Showing 1-20 of 894,751 packages
Token usage in, dollar totals out.
Sync Claude Code token usage to your self-hosted dashboard
OpenCode plugin that optimizes token usage by pruning obsolete tool outputs from conversation context
Base CSS endorsing semantic HTML and design token usage
Codex CLI token usage tracker (macOS-first, notify-driven).
OpenCode plugin for monitoring token usage and ecosystem analytics
OpenCode plugin for detailed token usage analysis with breakdowns by category, visual charts, and subagent cost tracking
OpenCode plugin that logs sessions, messages, tool executions, and token usage to PostgreSQL
A utility to format prompts for a cleaner presentation and optimal token usage
The Stripe Agent Toolkit enables popular agent frameworks including LangChain and Vercel's AI SDK to integrate with Stripe APIs through function calling. It also provides tooling to quickly integrate metered billing for prompt and completion token usage.
MCP server for TokenArena - Claude Code token usage global leaderboard
Dynamic Context Pruning extension for pi - intelligently removes obsolete messages to optimize token usage
Track AI coding assistant token usage and costs across Claude Code, Codex, Cursor, and more.
Codex CLI token usage tracker (macOS-first, notify-driven).
A high-performance CLI tool and visualization dashboard for tracking AI coding assistant token usage and costs across multiple platforms.
Alias for @tokscale/cli — A high-performance CLI tool and visualization dashboard for tracking AI coding assistant token usage and costs across multiple platforms.
Use local MCP servers securely with zero-trust isolation while reducing context window token usage by up to 98%.
CLI tool to monitor Z.ai token usage for Claude Code coding plans
Reduce LLM token usage by up to 50% through intelligent context pruning. Auto-supersede duplicates, manually discard/distill content, and preserve critical state.
Cost calculator for Vercel AI SDK token usage. Supports OpenAI, Anthropic, Google, xAI (Grok), and DeepSeek with long context pricing, prompt caching, and reasoning tokens.