#prometheus

Hourly pipeline that discovers, fetches, and classifies engineering jobs from company ATS boards — publishes a curated index to builder-jobs.

Deterministic health monitoring for LLM conversations. Detects context pressure, drift, repetition and tool anomalies without adding anything to model context.

Kubernetes observability suite: a pod/container metadata service plus a per-node agent that tails container logs, scrapes Prometheus targets, cadvisor, node metrics and journald, enriches everything with pod metadata, and exports OTLP

Local-first OpenTelemetry and Grafana diagnostic kit for Codex, with Loki logs, Tempo traces, Prometheus spanmetrics, privacy-safe derived evidence, and focused Grafana dashboards.

On-Premise RAG (продвинутая версия): vLLM/Ollama + bge-m3 + reranker + Qdrant + hybrid (BM25+RRF) + PDR + Basic Auth + Prometheus/Grafana + локальная оценка. Запускается на Ollama без GPU. Тех-задача Petrel AI (Astana Hub).

Production-oriented Kimi K3 inference control plane with checkpoint release gates, MoE capacity planning, OpenAI gateway, NVL72 deployment, benchmarks, and observability.

Production-grade LLM inference deployment on AWS using vLLM and Qwen2.5, running on NVIDIA GPU-powered K3s Kubernetes with Terraform, Helm, Prometheus, and Grafana observability.

Multi-agent LinkedIn branding system with ReAct tool-calling, human-in-the-loop approval, and full agent traces

Evidence-based Kubernetes AIOps incident analysis platform with Prometheus, Loki, rule correlation, LLM-assisted RCA, FastAPI, Docker and Helm Visibility: Public

Load test LLM inference servers with k6. TTFT, ITL, TPOT, goodput, cost, and energy metrics for any OpenAI-compatible server. Ships to Prometheus and Grafana.

Write the agent, not the chat integration. Kubernetes-native broker between Slack and streaming A2A AI agents (kagent, Google AX): threaded sessions, alert investigations, restart recovery.

Open, evidence-graded observability from agent actions to Kubernetes effects.

Zero-agent Kubernetes FinOps and pod rightsizing patch generator analyzing historical p95 metrics and cloud costs

Autonomous Incident Remediation Operator for Kubernetes workloads

Self-contained tool that runs real Timpi searches and shows live results, health metrics, and alerts on a local dashboard — one binary for Windows, macOS, Linux, and Raspberry Pi. Optional local-AI query generation (Ollama/LM Studio).

Ops platform for self-hosted infrastructure.

Evidence-driven Kubernetes root cause analysis with LangGraph-orchestrated, bounded read-only investigation and deterministic diagnosis.

Self-hosted network looking glass with remote agents: ping, traceroute, MTR, DNS, TLS and bandwidth tests, scheduled probes, Prometheus metrics and a latency mesh.