CostHawk Launches Public Leaderboard for Claude Code, Codex, and Cursor Token Consumption
CostHawk released a public AI Tools Leaderboard that ranks users of Claude Code, OpenAI Codex CLI, and Cursor by total token consumption. The leaderboard updates every 5 minutes and includes per-tool breakdowns by token share, operator mix (single-tool vs. multi-tool), and daily momentum. Monthly seasons reset at midnight Central Time.
Token counts, model identifiers, sync timestamps, and hashed project IDs are tracked, but the service explicitly does not store prompts, responses, or source code. Data is parsed locally from developer-tool data directories before leaving the machine, with AES-256-GCM encryption for API keys. Connection options include Admin API keys, wrapped proxy keys, or MCP telemetry. The auto-sync feature is opt-in (COSTHAWK_AUTO_SYNC=true) and defaults to off.
Connecting a Local Tool
Run the following one-liner in a terminal:
npm exec --yes costhawk@latest -- --loginThis authenticates the machine and installs the CostHawk MCP server for Claude Code, Codex CLI, Cursor, and Gemini CLI. After connecting, tokens are reported under a hashed project identifier.
The leaderboard currently shows no activity (all zeroes) because no operators have synced yet—the site notes “No leaderboard activity yet” and “LOADING DATA SHOWING 0 OF 0 OPERATORS.” Monthly rankings will become populated as users opt in and sync.
📖 Read the full source: HN AI Agents
👀 See Also
UK Sovereign LLM Inference: Relax.ai Launches Public Docs
Relax.ai released docs for UK sovereign LLM inference, redirecting to /docs/getting-started/introduction. The service was shared on HN with 104 points.
DuckDB’s Quack Protocol Enables Client-Server with Multiple Concurrent Writers
DuckDB introduces the Quack remote protocol, allowing two DuckDB instances to communicate as client and server, supporting concurrent writers and leveraging HTTP for transport.
Membase: External Memory Layer for AI Assistants Across Tools
Membase is an external memory layer that extracts and stores conversation context in a knowledge graph, then injects relevant memories into new chats across Claude, ChatGPT, Cursor, Gemini, and other AI tools. It's currently in private beta with all features free.
Queuelo: A Lightweight Approval API for LLM Agents
Queuelo is a simple API layer that lets LLM agents pause before irreversible actions. Agents POST action requests, you get notified to approve or reject, and the agent receives the answer via webhook.