Observability

Frugal Tokens is a free, local, read-only web dashboard that shows exactly how many tokens each of your AI coding agent sessions consumed and what those tokens cost, across OpenCode, Claude Code, PI, Codex, and Cursor. It runs entirely on your machine, never mutates your agent databases, and surfaces hidden costs like prompt-cache misses that most developers never see. This guide walks you through installing it, pointing it at your agents, and reading the per-session explorer to cut your coding agent spend. ...

A local-first control plane agent like Swarm watches every Claude Code session on your machine live so you can see each agent’s tool calls, reasoning, token spend, and cost from one dashboard instead of cycling through terminal tabs. It keeps a ledger of who holds which task and worktree, turns CLAUDE.md “never do X” prose into real permission decisions, and runs entirely offline with no account and no telemetry. What Is a Local-First Control Plane for Coding Agents? A control plane is the management layer that decides how the agents underneath it behave. In IT operations, the control plane and the data plane are separated: the data plane does the work, while the control plane watches, meters, and governs. ra3orblade/swarm applies that same separation to AI coding agents, with one crucial twist: the entire control plane runs on your own machine. ...

MCP observability turns the Model Context Protocol into a two-way interface: AI agents don’t just call tools, they receive ground-truth telemetry from kernel tracepoints, eBPF programs, and kprobes. By exposing low-level system instrumentation through MCP servers, agents get a real-world model of the live system instead of hallucinated state — closing the observability gap that traditional APM leaves wide open. What Is MCP and Why It Needs Observability The Model Context Protocol (MCP) is an open standard that standardizes how AI agents discover and invoke tools, resources, and prompts. Instead of every agent building bespoke integrations with every service, MCP defines a common protocol: a host (the agent runtime) connects to MCP servers, which expose tools the model can call and resources it can read. ...

An agentic PostgreSQL investigation is an AI-driven workflow that explores a database to answer operational questions, and OpsGraph makes it evidence-first: it discovers an approved read-only schema, validates every SELECT against the PostgreSQL AST and policy bounds, and records a tamper-evident audit chain so no conclusion can be asserted without opening its exact evidence. Instead of giving a model direct credentials and “asking it anything,” OpsGraph constrains the investigation to bounded, read-only, auditable queries that fail closed on unsafe SQL. ...

An agent trajectory monitor watches the full sequence of steps, tool calls, decisions, and token spend an AI agent makes in real time — not just the final answer. Because AI agents consume 5-30x more tokens per task than standard chatbots, real-time trajectory monitoring has moved from a nice-to-have to a budget requirement. It lets you see whether your agent is doing the right work or just getting the right answer by chance. ...

DeepSeek Harness observability usually means standing up an OpenTelemetry collector, a tracing backend, and code instrumentation. The TencentCloud AgentObs SDK for DSH eliminates all of that: it is a DeepSeek Harness plugin that observes the harness’s native session, agent-loop, LLM-stream, and tool lifecycles and uploads GenAI trace spans directly to Tencent Cloud Log Service (CLS) using Protobuf. There is no OTLP collector, no sidecar, and no extra service to deploy. If you already run agents on Tencent Cloud, this is the fastest path from “where did my agent spend its tokens?” to a dashboards-and-alerts answer. ...

OpenTelemetry tracing for DeepSeek Harness lets you export every agent session, LLM call, and tool invocation as a standard OTLP trace tree to backends like Jaeger, Grafana Tempo, SigNoz, or Langfuse. You add it by installing a community plugin that implements the official @deepseek-ai/dsh-session-telemetry seam, configure an OTLP endpoint and a privacy mode, and then read the GenAI trace tree to debug agent loops, retries, and token usage. What is DeepSeek Harness and why it needs tracing DeepSeek Harness is the official open-source agent framework from DeepSeek, written in TypeScript with the tagline “Everything is a Plugin.” Its official repository has roughly 123,000 GitHub stars, making it one of the most popular agent harnesses in the ecosystem. The framework orchestrates multi-step agent loops: it plans, calls LLMs, invokes tools, spawns subagents, and retries failed steps. Each of those steps is a potential failure point, and without tracing you are effectively debugging a black box. ...

What is mcpsnoop? — Wireshark for MCP mcpsnoop is an open-source transparent proxy for the Model Context Protocol (MCP) that sits between your MCP client and server, capturing every JSON-RPC frame in real time. Built in Go with a Bubble Tea terminal UI, it gives developers the same kind of deep packet inspection for MCP traffic that Wireshark provides for network packets. Launched in late June 2026, mcpsnoop reached 270 GitHub stars in just three weeks and is rapidly becoming the go-to tool for MCP debugging. ...

An AI agent overspend model line mistake is a configuration bug with a billing blast radius. In my case, a missing model value silently routed routine agent steps to a pro-tier model, and the fastest fix was not prompt tuning. It was tracing requested_model, response_model, tokens, tools, retries, and config diffs in one place. What actually happened when the model line was missing? The failure was boring, which is why it was expensive. ...

OpenTelemetry is the standard way to add structured tracing, metrics, and logs to AI agents in 2026 — covering token usage, tool call latency, and multi-agent context propagation with a single SDK and vendor-neutral backends. Why Traditional Observability Fails for AI Agents Traditional APM tools like Datadog APM or New Relic were designed for deterministic request/response cycles: a user hits an endpoint, a function runs, a database query fires, a response returns. The execution path is fixed, latency is bounded, and errors are binary. AI agents break every one of these assumptions. An agent reasoning chain is non-deterministic — the same input prompt can trigger three tool calls in one run and seven in the next. Execution duration ranges from 500ms for a fast LLM call to 3+ minutes for a multi-step agent that searches the web, queries a database, and synthesizes results. Without agent-native spans, you cannot tell which tool call caused a timeout or why a particular run cost $0.40 while a similar one cost $0.03. Traditional APM measures function latency in microseconds and ignores tokens entirely. The LLM observability platform market recognized this gap — growing to an estimated $2.69 billion in 2026 and projected to reach $9.26 billion by 2030 at a 36.2% CAGR. OpenTelemetry’s GenAI Semantic Conventions fill that gap with a purpose-built span model for LLM operations, agent reasoning loops, and tool executions that traditional APM never anticipated. ...