Monitoring middleware
-
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.
-
AgenticLedger
Local-first flight recorder for AI agents: every LLM call, tool call, cost, and loop captured by a transparent proxy. Zero code changes.
-
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.
-
aurora-cloudbank-symbolic
Secure symbolic memory vault for Aurora runtime, seeds, and exports
-
cks-runtime
Sessions, transactions, and version history for your knowledge graph. Operate without becoming the authority.
-
clinicaltrial-watch
ClinicalTrials.gov API를 사용하여 특정 임상시험의 변동 사항을 정기적으로 모니터링하고, 그 결과를 Quarto 기반의 웹사이트로 배포.
-
daily-watchlist
Automate investment research by tracking your watchlist to fetch prices, scan news, and generate structured daily reports using Claude Code.
-
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.
-
EJAgent
EJAgent Core is an agent harness core with runtime control, extensibility, tool safety, context management, durable sessions, branching, and observability.
-
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.
-
infra-health-checker
Declarative infrastructure health checker: HTTP, TLS, TCP, DNS checks from YAML config. Auto-reports via GitHub Actions schedule.
-
KnowledgeBase
Build a personal knowledge base that turns raw notes into structured wiki pages, with Q&A, health checks, and export tools
Monitoring Python -
KubeAstra
AI-powered Kubernetes troubleshooting via chat or MCP
-
LazySlurm
A terminal UI for monitoring Slurm HPC jobs — like htop for your cluster
Monitoring Python -
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.
-
longhouse
Self-hosted mission control for CLI coding agents — one searchable timeline for Claude Code, Codex & more, across your machines, with live remote control.
-
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.
-
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.
-
polylogue
A local evidence system for AI work—unifying ChatGPT, Claude, Codex, Gemini, and agent histories into one searchable, auditable archive.
-
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.
-
roost
top for Claude Code - live sessions, models, context, and the subagents they spawn
-
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.
-
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.
-
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。
-
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