Observability platform for Digital Employee, providing real-time tracing, session insights, and cost analysis for multi-agent workflows

Real-time cost tracking and budget management for Claude Code. Zero setup. No Docker. No Grafana. Just install and go.

Claude Code Telemetry is a lightweight bridge that captures telemetry data from Claude Code and forwards it to Langfuse for visualization, with a secure local turnkey installation under a minute.

45% cost reduction measured. The only Claude Code plugin built from CC source analysis — cache expiry prevention, SubTask auto-delegation, zero-cost context restoration, real-time dashboard. Max Plan + API pay-per-use.

📊 CLI tool to track Claude Code usage, costs & token consumption. Analyze your AI coding assistant spending locally.

Bridge OpenClaw to EkyBot — inter-agent @mentions, cost tracking, machine health. MIT license

Real-time observability, cost tracking, and kill-switches for OpenClaw AI agent deployments — multi-provider proxy with dashboard

Interactive terminal dashboard for Claude Code token usage and cost tracking — like htop, but for Claude AI

Claude Code + Codex CLI cost, quota and rate-limit statusline — one 3-line terminal bar for multi-session AI engineers

Real-time status bar for Claude Code showing model, token usage, cost, burn rate, and time remaining. Passwordless one-line install; includes a Next.js dashboard.

Local AI routing gateway with cost tracking. Proxy OpenAI/Anthropic/Ollama/LmStudio with real-time token usage and cost analytics dashboard.

Track and visualize your claude code usage across your development machines

Cost dashboard for the pi coding agent — overview, project, session drill-down with actual and estimated spend.

MCP server providing AI agent observability — tracing, cost tracking, performance monitoring, and audit trails

Real-time token, cost, and AI limits widget with multi-device sync for Claude Code, Codex, OpenCode, Hermes, OpenClaw, and Cursor. | 為 AI Tools 打造的即時 Token、成本與限制監控桌面組件，支援多裝置同步

MCP server for @mukundakatta/agentbudget — token + dollar budget caps for AI agents over stdio. Drop into Claude Desktop, Cursor, Cline, Windsurf, Zed.

Open-source LLM observability dashboard — log every call, track costs & latency, explore traces, set alerts. Self-hostable with one SDK decorator.

Token + dollar budget caps for AI agents — throws when an LLM call would push past the ceiling. Zero deps, drop into any provider SDK.

Cost and latency tracking for AI agent runs. Wraps your LLM call, returns a per-step + per-run breakdown.

Pixel-art fleet status board for OpenClaw agents. Live cost tracking, burn-rate room glow, sub-agent minions, model switcher. Zero npm dependencies. Try it: npx clawhouse --demo