Havuz

Introspection dashboard for the pi coding agent — tools, prompts, skills, and the system prompt injected on init.

Compact AI agent runtime control plane with governed tools, HITL approval, resumable execution, trace-driven evaluation, and SWE-bench-shape

Request-level runtime coverage attribution for Spring MVC/WebFlux applications.

A Kubernetes lab that reproduces real production incidents on a live, instrumented microservice stack — for testing root-cause-analysis tool

Economical human-readable logs and structural (event pattern) retrieval for agentic trajectories

Self-hostable incident-investigation agents for Sentry, Datadog, and Slack.

Standalone observability dashboard and developer playground for the Laravel AI SDK. Zero build steps. Telescope for your AI agents.

Detect hallucinations in LLM responses. Verify every claim against source documents using hybrid STS + NLI. Works with LangChain, LlamaIndex

Cost-efficient coding-agent runtime: prefix-aware prompt-cache routing, poisoning-safe semantic cache, budgeted context compression, request

Catch silent failures in AI agents before your users do

Runtime visibility for Python MCP servers. Captures tool calls, session lifecycle, module imports (SHA-256), and subprocess execution as str

Inspect ASP.NET Core HTTP traffic with a built-in dashboard and compare traces across environments.

Terminal fleet monitor for GPUs, NPUs, and 13 other accelerator kinds, from utilization down to which pod is using them.

Cross-platform .NET performance engineering skill for coding agents, covering CPU, memory, GC, benchmarking, concurrency, startup, native pr

Runtime behavior diffs for pull requests

Lightweight, dependency-free logging and analytics for LLM API calls — track tokens, cost, and latency to a plain JSONL file.

Real-time execution trace and cost intelligence for Claude Code

A lightweight Laravel queue monitoring package that tracks job lifecycle (processing, success, failure) across any queue driver. It provides

A Github Copilot usage analyzer for VS Code.

Local-first multi-runtime AI cockpit (CLI + desktop + MCP). War-rooms, review receipts, open multi-model coding benchmarks. MIT.

`roctop` is a small AMD ROCm GPU monitor. It shows GPU VRAM usage, utilization, temperature, and GPU processes in a refreshing terminal UI.

Lightweight SSH login observability for Linux servers. Sends a rich push notification via ntfy on every SSH login and failed attempt, and sh

A three-part toolkit for browser session capture, automated crawling, and offline reconstruction of modern web applications.

The command center for n8n automation operators: multi-instance management, real-time error tracking, AI-assisted debugging, a Code Lab, and

Audit any agent decision across its past, present, and future, on one typed graph.

Fuel gauge for AI coding agents: reads real plan limits, answers go, wait or reroute.

Self-hosted LLM gateway — route OpenAI/Anthropic/Gemini traffic by config, not code. Fallback, protocol translation, telemetry.

Mindlas catches your coding agent drifting before the bad code lands. Real-time tracking and correction for context rot, unverified done cla

OpenTelemetry tracing for DeepSeek Harness (dsh): turns each agent turn into a GenAI span tree — steps, LLM calls with TTFT, tool executions

Local monitor for Claude Code API traffic, logs, prompts, and tools

Make stochastic AI systems durable with one decorator

Read-only Kubernetes troubleshooting agent in Go (client-go) — explains CrashLoopBackOff, ImagePullBackOff, OOMKilled, Pending/Unschedulable

Community-maintained observability for self-hosted Supabase: logs, metrics, and traces.

< AI 시대에 개발자가 알아야 할 인프라 구성 배포 with 클로드 코드 >

Agents you can inspect, replay and trust. An agent framework for TypeScript and Python, built on an append-only event log.

The agentic debugger for Claude Code, Codex CLI and Gemini CLI: a token usage, cost and context-window tracker that shows what the tokens AR

One command turns every agent session already on your disk into a graph: subagents, tool calls, retries, the moments you said no. Ask your a

Lightweight cross-platform AI coding agent usage & cost tracker. Single binary, SQLite, web dashboard. | 轻量跨平台 AI 编程工具用量与费用追踪器，单二进制、SQLite 存

Agent trace analysis and context remediation plugin for Claude Code. Detects quality issues in your AI agent traces — goal drift, hallucinat

Observable diagnostics, failure attribution, metrics, and no-key replay for multi-agent runtimes.

Production-ready Java implementation of the Transactional Outbox Pattern for Spring Boot 4, Kafka and PostgreSQL, with idempotency, batch pu

Open-source, decentralized uptime monitoring — from everywhere, owned by no one.

Record-and-replay for agent decision graphs: reproduce a prod agent failure as a committed regression test, and re-run your fix without live

Skill pack that turns any coding agent (Claude Code, Codex, AGENTS.md-compatible) into a senior production engineer — FastAPI, PostgreSQL, D

Live terminal Redis traffic profiler built on eBPF. Ranks key patterns, flags footguns, reads TLS.

Enterprise AI traffic gateway — unified compliance, routing across 20+ LLM providers, semantic cache, quotas, and audit. SDK / network / OS-

SunnyDayBPF: eBPF-based post-syscall user-buffer telemetry deception research by Azizcan Daştan

CONTINUUM: Verifiable semantic recovery for long-running AI agents. Semantic checkpoints (not conversation dumps), an idempotent action ledg

A fast, keyboard-first system cockpit for Linux and macOS

Deterministic, local-only audit reports for Claude Code AI agent sessions. Rust + SQLite. Zero network calls. MCP server for agents.