Havuz

自托管 AI Coding Agent（Rust）：常驻 Runtime 撑起终端 / 浏览器 / 手机三端；每行改动可追溯到具体 Agent 与工具调用，子 Agent 的活由退出码裁决，检查点回退、目标 token 预算与验收清单跨轮次跨重启累计，用量与反馈账本留在本地。接任

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

MCP server for Asterisk and FreeSWITCH. Lets AI assistants inspect channels, SIP registrations, trunk status and dialplan on a live PBX.

Real-time web dashboard for AI-agent behavior monitoring, built on Perplexity's Numbat. Zero-dependency Python.

Android uptime monitoring with no server and no account. Checks run on your phone; an outage arrives as a full-screen page with a looping al

What Claude Code is doing between your prompt and its answer, drawn live from the logs it already writes: every model call, every tool, each

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

The lowest-overhead LLM router. Production-ready, highly available, one OpenAI-compatible endpoint in front of 80 providers and your own vLL

A deliberately breakable three-tier platform plus a full DevOps / SRE / DevSecOps training curriculum (handbook, capstone assignment, soluti

Watch your Claude Code subagents work as a pixel-art office. Rewind any second, see what every agent cost, and turn any session into a timel

The whole eve stack. On your own machine. Durable Postgres sessions, a Docker sandbox, memory, approvals, schedules, 1,070 tool integrations

Antigravity Observability Console & Wire-Tap Module

An open‑source technical wiki connected to the systems it describes

Run cyber-AI agents against real missions in isolated environments. Record everything as OpenTelemetry evidence. Grade the evidence, not the

CloudFormation template that enables CloudWatch logs and X-Ray traces for every Amazon Bedrock AgentCore resource type (Runtime, Gateway, Me

An AI troubleshooting workbench for internal systems: it integrates ticketing and alerting systems via HTTP APIs and webhooks, connects code

Welcome to cerbere-agent guard, originally just agent guard, then rebranded after the mythical hound of the underworld. Our mission? Guardin

The trust layer for your AI agent on any platform. Trace and evaluate your agent. Full Observability. Run Model portability analysis. Autotu

Codex Usage — Local-first Codex usage analytics · 逐电脑/模型/项目/会话 Token 用量明细与 API 等价成本，支持 Windows/Linux/Mac。

🐶 An LLM-powered local-service watchdog: probe → diagnose with LLM → 4 guardrails → fix → verify → self-heal. Learns from bugs it fixes. sys

Read-only Windows diagnostics: the Event Log in plain language, blue screens explained. Offline and open source.

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

Thermal guard for Apple Silicon: pauses hot jobs with SIGSTOP and resumes them cool, optional admission queue against a thermal budget, keep

ZhuLing — Zero-config AI Agent framework for Java. One YAML to launch Agents on Spring AI + DDD, with MCP tools, full observability and a Re

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

Fast, zero-dependency access log analyzer, security threat inspector, and TUI dashboard for Caddy v2

Prometheus exporter for Dagster — run, schedule, sensor, asset and code-location metrics polled from Dagster's GraphQL API. Grafana dashboar

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

agentacct, coding agent oturumlarını yerel verilerden toplayıp yapılan işleri, kullanılan araçları, kontrolleri, token tüketimini ve tahmini maliyeti dashboard ile TUI üzerinden gösterir.

Neden yükseliyor · 65 günde 755 yıldıza ve son 28 günde 198 commite ulaşması hızlı ilgi ve aktif geliştirme sinyali veriyor; ancak aynı dönemde yalnızca 2 farklı yazar bulunması katkı tabanının dar olduğunu gösteriyor. Bu ilginin kesin nedenini ölçümlerden çıkarmak mümkün değil.

Tools for AI agents to test, fix and optimise your codebase

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

AI Agent / LLM application engineer Chinese interview question bank: 2,038 questions with reference answers

Diff your AI agent's behavior between two runs. See exactly which tool calls, args, costs and outputs changed when you swap models or edit p

Self-hosted observability platform — error tracking, performance tracing, metrics, uptime monitoring, and profiling.

Lightweight observability for multi-agent AI pipelines. Self-hosted, no cloud dependency — add two lines of Python and see real-time agent e

Engineering deterministic, production-grade systems around non-deterministic LLMs — FSM, durable execution, retries, DAGs, agent runtimes, m

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

A lightweight SmokePing-like tool for Linux, packaged in a single Go binary with a Web UI for target management—deployed in 30 seconds

Auditable AI operations agent for inventory exceptions, equipment alerts, and human-approved workflows.

A token-spend profiler and cost-regression gate for AI agents.

Docker Monitoring frontend module for Zabbix 8.0 — nodes overview, container metrics, native UI integration. Developed by MonZphere.

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

Open-source uptime monitoring for websites, APIs, SSL, and cron jobs with failure verification before alerts.

The AI Runtime for Kubernetes

Open-source incident triage: Datadog errors to Claude RCA, GitHub issues, and reviewable fix PRs

Lightweight self-hosted application monitoring for small servers. Spring Boot, Micronaut, Quarkus, SQLite-backed history, simple charts. No

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

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

Runtime observability and reliability for the Model Context Protocol ecosystem.

Self-hosted web viewer for Claude Code session transcripts — read, search, replay, and audit every session you have ever run