy enforcement and anomaly detection.
-
AIsland
A local-first multi-agent status island for Windows
-
akmon
Tamper-evident evidence and verification layer for AI agents. Verify any agent's session offline with just openssl. No cloud, no lock-in.
-
alertdam
Self-hosted, ChatOps-first incident management and on-call alerting for engineering teams. Single Go binary + PostgreSQL.
-
alertint-agent
Read-only Alertmanager intelligence agent — correlates alerts, triages incidents with LLMs, and exposes findings via MCP to AI coding agents
-
ampere
Observable AI cognition in Kotlin Multiplatform. Every agent decision emits a structured event — peer into the glass brain.
-
apm-bash-completion
Completion for Atom Package Manager
-
atalaya
Uptime & status page that checks from multiple regions, built on Cloudflare Workers.
Monitoring TypeScript -
aurora-cloudbank-symbolic
Secure symbolic memory vault for Aurora runtime, seeds, and exports
-
bash-pilot
CLI toolkit: SSH host management, Git profiles, env health checks, smart prompts
-
BasicallyMythos
See when Claude Code reroutes your request to a different model — and choose the fallback yourself. 123-line local proxy, zero deps.
-
bitrix-cdn
🌐 Enhance your Bitrix site with a high-performance CDN that automates image conversion to WebP, reducing load times by up to 75%.
-
bloxos
Self-hosted fleet management dashboard for AI and compute machines. Monitor GPU health, control services, open terminals — one dark-mode web UI.
Monitoring Go -
boltarr
Self-hosted network dashboard — topology, scanning, VLANs, AI analysis
-
bottom
A read-only process lifecycle flight recorder: what ran, who spawned it, and how it ended.
-
bun-microservice-gateways
This repository provides a fast and configurable gateway using Bun, designed to route HTTP requests to your microservices efficiently. With features like smart routing and built-in health checks, it simplifies local development and lightweight setups. 🐙🚀
Monitoring TypeScript -
caprock
Mission control for Claude Code — run, observe, and orchestrate your agent sessions locally. Live activity, cost & token burn, loop detection, verified multi-agent tasks.
-
ccdash
Lightweight TUI dashboard for Claude Code token usage, agent sessions, and system resources. Go.
-
changedetection.io
🔍 Detect website changes automatically and receive real-time alerts via various channels to stay informed on updates, prices, and content edits.
-
cks-runtime
Sessions, transactions, and version history for your knowledge graph. Operate without becoming the authority.
-
claudetrack
Track Anthropic Claude API tokens, forecast costs, and predict rate limits in real time with a self-hosted, zero-code tool.
-
cli-dashboard
📊 Beautiful terminal dashboard for monitoring CPU, RAM, disk, network, and Git stats. Built with TypeScript.
-
clinicaltrial-watch
ClinicalTrials.gov API를 사용하여 특정 임상시험의 변동 사항을 정기적으로 모니터링하고, 그 결과를 Quarto 기반의 웹사이트로 배포.
-
clterm
Real-time, tail -f-style viewer for Amazon CloudWatch Logs, rendered in a browser terminal (Live Tail + WebSocket fan-out)
-
comis
Open-source security-first runtime for AI agents that learn and act across sessions.
-
crumbtrail-cli
Crumbtrail SDKs and CLI — bug-context capture for coding agents. Source for the crumbtrail, crumbtrail-core, crumbtrail-node, crumbtrail-react, crumbtrail-react-native and crumbtrail-tauri npm packages.
-
crux
Typed building blocks for everything around your LLM call.
-
ctxprof
ctxprof
-
cxusage
📊 Analyze Codex daily usage from session logs, aggregating token counts by day or model. Output options include plain, Markdown, or JSON.
-
daily-watchlist
Automate investment research by tracking your watchlist to fetch prices, scan news, and generate structured daily reports using Claude Code.
-
dash0-cli
Command line utility to interact with Dash0
-
datasentry
Evidence-driven, local-first AI copilot for data quality. 39 detectors, six-dimension scoring, human-approved repair, drift engine, MCP/REST/CLI, Web UI — Apache-2.0.
-
debug-recorder-mcp
TypeScript MCP server for structured debug session capture, reproducible diagnostics, event recording, and developer workflow observability.
-
DevPulse-Dashboard
📈 Track real-time data with DevPulse-Dashboard for efficient monitoring and low-latency charting using WebSockets.
