Search

Pirate-voiced LLM chat REPL powered by Groq.

LLM-based chat/document summarization project for CSC040

Scrub PII from text before sending to LLMs. Detect and redact emails, phones, SSNs, credit cards, names, and more.

Track and limit LLM API spending in real-time. Drop-in middleware for OpenAI, Anthropic, Google, and any OpenAI-compatible API.

Prevent LLM context window overflow with token counting, smart truncation, and budget management

Validate LLM responses against schemas, types, and constraints. Catch bad JSON, missing fields, and hallucinated formats before they crash your app.

Automatic failover between LLM providers. When OpenAI is down, seamlessly switch to Anthropic, Google, or any backup.

Detect and block prompt injection attacks before they reach your LLM. Zero dependencies.

Python SDK for ZITGUARD AI — LLM guardrails made simple

Detect Indirect Prompt Injection attacks before your LLM reads them

Lightweight local LLM proxy with multiple provider management, automatic failover, privacy protection, and latency-based selection.

A (terragrunt) wrapper around a (tofu|terraform) wrapper around ....

AI-powered Git commit message generator using Claude

AI Skill 模板包 — 一键导入 AI 指令 + 组件文档 + 通用组件 + 领域样例，覆盖 Copilot/Cursor/Windsurf/Kiro 等主流 AI 编辑器

OpenCode CLI plugin that automatically downloads and keeps skills up to date.

AgentKit Preview — closed intelligence layer for agentic coding. Proprietary routing, memory, and workflow enforcement across 10+ AI coding platforms.

GitCode CLI — manage issues and PRs from the terminal

Bridge Claude Code and Codex into Feishu/Lark with isolated group sessions, local state recovery, and streamed CardKit interactions

OpenClaw skills and plugins for AI Personal Assistant agents

Spec-Driven Development toolkit for AI-powered IDEs