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.

Real-time observability for OpenClaw agents — token usage, API cost, context health, and smart alerts. Zero config. 100% local.

Universal LLM token counting and cost management. Track spending, set budgets, compare providers.

Track AI API costs per task, model, and project. Stop guessing your spend.

Claude Code Skill — estimate and compare LLM API costs across OpenAI, Anthropic, Google, DeepSeek, Mistral. Per-token pricing, batch/caching discounts, workload templates, cross-provider comparison.

Calculate token counts for text using various LLM tokenizers to estimate API costs and context limits

An open-source, local-first framework for building multi-model, multi-agent RAG pipelines.

LLM Cost Optimizer that routes requests to cheaper models, caches semantically similar queries, and compresses prompts to reduce AI API spending by up to 70%. Python backend + Next.js dashboard.

Local, single-file HTML dashboard for Claude Code usage and estimated USD cost — token totals across all classes (input/output/cache), per-model spend at list API prices, live current-day data, MCP activity, web research, AI-clustered themes. One uv-runnable Python script.

Minimal Python library to calculate LLM API costs based on the LiteLLM model catalog.

Benchmark latency and route fit for OpenAI-compatible AI API endpoints.

AI API cost monitoring tool - Track and manage costs across multiple AI providers

Passive cost memory for AI Assisted Coding— detects paid services, tracks spend, injects budget context into your AI coding sessions.

🛡️ Cost circuit breaker for Claude Code — hard budget limits, auto-kill runaway sessions, anomaly detection. Zero dependencies.

LLM API Token Price Aggregator & Promotion Tracker. Multi-model cost comparison (OpenAI, DeepSeek, Anthropic, Qwen) normalized per 1M tokens