Search

RAG evaluation with exactly 6 metrics. 3 variables, 6 relationships, nothing more.

External reasoning framework for LLMs. Cognitive drift + fieldmap knowledge injection. Qwen 7B +10% on HumanEval, zero training.

An AI skill that creates standardized specification documents before implementation. Specs first, code second.

Distill your ideal buddy into an AI Skill — OpenClaw skill installer. Import chat history, photos, or describe your dream buddy. Powered by evolink.ai

Prompt-first Bazi persona skill kernel

Synap CLI — connect OpenClaw to sovereign knowledge infrastructure

AI-powered development lifecycle loom — weave goals into shipped software

Business rules as structured data, compiled into LLM-ready markdown prompts

Quake Code AI layer with provider integration, auth, and model discovery

LLM-MAR is a compact CLI that creates LLM agents, lets them debate, answers questions, and builds workflows.

Reusable RSS digest CLI orchestration and digest engine.

巴逆逆反指標追蹤器 — 常駐排程 + CLI 雙模式

OpenAI token usage cost calculator and fetch-based call tracker utilities.

A caching layer for OpenAI API calls, designed to improve performance and reduce costs.

Usda Code - Open-source AI coding agent with terminal-first experience and multi-model support

LLM function calling reliability platform. Validate, monitor, and gate tool-call behavior.

OpenClaw skill that audits your config and rewrites it to minimize Anthropic API costs

Translate JSON locale files into multiple languages using AI providers

Enhanced Anthropic auth plugin for OpenCode - Makes OpenCode indistinguishable from Claude Code to Anthropic's API

Unofficial open source toolkit for Claude Code — AI-powered business operating system