#observability

A comprehensive microservices based platform to handle language based AI models inferences at scale.

Structured error protocol for Go — behavioral error classification (Rejection/Conflict/Transient/Corruption/Infrastructure), exit codes, HTTP status mapping, and diagnostic rules. Share the protocol, not the implementation.

No repository description published.

The implementation of Model Context Protocol (MCP) server for VMAnomaly

Simple, modular, and observable Go framework for backend applications.

Find what broke in your agent calls. Pin it so it never ships again. Local voice-agent call forensics and regression guards.

Governed, provider-agnostic Python agent SDK: cost budgets, tamper-evident audit, and PII redaction built in.

Zero-dependency Prometheus text-format metrics for Go

The runtime reliability layer for AI agents.

A lightweight, highly secure AI API Gateway/Proxy written in Go. Acts as transparent middleware between local AI coding clients (OpenCode/Pi/Cursor) and upstream LLM providers (Gemini, DeepSeek, Zhipu z.ai).

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.

Know what an LLM job will cost before you run it — and prove your ledger matches the provider's bill. Pre-submit estimates, hard caps, and reconciliation to actual billing. No proxy.

Open-source AI engineering platform — LLM observability, evals, metrics, prompt management, playground, and datasets. OpenTelemetry-native, self-hostable. Because "it worked when I tried it" is not an eval.

OpenTelemetry (Tracing + Metrics) module for Nest framework (node.js) 🔭

Per-project AI coding harness for Claude Code · Cursor · Codex. Profiler + 10-dim interview build a different harness for every project.

Prometheus exporter for Dagster — run, schedule, sensor, asset and code-location metrics polled from Dagster's GraphQL API. Grafana dashboard, Docker image and Helm chart included.

.NET framework for A/B testing, feature flags, trial fallback, and observability.

Make AI coding agents safe to scale autonomously: assign work, cap spend, enforce policy, verify output, roll back failures, learn from loops, and prove ROI across every repo.

Audit-log plugin for samber/do v2 — track every DI registration, invocation, and shutdown with timestamps, dependency graphs, and self-contained HTML visualization

Streaming metrics compression engine. 100M events → 93 KB.

CLI and MCP server for querying logs and metrics via Grafana datasource proxy

A type-safe abstraction layer over LLM provider SDKs for TypeScript

OpenTelemetry instrumentation plugins for JavaScript-based AI coding agents. Collect traces, tool calls, and LLM metrics from Claude Code and OpenClaw — zero code changes required.

Open-source security-first runtime for AI agents that learn and act across sessions.

A Prometheus exporter based on eBPF that gathers comprehensive container metrics

Fleetlens — local-only dashboard for Claude Code sessions. Heatmaps, timelines, parallel agent detection, PR metrics, and Ask Claude analysis.

Auto-generated Rust client for Langfuse API from OpenAPI specification