Tag
Porch 是一款开源的本地工具，可将 Claude Code 和 Codex 的使用情况汇总为按项目分类的日/周/月报告，包含任务耗时、阻塞点、token 与 API 成本估算，并支持导出为 Markdown 到 Obsidian，数据全部保留在本地 Mac 上。
A step-by-step guide to building a Claude Code mod called run-ledger that integrates with Jev for model routing, cost estimation per run, and subagent status tracking. The post walks through connecting Jev, authoring the mod, testing hot reload and duplicate counting, and installing it as a persistent plugin.
Inferock 在 Product Hunt 发布，提供每笔 LLM API 调用的独立收据、失败调用返额以及自带密钥的调用监控与成本追踪，支持 OpenAI、Claude、Gemini 等模型的无服务器按 token 计费推理。
herdr is a Rust binary that serves as a background server for running coding agents, praised for its pane state model and agent-driven coordination, but criticized for missing cost accounting and unattended run logging.
The article explores common challenges in running multiple AI agents, such as debugging, state management, and cost, and invites community input on real-world experiences in production.
Hugging Face hub now provides receipts for Agent Traces, displaying token usage, cache hit rate, and cost for each run.
The ChessBench AI chess leaderboard has been updated with new model performances, including GPT-6 Astra achieving 2,340 Elo and ranking #11, along with other models like Claude Fable 5.1 and Gemini 3.8 Flash.
Psst is a shared shopping list app that remembers item costs by scanning receipts and comparing unit prices accurately, focusing on reliable price tracking.
ARK introduces a runtime system for AI agents that monitors and enforces policies, tracks decision costs, and is being developed into an SDK to enhance agent reliability and reduce compute waste.
Teams are encountering increasing challenges in managing AI costs as usage scales across multiple teams and models, highlighting the need for strategies to evaluate workflow costs and implement efficient tracking.
Sapiom raises $35M Series A to build infrastructure for AI agents, focusing on cost management and launching three new products. The tweet highlights capabilities like multi-vendor API key management, per-agent cost tracking, and observability.
ccusage is an open-source command-line tool that helps developers inspect token usage and costs from local coding-agent CLI data, offering daily/weekly/monthly reports, model breakdowns, and JSON export.
DepthData is a system of record for tracking and managing a company's AI spending.
agentglass is an open-source local dashboard that provides real-time monitoring, cost tracking, and fleet management for multiple AI coding agents like Claude Code, Codex, and Gemini.
A developer shares a personal experience of unexpectedly high costs from a multi-agent AI system, sparking a discussion on cost tracking and observability in agent frameworks.
Trovis is a plugin for OpenClaw that records all agent actions, costs, and deviations, presenting them in plain English for better observability.
A developer argues that most production AI agents lack essential observability like session traces and cost tracking, comparing it to deploying a web app without monitoring. The article questions whether agent observability is an unsolved problem.
A tool to help developers accurately track AI costs while coding, eliminating guesswork.
A developer argues that voice call logs must include cost and token data, not just duration and status, to properly assess voice-agent economics, sharing a lesson from a stress test where cost fields were initially null.