Search

Comprehensive AI Model Evaluation Framework with support for multiple LLM providers

Find why your AI app fails — trace, evaluate, analyze failures, and secure your LLM applications.

Model encryption and authorization extension for vLLM 0.18.0+

OpenAI client for the datapizza-ai framework

CLI, OpenClaw plugin, and agent skill for creating and trading B.fun meme tokens on BSC

企业内部 Skills 管理 CLI

FinOps cost attribution and optimization tool for LLM API usage. Scans codebases for LLM calls, estimates costs, recommends optimizations.

Static security scanner for LLM prompts — CLI tool

Topic-aware context routing engine for LLM conversations. Auto-clusters messages by topic, assembles only relevant context using hybrid retrieval (vector + BM25 + RRF) and LLM judgment.

A multi-tenant fine-tuning platform for LLMs with Tinker-compatible API

Sandboxed bash interpreter for JavaScript/TypeScript

Bring your models. We'll bring the party.

Mock server for OpenAI-compatible APIs. Test your LLM integrations with a real HTTP server.

AI-friendly architecture context manager for vibe coding. Automatically manages CLAUDE.md and enforces architecture rules.

CLI launcher for the multi-provider agent-ads Rust binary

Zero-overhead AI usage tracking for LangChain and LLM APIs

The open agent skills ecosystem

Add agent skills to your project

简约的插件化 Agent 框架

Git YapYap — AI-powered GitHub activity summarizer. See what you shipped today.