-
DevTree
DevTree
-
digitrace
本地优先的 Windows 使用统计与系统监控工具（Local-first Windows usage tracking & system monitor）：应用使用时长统计、网络/硬件实时监控、健康提醒、独立监控 + Lite 查看器、共享内存指标对外接口，数据全部本地存储不上传
Monitoring Rust -
dishwatch
Tiny bash CLI for Starlink: live terminal dashboard from the dish's local gRPC API — connection, signal, aim, GPS, power draw, 60s sparklines (ping/drop/up/down/watts). Logs reboots and dropouts so you can tell whether the dish rebooted or your Wi-Fi died. Mac-side speed test included. Tested on Starlink Mini.
-
docker-commander
Self-hosted Docker monitoring & control panel — a single Go binary with an embedded React UI. Multi-host, live logs & stats, image/volume/network management, RBAC and alerting.
-
dockgate
Self-hosted Docker control panel for your local daemon and remote hosts over SSH — manage containers, build & deploy, provision servers, monitor hosts, and get Telegram/email alerts.
-
documents
Source markdown files of Mackerel documentation hosted on https://mackerel.io
-
dsh-context-lens
See what every plugin puts into the model.
-
dsh-plugin-wiki-tools
Native DeepSeek Harness tools for an Obsidian wiki vault: wiki_query, wiki_write, and wiki_lint implement the mechanical core (path routing, delta tracking, index/log bookkeeping, health checks) of the wiki skill suite.
-
duplicacy-mcp
MCP Server for Duplicacy — monitor backup status, progress, and health from Prometheus exporter via MCP
-
EJAgent
EJAgent Core is an agent harness core with runtime control, extensibility, tool safety, context management, durable sessions, branching, and observability.
-
eve
Filesystem-first framework for durable backend AI agents that run anywhere.
-
Faro
A modern DNS control plane built on CoreDNS with local DNS, blocklists, observability, caching, and per-device network insights.
Monitoring Go -
flakemetry
OpenTelemetry-native test intelligence platform — test observability, explainable flaky-test detection, and AI root-cause analysis. Treat every test run as a trace, not a report.
-
forgeterm
Monitor AI coding agents in real-time to block unauthorized file access, network connections, and dangerous commands while enforcing system resource limits.
-
franken_node
Trust-native JavaScript/TypeScript runtime platform built on franken_engine with deterministic compatibility, migration autopilot, extension trust controls, and incident replay.
-
gotcha
Self-hosted observability platform — error tracking, performance tracing, metrics, uptime monitoring, and profiling.
-
headsup
Glanceable Claude Code and Codex state in your terminal tabs: white=idle, blue=working, orange=waiting. Multi-terminal (iTerm2, WezTerm, AI Power Term), a live status bar with Anthropic usage limits, /sfl and /nil window save-and-restore, and twelve companion skills. macOS only.
-
health-monitor-mcp
TypeScript MCP server for service health monitoring, status checks, uptime probes, and operational diagnostics across local or remote targets.
-
hiloop-interceptor
hiloop interceptor wrapper for agent harnesses - captures LLM calls, network traffic, telemetry, and stdio.
-
homelab
homelab is a self-hosted infrastructure and experimentation environment for exploring Kubernetes, networking, automation, observability, and platform engineering workflows. It documents real-world operational practices, infrastructure design decisions, and production-inspired DevOps experimentation.
-
hooktrace
Hooktrace — a programmable webhook engine with real-time visibility, intelligent retries, aggregation, and AI-powered debugging.
-
howl
⚡ Blazing-fast Go statusline HUD for Claude Code — 13 metrics, adaptive layouts, zero dependencies
-
htrBox
A scalable platform for managing VPN infrastructure with access control, traffic analytics, user and server management, and dynamic Hysteria2 node orchestration. Built for corporate and private VPN networks that require strong control, visibility, and automation.
-
hyakume
A terminal-native observability dashboard with a hundred eyes on your logs, traces, metrics, and services.
-
iBetaBot
⚡ Real-time Apple beta & RC firmware watchdog — iOS, iPadOS, macOS, tvOS & visionOS builds pushed straight to Telegram the moment they drop. Cron-ready, dependency-light, zero manual checking.
-
Incident-Investigator
Stateful MCP server for incident investigation: dynamic evidence planning, competing hypotheses, confidence scoring, timelines, blast radius, and postmortems. Works with Cursor, Claude Code, Codex, and any MCP client.
-
infra-health-checker
Declarative infrastructure health checker: HTTP, TLS, TCP, DNS checks from YAML config. Auto-reports via GitHub Actions schedule.
-
infra-lens-mcp
TypeScript MCP server for infrastructure visibility, health checks, inventory inspection, and operations-focused automation across developer environments.
