Search

Privacy bridge for LLMs — mask PII before it leaves your machine.

The official Revenium Python SDK — unified AI metering middleware for OpenAI, Anthropic, Google, Ollama, LiteLLM, Perplexity, and fal.ai.

Claude Code skill: 106 cognitive biases & behavioral principles for UX design

Claude Code skill for systematic clinical literature searches via PubMed and Scholar Gateway — produces evidence summaries, YAML reference ledgers, and Zotero exports

TeamCity from your terminal – or your AI's. Builds, logs, agents, agent terminals, queues.

把任意文本、文章链接或线程内容，转成一张可以直接发布的 HTML 信息卡。 让卡片本身完成信息传达：先可读，再有审美，再适合传播。

One command to set up a complete AI-powered development workflow with Claude Code. Persistent memory, session management, 35+ CLI tools.

An automated AI research-paper writer based off PaperOrchestra paper's implementation through a skills : five composable skills + benchmark + autoraters using any coding agent (Claude Code, Cursor, Antigravity, Cline, Aider). No API keys, no LLM SDKs.

No description available

AI agent skills for Claude Code, Cursor, Codex, and 40+ coding agents — architect, notebook, extract, cleanse

SuccessFactors OData Metadata Parser tool

Claude Code skills that replace "make it clean and modern" with named anchor recipes, design tokens, and a slop-detection checklist. Web, iOS, Android.

Library to systematically track and evaluate LLM based applications.

Library to systematically track and evaluate LLM based applications.

Library to systematically track and evaluate LLM based applications.

Library to systematically track and evaluate LLM based applications.

Library to systematically track and evaluate LLM based applications.

A TruLens extension package adding Snowflake Cortex support for LLM App evaluation.

Library to systematically track and evaluate LLM based applications.

A TruLens extension package implementing feedback functions for LLM App evaluation.