clawcache-free

Solid

Smart LLM cost tracking and caching for Python

Data & Documents 19 stars 3 forks Updated 3 months ago MIT

Install

View on GitHub

Quality Score: 75/100

Stars 20%
43
Recency 20%
50
Frontmatter 20%
70
Documentation 15%
100
Issue Health 10%
50
License 10%
100
Description 5%
100

Skill Content

# ClawCache Free - LLM Cost Tracking & Caching **ClawCache** is a production-ready Python library that helps you **track every penny** spent on LLM APIs and **automatically cache responses** to slash costs. ## ๐ŸŽฏ What You Get ### ๐Ÿ’ฐ Cost Tracking - **Automatic logging** of every LLM API call with precise token counting - **Daily CLI reports** showing spending, savings, and cache efficiency - **Multi-provider support**: OpenAI, Anthropic, Mistral, Ollama, and more - **2026 pricing** built-in for accurate cost calculations ### โšก Smart Caching - **Exact-match caching** using SQLite (fast, reliable, local) - **58.3% cache hit rate** proven in real-world scenarios - **Automatic savings** - cached responses cost $0 - **Composite cache keys** for better accuracy (model + temperature + params) ## ๐Ÿ“Š Real-World Performance Based on comprehensive simulation with **48 API calls** across 4 common use cases: | Metric | Value | |--------|-------| | **Cache Hit Rate** | 58.3% | | **Total Cost** | $0.0062 | | **API Calls Saved** | 28 out of 48 | | **Scenarios Tested** | Code Review, Data Analysis, Content Generation, QA Support | ### Scenario Breakdown | Scenario | Calls | Cache Hits | Hit Rate | |----------|-------|------------|----------| | Code Review | 12 | 7 | 58.3% | | Data Analysis | 12 | 8 | 66.7% | | Content Generation | 12 | 7 | 58.3% | | QA Support | 12 | 6 | 50.0% | ## ๐Ÿš€ Quick Start ### Installation ```bash pip install clawcache ``` ### Basic Usage ```python from c...

Details

Author
AbYousef739
Repository
AbYousef739/clawcache-free
Created
3 months ago
Last Updated
3 months ago
Language
Python
License
MIT

Integrates with

Similar Skills

Semantically similar based on skill content โ€” not just same category

Testing & QA Solid

finclaw

AI-native quantitative finance toolkit for OpenClaw. Use when: querying stock/crypto prices, running backtests, scanning stocks (US + China A-shares + Crypto), generating trading strategies from natural language, detecting market regimes, or checking backtest plausibility. Triggers: stock quote, backtest, trading strategy, market analysis, RSI, MACD, portfolio, paper trading, regime detection, A-share scanner, crypto signals, DeFi yields. NOT for: general math, non-financial data analysis, or web scraping.

16 Updated 1 months ago
NeuZhou
Data & Documents Solid

clawdfolio

Quantitative portfolio toolkit โ€” multi-broker aggregation (Longport, Moomoo/Futu), institutional risk analytics (Sharpe, Sortino, VaR, CVaR, Beta, RSI), options strategy lifecycle, 20+ finance workflows, and CSV/JSON export. Use when the user asks about portfolio analysis, risk metrics, stock quotes, DCA strategy, earnings, options, or financial data export.

11 Updated 1 months ago
YichengYang-Ethan
AI & Automation Featured

manifest

Model Router for OpenClaw. Save up to 70% by routing requests to the right model. Choose LLM fallback to avoid API rate limits, set thresholds and reduce token consumption.

6,605 Updated today
mnfst
Data & Documents Solid

notebooklm-research

Full-autopilot AI research agent powered by Google NotebookLM (notebooklm-py v0.3.4). Ingests sources (URL, text, PDF, DOCX, YouTube, Google Drive), runs deep web research, asks cited questions, and generates 10 native artifact types (audio podcast, video, cinematic video, slide deck, report, quiz, flashcards, mind map, infographic, data table, study guide). Produces original content drafts via Claude, with optional publishing to social platforms via threads-viral-agent integration. Use this skill when the user mentions: NotebookLM, research with sources, create notebook, generate podcast from articles, turn research into content, trending topic research, research pipeline, source-based analysis, cited research answers, generate slides, generate quiz, make flashcards, deep web research, create infographic, compare sources, research report, study guide, source analysis, or knowledge synthesis.

233 Updated 1 months ago
claude-world