-
inspector
Modern MCP Inspector for remote mcp servers with support for Apps SDK
-
jobman
A daemon-less command line job manager with flexible support for retries, timeouts, logging, notifications, and more.
-
Kaku
🚀 Deliver a fast, ready-to-use terminal tailored for AI coding to boost development efficiency.
Monitoring Rust -
keeperhub
Automate on-chain events and actions reliably and securely. Build Workflows in minutes without the need for infrastructure, code or wallet management. Get instant alerts and never miss what matters.
-
kerberos
Kerberos is a lightweight API gateway that provides: observability, routing, authN, authZ, and OpenAPI validation.
-
KnowledgeBase
Build a personal knowledge base that turns raw notes into structured wiki pages, with Q&A, health checks, and export tools
Monitoring Python -
kookr
A smart attention router for developers running multiple AI coding agents.
-
kprompt
The AI Runtime for Kubernetes
-
kubeagent
Read-only Kubernetes troubleshooting agent in Go (client-go) — explains CrashLoopBackOff, ImagePullBackOff, OOMKilled, Pending/Unschedulable with P1-infra to P2-workload reports; guarded reversible --fix; optional AI --explain via Claude API.
-
KubeAstra
AI-powered Kubernetes troubleshooting via chat or MCP
-
laravel-kick
🔗 Connect and manage your Laravel app effortlessly with an MCP server and REST API for health checks, log reading, and command execution.
-
LazySlurm
A terminal UI for monitoring Slurm HPC jobs — like htop for your cluster
Monitoring Python -
LittleControlRoom
Terminal dashboard for tracking AI work across multiple local projects
-
llm-cost-profiler
Track, visualize, and optimize LLM API spending. Monitor OpenAI & Anthropic costs per feature, detect waste, suggest savings. Zero-config Python profiler.
-
llm-drift
LLM drift detector — know within 5 min when GPT-4o, Claude, or Gemini silently changes behaviour. Open source, self-hostable.
-
llm-eval
Evaluate large language models with tools for performance and consistency scoring as part of the llm-cpp C++ infrastructure toolkit.
-
longhouse
Self-hosted mission control for CLI coding agents — one searchable timeline for Claude Code, Codex & more, across your machines, with live remote control.
-
mcp-datadog
📊 Integrate Datadog Logs, Monitors, Metrics, Incidents, and Dashboards with this Model Context Protocol (MCP) server for seamless AI assistance.
-
metagraphed
Operational metadata, health, schemas, and public interface discovery for Bittensor subnets.
-
meterbar.dev
Track your AI coding assistant usage limits from the macOS menu bar
-
MIMIGenRec
⚙️ Build and train flexible generative recommendation models with modular tools, multi-GPU support, and integration with Hugging Face and LlamaFactory.
-
mlguard
Perform pre-deployment checks for ML models to detect data drift, performance drops, and latency issues, preventing faulty deployments.
-
monitor-acn-nis2
🛡️ Monitor automatizzato ACN NIS2. Regulatory Intelligence in tempo reale per la cybersicurezza italiana.
-
Netstamp
Open-source network observability from probes you control.
Monitoring Go -
ngx-ai-devtools
Network-tab-style DevTools for LLM calls in Angular apps. See every prompt, response, token, and dollar your app spends — without leaving the browser.
-
NIE-SLA
Cloudflare-native status page and VPS telemetry platform with a Rust Agent, D1, R2, Pages and Telegram alerts.
-
node-scorecard
Network intelligence & historical diagnostics for Sentinel dVPN nodes. Reliability scores, lease tracking, "where to host" advisor — no backend, fully static, archived on Walrus.
-
novafabric
Capture, replay, diff & audit AI agent and model runs as portable, signed evidence capsules. Open-source and self-hosted — runs in your own infrastructure, from a laptop to a cluster. No SaaS, no telemetry.
-
nsauditor-ai
NSAuditor AI — Open-source, AI-powered network security scanner. 27 plugins, CVE matching, MITRE ATT&CK mapping, verified vulnerabilities, continuous monitoring, MCP integration. Zero data exfiltration. MIT licensed.
-
obs-stats
A btop-style terminal dashboard for OBS Studio — live CPU, frame pacing, encoder health, outputs, scenes and audio over obs-websocket 5.x
-
open-tender-watch
Monitor public procurement data to detect corruption risks and provide flagged cases for investigation by journalists and auditors.
