#observability

Agentic AI Coding Platform that enables everyone to train, design and embed custom LLMs into a custom agent. Deploy your agent into the builderforce (a workforce and hiring platform). Explore skills, personnas, content, governance and workforce agents in the marketplace.

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 AGENTS.md — no API key, one npx command.

Thin Rust wrapper around SQLx that emits OpenTelemetry spans and metrics following the database client semantic conventions.

Production intelligence layer for feature flags at scale — blast radius gating, circuit-breaker auto-rollback, Merkle-linked audit log, incident correlation, and Knight Capital–style tombstoning. Go + Python + TypeScript polyglot monorepo.

Terminal trace debugger for AI agents.

AgentlensPro — professional AI-agent observability: OTEL + local-log ingestion, burn forensics, cost analytics, burn-gate hooks. CLI + server + skills.

Опис репозиторію не опубліковано.

abide — type-safe isomorphic framework on Bun + web standards

Capability Host Protocol — make agent and tool execution visible, replayable, and ready for governance.

Cardamon is an audit tool for Prometheus that generates insight into unused metrics from Grafana and Prometheus.

Route every LLM request to the cheapest model that provably passes your quality gate — with a signed, tamper-evident receipt for every decision. Proof over prediction.

Self-hosted Laravel monitoring agent. Drop-in Nightwatch alternative, open-source.

High-performance, non-intrusive evidence capture for Go HTTP clients. Records verifiable HAR 1.2 exchanges with bounded streaming redaction, async delivery, and production-safe failure isolation.

Опис репозиторію не опубліковано.

Lifecycle event observability feature for Kestrel Sovereign — hook-driven logging with shared Prometheus registry

AI-powered root cause analysis and production investigation platform.

Deterministic security-engineering range for authoritative simulation, protocol hardening, evidence integrity, forensic replay, analytics, and reproducible verification.

Local-first cost & token tracking for Claude Code, Cursor, Codex & 23 more AI coding agents — proxy-accurate per-model spend, an MCP server your agent can query, and an opt-in team rollup. 100% local, no telemetry.

AI agent debugging, collaboration, and trace observability. Built for teams using CrewAI, OpenAI, and more.

Prometheus exporter for Meinberg LTOS devices

SqlCommenter plugin for Kysely: Trace slow database queries back to the request, route, or application code that generated them

A library that records a program's external inputs — database, HTTP, clock, randomness — and replays them, so any past run can be reproduced and debugged exactly.

Local LLM cost-tracking proxy for OpenAI, Anthropic, Gemini, and pinned OpenRouter calls with token usage, failure, and billing-integrity receipts.

Transparent logging proxy for Claude Code — audit what eats your context, with local ClickHouse/Loki/Grafana analytics

Vantage : Advanced Laravel Queue Monitoring & Insights package

Extracted TypeSpec API source for ANcpLua OpenTelemetry convention experiments

Zero-config log line enrichment for Go: auto-detects JSON, logfmt, and 20+ plain-text formats and extracts timestamp, normalized severity, message, trace/span IDs, HTTP status, and exception details — allocation-free

Sessions, transactions, and version history for your knowledge graph. Operate without becoming the authority.

Sentry-like error tracking SDK for the Smoo AI platform — browser, Node, React, and Next.js. The open-core companion to the hosted error + metrics dashboards.

Extends Ecotone with Open Telemetry integration for tracing message flow in your system