cc-canary: Local Drift Detection for Claude Code
A local, privacy-centric forensic tool for detecting and reporting performance drift in Claude Code sessions.
Observability
Monitoring, tracing, and auditing the behavior of software systems at runtime — including OpenTelemetry, structured logging, and tools for making AI agent decisions and actions transparent and inspectable.
Reading List
Agents Observe: Real-Time Claude Code Monitoring
A real-time observability and debugging dashboard for tracking Claude Code agent activities and hierarchies.
MCP: The Foundation for Enterprise Agentic Engineering
289
MCP is the indispensable foundation for professional agentic engineering in organizations, offering security and observability that simple CLI tools cannot provide.
Slash Claude API Costs with Automated Prompt Caching
An open-source MCP tool that automates Anthropic prompt caching to reduce token costs by 90% and provide deep usage observability.
Rudel: Open-Source Analytics for Claude Code
140
Rudel is an open-source analytics platform providing dashboards and usage insights for Claude Code coding sessions.
AAP and AIP: Observability Infrastructure for AI Agent Alignment
AAP and AIP are protocols designed to make AI agent behavior and reasoning observable through structured alignment declarations and audit traces.
Tailscale Peer Relays Reach General Availability
470
Tailscale Peer Relays are now generally available, offering high-performance, customer-deployed connectivity for restrictive network environments.
Claude Code 2.1.20 Hides Context; Users Want a Toggle, Not Verbose Mode
1085
A “simplification” that hid essential inline context backfired; users want a simple toggle to restore transparency, not an overloaded verbose mode.
Codex Security: Sandbox, Approvals, and Enterprise Controls
Secure-by-default agent: sandbox + approvals, controlled network/search, and enterprise-managed policies with optional privacy-conscious telemetry.
OTelBench: LLMs Still Can’t Reliably Instrument Distributed Tracing
144
LLMs still struggle to instrument OpenTelemetry correctly in real services, so reliable distributed tracing remains a job for human engineers.
Durable Workflows for TypeScript: Reliability and Observability with Zero Plumbing
106
A portable toolkit that turns plain async TypeScript functions into durable, observable workflows with minimal code and no infrastructure plumbing.
Standardize LLM Observability on OpenTelemetry
144
Standardize LLM observability on OpenTelemetry, enrich it with AI-specific attributes, and help evolve OTel’s GenAI semantics instead of fragmenting on multiple standards.
Next.js Makes Request‑Scoped Logging Needlessly Hard
1033
Next.js makes basic request-scoped logging painfully hard due to restrictive middleware and broken async context propagation, while SvelteKit solves this cleanly.