#opentelemetry

🦀 Ultra-minimalist, high-resilience LLM routing gateway in Rust. OpenAI-compatible with auto-retry, backoffs, circuit breakers, SIGHUP hot-reloads, and open telemetry. Ideal for free provider surfing.

Zero-config, OTLP-native flight recorder for your backend. Records every request, query, job, and exception — correlated — into a beautiful TUI, a JSON CLI, and an MCP server your coding agent can drive. Local-first.

Rust-core agentic framework with durable journal, exactly-once replay, Ed25519 A2A identity, and MCP tool server. Bindings for Go, Python, TypeScript, .NET, and Java via C ABI.

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

Spring AI chat app that queries Grafana over MCP and exports its own telemetry to the official OpenTelemetry Collector. Notes on where Spring AI diverges from the GenAI semantic conventions.

AI Runtime Meter gives developers a live token, cache & cost meter for Claude Code. Shows tokens, cache, model, source , cost and session totals per request. Run from any terminal or IDE.

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

Autonomous Claude Code CI agent in a rootless Podman sandbox — GitLab CI & GitHub Actions, two personalities (read-write Agent, read-only Advisor), OpenTelemetry audit to Elastic, Helm chart for AKS/OpenShift.

Query billions of AI events by what they mean. PrismDB is a semantic event store: columnar analytics, similarity search, and meaning-based clustering over your LLM and agent telemetry — in one engine, one SQL query, at full retention.

Local-first AgentOps flight recorder and capability firewall for MCP-based coding agents with OpenTelemetry traces.

Self-hosted telemetry stack for AI coding tools (Claude Code, Codex): OTLP ingest, VictoriaMetrics/Loki storage, Grafana dashboard for token usage & cost

Autonomous coding agent that fixes buggy repos by iterating against their pytest suite in an isolated Docker sandbox provider-agnostic LLM layer, 22-task eval harness, and OpenTelemetry→Langfuse tracing.

Open measurement infrastructure for the Agent Capability Economy — how AI agents discover, choose, use, and derive value from software capabilities (Reach → Choice → Use → Utility → Value). A proposed open measurement standard.

OpenTelemetry observability and privacy-aware failure replay for production AI agents.

The Trust Stack for Agent Apps — independently installable Python libraries that make AI agents reliable, auditable, and accountable. Because agent failures are trust failures.

Predict rate-limit cutoffs inside your AI agent. Local MCP server + CLI that tracks Claude Max, ChatGPT Plus/Pro/Team, GitHub Copilot, Cursor plan windows and warns before you hit the cap.

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