-
openclaw-dashboard
Monitor and control AI agent fleets locally with real-time analytics, workflows, and secure data management without cloud dependency.
-
opscanopy.com
29 free browser-based DevOps tools — validators, converters and testers that never touch a server.
Monitoring Web -
oss-stack
oss-stack is a collection of scripts, blocklists, and labs you can run to self-host your own professional IT infrastructure.
-
otelop
Local OpenTelemetry viewer for traces, metrics, and logs — single binary, persistent DuckDB storage, browser UI.
-
ottto
Local-first observability for AI coding agents - see what Claude Code, Codex & other agents cost and do
-
pagedog
Self-hosted website change watcher. Visual picker, hourly checks, email notifications. Free forever.
-
personal-memory-bank
AI session memory framework for Claude Code and Cursor. Five structured files, the mb CLI (13 commands, 24 health checks), versioned git hooks, CI guardrails, semantic drift detection, and slash commands for code review, security scanning, and test coverage. Drop-in install for any project.
-
pgwd
Go CLI that checks PostgreSQL connection counts and notifies via Slack and/or Loki when configured thresholds are exceeded. It can also alert on stale connections.
-
polylogue
A local evidence system for AI work—unifying ChatGPT, Claude, Codex, Gemini, and agent histories into one searchable, auditable archive.
-
proxmox-homelab-automation
Shell-based automation for deploying containerized services in LXC containers on Proxmox VE. Features automated stack deployments, monitoring with Grafana/Prometheus, and comprehensive homelab management tools.
-
PulseWatch
Self-hosted uptime monitoring with Telegram alerts, AI-explained incidents, and public status pages. FastAPI + React/Vite/TS.
-
Pynput-Project
🖱️ Monitor and control mouse and keyboard inputs with the Pynput Project, utilizing Python for automation and event tracking.
-
raven
Self-hosted corporate AI assistant: 12 messengers, RAG, monitors, coding tools, RBAC. Python/TS/Go/Rust stack. Privacy-first & modular.
-
remote-claude-code
🚀 Run Claude Code on a VPS and access it from any device, allowing you to code from anywhere with ease and security.
-
reqover
Request-level runtime coverage attribution for Spring MVC/WebFlux applications.
-
resolix
🛡️ A high-performance Tailscale DNS server providing custom DNS overrides, intelligent upstream forwarding, and a premium real-time monitoring dashboard.
-
Rollback-Core
Implement deterministic rollback netcode in Unreal Engine 5 projects with this lightweight plugin for high-performance fighting game synchronization.
-
roost
top for Claude Code - live sessions, models, context, and the subagents they spawn
-
RSS-AI
📡 Automate RSS feeds, summarize articles using AI, and push updates to Telegram with a simple web interface and powerful backend.
-
Scolect-ScreenTimeApp
A Desktop app for intelligent screen time tracking, productivity analysis, and digital wellness management. Desktop screen time and productivity tracking application built with Flutter.
Monitoring Flutter -
shellfleet
One dashboard for your whole fleet - systemd, Docker, Swarm, Kubernetes, health probes, backups, remote shells. Open source, self-hosted.
Monitoring Rust -
shipyard
Shipyard 🚢 — Cross-platform Docker container management platform. Python FastAPI backend + Flutter frontend for Android, iOS, macOS, Web & OpenHarmony. Manage multiple Docker hosts, monitor CPU/GPU resources in real time, control containers & Compose projects, built-in MCP server.
-
signal-house
Signal House should make it obvious whether agent work is moving and where it is getting stuck.
Monitoring TypeScript -
SiteAgent
SiteAgent for Aura — WordPress remote management agent with safe updates, health checks, rollback, MCP tools, and Aura dashboard integration. https://my-aura.app
-
solo-saas-field-manual
📘 Ship and operate your solo SaaS with practical docs, checklists, and playbooks to handle real-world challenges effectively.
-
Spanlens
Open source LLM observability and monitoring. Drop-in proxy for OpenAI, Anthropic, and Gemini with request logging, cost tracking, and agent tracing. Self-host with one Docker command. MIT.
-
statlite
A tiny self-hosted metrics dashboard for small servers. Spring Boot Actuator monitoring with SQLite, simple charts, and no Prometheus/Grafana stack required.
-
storage_ballast_helper
Cross-platform Rust daemon that prevents disk-full incidents for AI coding workloads using predictive pressure control, safe artifact cleanup, and multi-volume ballast pools.
-
svelte-vitals
A static code-health checker for SvelteKit — SEO, Performance, Correctness, Security, and Architecture, from source. Not a runtime Web Vitals reporter.
