Havuz

Future AGI, LLM ve AI agent uygulamalarını değerlendirme, izleme, simüle etme ve koruma işlerini self-host edilebilen tek bir platformda birleştiriyor.

Neden yükseliyor · Konu, agent uygulamalarında evaluation ve observability ihtiyacının artmasıyla örtüşüyor; 157 günlük repo yaşına karşılık 2.081 yıldız ve son 28 günde 597 commit geliştirme temposuna işaret ediyor. Farklı yazar sayısı 6; bu veriler ilginin nedenini tek başına kanıtlamaz ve yıldızlar benimseme ya da kalite ölçüsü değildir.

Ongrid, altyapı gözlemlenebilirliği ve operasyon araçlarını chat kanalları üzerinden kullanılabilen bir ops AI Agent içinde birleştiriyor.

Neden yükseliyor · 127 günde 1078 yıldız almış olması ve son 28 günde 69 commit ile 8 farklı yazarın katkısı dikkat çekiyor; bu, yalnızca tek kişinin yürüttüğü durağan bir repo olmadığını gösteren olumlu bir aktivite sinyali. Ops AI Agent ve incident response alanlarına ilgi de görünürlüğüne katkıda bulunmuş olabilir; ancak README ve bu ölçümler yükselişin nedenini veya gerçek kullanıcı benimsemesini kanıtlamıyor.

Wireshark for MCP. A transparent proxy between your AI client and MCP server. Watch every call live in your terminal, fail CI on what it fin

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.

DataBuff is an AI-native APM built on Opentelemetry，with multi-agent troubleshooting out of the box.

The semantic layer that makes enterprise data understandable to AI agents — model entities and relations once, query through SPL/MCP/REST, a

The open standard for runtime agent control — declarative hooks, policy enforcement, and observability across AI agent frameworks.

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

GPU-accelerated transparent compression S3-compatible storage gateway. Drop-in replacement for AWS S3 endpoints; cuts your S3 bill 50-80% wi

Token Efficiency For AI Agents

Local-first observability your agent reads back. TMA1 records every LLM call, then routes what it sees into the agent's next turn via hooks

Terminal monitor for live HLS, DASH, and IPTV streams. Wire probes, TR 101 290, SCTE-35, Prometheus and OpenTelemetry metrics. Rust CLI and

Self-hosted AI SRE for Kubernetes — zero-instrumentation eBPF observability plus a copilot that fixes issues through guardrailed, self-verif

A set of Claude Code and GitHub Copilot plugins providing the AI Literacy framework's complete development workflow — harness engineering, a

Observability for AI agents. See what your agent did, why it cost that much, and what to fix.

Lightweight OpenTelemetry receiver and local dashboard for LLM development — single binary, zero dependencies

Visualize Pydantic AI agent workflows from Logfire traces as an interactive HTML diagram — tools, nested sub-agents, tokens and exact cost.

Drop-in Prometheus / Loki / Tempo HTTP gateway for ClickHouse. Translate PromQL, LogQL, and TraceQL into optimized CH SQL — keep Grafana, sw

🇺🇦🇵🇱 A static analysis tool for OpenTelemetry Collector configurations. Built on OPA/Rego, it validates your pipelines, receivers, processor

Apache Airflow-compatible workflow orchestrator, re-engineered in Go: the drop-in Airflow UI and REST API on a single-binary control plane (

A distributed OpenTelemetry-native columnar datastore whose only backend is object storage.

Loki-compatible API proxy for VictoriaLogs. Use Grafana's native Loki datasource, Explore, and Logs Drilldown with VictoriaLogs. No plugin r

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

Local-first policy gateway for coding agents. Allow, review, or block MCP, shell, SQL, GitHub, and HTTP actions with scoped credentials and

Langfuse on GreptimeDB. Self-hosted LLM observability.

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

Tamper-evident evidence and verification layer for AI agents. Verify any agent's session offline with just openssl. No cloud, no lock-in.

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

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

Visual debugging, execution traces, and observability for AI agents.

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

Distributed system topology as a declared, verifiable, executable layer — change how your components connect without touching code.

K-O11y: Kubernetes Observability Platform (SigNoz + OTel + Beyla)

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

Local-first observability and evaluation for production forecasts - capture, validate, and compare forecasts with a local UI.

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