Havuz

Tamper-evident tracing, policy gates and cross-checks for AI agents: see what the agent did, and why.

🛰 Every AI coding agent on your machine, on one screen — live cost, tokens and tool calls across every provider, and a hold on anything dang

DevOps cockpit in one window: terminal with local AI, Kubernetes, SSH, databases, IDE with git, alerts, notes and KeePass. Free, open source

Self-hosted control plane & usage observability console for CLIProxyAPI (CPA) — AI providers, client keys, streaming telemetry, and model co

Replay your coding agent sessions as a map and a timeline

Your agent’s trace says “success” but the answer is wrong. Tracedown finds the step that caused it and replays the run with a fix.

Local-first telemetry collector for AI coding agents — unified OpenTelemetry events for Claude Code, Codex, Cursor and more. Token usage, co

A Claude Code mod that puts a live agent dashboard in your terminal: context and cost, advisor timeline, every permission check, subagent ca

OMA, insan onayı ve denetlenebilir çalışma kayıtlarını agent akışına dahil eden self-hosted bir TypeScript agent runtime sunuyor.

Neden yükseliyor · 180 günde 6.957 yıldızın yanı sıra son 28 günde 45 commit ve 7 farklı yazar, görünürlüğün devam eden geliştirme faaliyetiyle desteklendiğini gösteriyor. Durable approval ve offline doğrulanabilir kayıtlar, agent’ları denetlenebilir kullanma ihtiyacına doğrudan yanıt veriyor.

The black box for AI-written code. Passive decision graph linking every commit to the agent prompts behind it: drift detection, DLP audit of

Superlog, OpenTelemetry telemetry verilerini toplayıp incident’lara gruplamayı ve üretim sistemlerini araştırmayı sağlayan açık kaynaklı bir observability platformudur.

Neden yükseliyor · 117 günde 1.455 yıldız, erken dönem için belirgin ilgi gösteriyor; YC P26 ibaresi ve AI agent’lar ile observability’yi birleştiren konumlandırma dikkat çekmiş olabilir. Ancak README ve ölçümler bu ilginin kaynağını kesinleştirmiyor; son 28 günde 11 commit ve 2 farklı yazar, projenin aktif olduğunu gösterse de geniş katkıcı tabanına işaret etmiyor.

Token telemetry dashboard for AI autonomous and coding agents — tracks tokens, sessions, tool calls & reasoning across Hermes agent, Claude

TraceCrate, Claude Code, Codex ve belirli OTLP JSON trace dosyalarını tarayıcıda yerel olarak inceleyip karşılaştırmaya ve raporlamaya yarayan bir workbench'tir.

Neden yükseliyor · 17 günlük repo için 241 yıldız erken ilgiye işaret ediyor; AI agent gözlemlenebilirliği ve yerel/gizlilik odaklı inceleme ihtiyacı dikkat çekmiş olabilir. İlginin nedenini doğrulayan veri yok; son 28 günde 9 commit ve 1 farklı yazar, geliştirmenin tek kişide toplandığını gösteriyor.

top, but for the HTTP endpoints on your host — a live dashboard of the most active plaintext HTTP endpoints, right in the terminal.

Local evidence debugger and trajectory-test toolkit for TypeScript AI agents: inspect causal runs, catch wrong tool paths in CI, and share s

Real-time Kubernetes dashboard for SREs — live cluster state, drain wizard, YAML editor, just-in-time exec access, cost analysis, and AI dia

Pi coding agent extensions with code intelligence (LSP + Tree-sitter AST), semantic refactoring, code review, web/Context7 docs, and ask-use

Pan by Euraika — a self-hosted AI workspace for Hermes Agent. Chat, skills, extensions, memory, profiles, and runtime controls.

Self-hosted browser session replay built on S2 with live tailing

First LLM Studio: local-first LLM workbench for Apple Silicon + MLX. 本地优先 LLM 工作台，覆盖 Agent、对比、微调、评测与运行时遥测。

Local-first flight recorder for coding agents : replay every run as a live session map, score the context bill, and write the fix back into

Local-first analysis of Claude Code and Codex sessions: token spend, context windows, files touched, and cost.

Dashboard for monitoring and exploring Engram memory: sessions, observations, prompts, and stats

Agent reliability rulebook: the threat model and rationale behind each Agent Reliability Analyzer rule

Tired of scrolling through hundreds of near-identical posts across every social network just to find the few that actually matter. Instead o

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

Lightweight cost observability for every API call in your stack. Track LLM tokens, database ops, and external services from your terminal.

Observability module for SELISE Blocks: logs, metrics, traces and usage monitoring across services.

Schema-aware real-time API gateway for ClickHouse. Async ingestion with per-table batching, JWT/JWKS auth, Hasura-style access policies, que

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

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

Local streaming reverse proxy between AI coding agents (Claude Code, Cursor, Codex) and model APIs (Anthropic, OpenAI, Gemini, MiniMax). Met

AgentWatch — Real-time reasoning auditor and observability platform for AI agents. Catches silent failures in your agent's reasoning chain b

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.

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

TypeScript SDK for the NitroPing audit log — batching client, error capture, Hono/Express/Nitro adapters, and GenAI cost tracing.

Tends your codebase while you're away. An always-on AI engineer that reviews your logs, implements your tickets and keeps your pull requests

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

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

Graph-native studio, runtime integration, and self-hosted observability for mutable multi-agent LLM workflows.

Live code graph that fuses static analysis (tree-sitter) with OpenTelemetry runtime traces, queried over MCP so AI coding agents get real fu

Deterministic cost / loop / time budgets · full observability · crash-resumable runs · human-approval gates · a memory you own. Self-hosted.

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

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

Tree-shakable health endpoints for JS servers. Zero-dependency core, adapters for Hono, Elysia, Express, Next.js and TanStack Start, probes

Session replay and distributed tracing on one timeline - watch the user's session and the backend spans behind it.

A Symfony Web Profiler-inspired toolkit for NestJS — profile every request with a rich panel UI. Powered & maintained by Eleven Labs.

Device management & monitoring system. Go backend (Chi + SQLite, CGO-free) with an embedded SvelteKit 5 SPA — single-binary deploy. SNMP/ICM

The Platform Engineering CLI. Generate production-ready modern JS/TS architectures in seconds (starting with Next.js). Features built-in AST