-
swarm
Local-first control plane for AI-agent development — watch every Claude Code session live, ledger tasks/worktrees/resources, track token spend and cost, enforce rules.
-
switchback
One Rust binary for explainable AI provider routing: multi-provider fallback, encrypted credentials, budgets, quotas, and metadata-only traces — no client code changes.
-
tailscale2otel
Tailscale exporter for OpenTelemetry and Prometheus. Device fleet, network flow logs and audit logs as OTLP metrics & logs. Single Go binary, Grafana Cloud ready. Headscale supported.
-
terminal-stats
Terminal Stats is a sleek, customizable terminal dashboard displaying system stats, Git status, weather, and more. Built with Node.js, it renders beautiful ASCII art dashboards directly in your terminal with real-time updates and plugin support.
-
tetherd
The lightweight agent for the Tether ecosystem.
-
The_Watcher3.0
👁 Self-hosted Instagram monitor you run entirely from Telegram — watches 25+ public & private accounts at once, tracks 10+ profile fields, and auto-delivers new posts, reels, stories & highlights to your chat. 100% login-free. Python · FastAPI · PostgreSQL · Docker.
-
theodosia
Put an AI agent on rails: mount a Burr state machine as an MCP server so the agent can only take the next allowed step, with every step recorded and replayable.
-
timmy-tui
TIMMY — the Agent Trust OS. Local-first flight recorder + control plane for AI agent work: every run gets a signed, hash-chained receipt; replays refuse to lie. Trust the receipt, not the model.
-
tokenfuse
TokenFuse — runtime control for AI agents: per-run budgets, loop detection, burn forecast, kill-switch. Observability shows the fire; TokenFuse is the automatic extinguisher.
-
tokenpak
Local proxy that puts the right project context in front of the model before it starts working — with a receipt for what was added
-
TooGoodToGo-CLI
The only CLI for Too Good To Go (TGTG) that automates the full checkout process.
-
TripStar
Plan and manage trips using AI agents that create detailed itineraries, maps, budgets, and real-time travel information in one platform.
-
trytokka
TryTokka — AI API spend alerts (Scout). Synced spend across OpenAI, Anthropic, Gemini & more. By Acsaven.
-
ukrainian-stats-mcp-server
🇺🇦 Access Ukrainian government statistics effortlessly through a Model Context Protocol server, offering fast and flexible data integration for AI models.
-
umans-gate
LLM capture proxy with Anthropic cache_control TTL stamping, vision handoff, concurrency gating, rate limiting, and a live inspection dashboard
-
up-timer
Uptime monitoring dashboard for tracking service health, response times, and incidents.
-
upstream-radar
Scan and monitor DeepSeek Harness plugins: find exact dependency and compatibility problems, then keep a fixable report for authors and agents.
-
UsageMonitor
Windows 本地使用情况监控工具：前台会话计时/浏览器历史/社交联系人/AI编程监控/日报仪表盘（纯本地、零依赖）
-
VibeTrace
Windows 本地使用情况监控工具：前台会话计时/浏览器历史/社交联系人/AI编程监控/日报仪表盘（纯本地、零依赖）
-
vibops-mcp
83 MCP tools for GPU infrastructure + Agent FinOps — deploy LLMs, manage VMs (Proxmox/XO/vSphere), track cost per agent, enforce budgets and model policies. Works with Claude, Cursor, n8n, LangChain
-
vigil-tui
Monitor real-time power consumption, thermals, and clock speeds for CPU, GPU, and RAM directly in your terminal.
-
voicegateway
Drop-in observability and cost-control layer for LiveKit voice agents
-
watchmend
面向 Homelab 和小团队的 AI 运维哨兵：确定性规则告警、只读 LLM 诊断与降噪、可追溯事件面板和多渠道通知。
-
weather-mcp
Free, open-source MCP server giving AI assistants 17 weather tools — a one-call weather summary plus forecasts, alerts, air quality, marine, radar, lightning, rivers, wildfires, and historical data back to 1940. Ask by city name or coordinates. Built on free public APIs (NOAA, Open-Meteo). No API keys, no signup.
-
Zepeed
Zepeed is a self-hosted internet speedtest tracker for monitoring ISP performance.
Monitoring PHP -
zWorkforce
Enterprise AI Workforce Operating System — distributed control plane, durable agents, workflow automation, governance, MCP integration and AI FinOps. zWorkforce turns one or more LLM endpoints into a governed AI workforce. A tenant dispatches work to named agents; a cost-aware Luna/Terra/Sol