agent▌

TypeScript SDK for deploying AI agents as HTTP services with AG-UI protocol support. \n \n Supports three adapter patterns: LangGraph for stateful graph-based workflows, LangChain for chain-based agents, and custom adapters via AbstractAgent interface \n Includes @cloudbase/agent-server for HTTP service deployment with built-in CORS, logging, and observability configuration \n Provides UI client libraries for web applications ( @ag-ui/client ) and WeChat Mini Programs ( @cloudbase/agent-ui-minip

Framework for testing LLM agents across behavioral, capability, and reliability dimensions with production-focused evaluation patterns. \n \n Covers five core evaluation areas: agent testing, benchmark design, capability assessment, reliability metrics, and regression testing \n Emphasizes statistical test evaluation (multiple runs with distribution analysis) and behavioral contract testing over single-run or string-matching approaches \n Includes adversarial testing patterns and guards against

Design LLM-facing tool schemas that prevent hallucination, silent failures, and token waste. \n \n Focuses on JSON Schema design, input examples, and error handling patterns that help LLMs use tools correctly \n Emphasizes explicit documentation and clear descriptions over implementation details, since LLMs only see the schema \n Identifies anti-patterns like vague descriptions, silent failures, and tool overload that cause agent failures \n Covers function-calling, MCP tools, and tool validatio

A lightweight CLI tool for comparing coding agents head-to-head on reproducible tasks. Every "which coding agent is best?" comparison runs on vibes — this tool systematizes it.

Design patterns for building autonomous coding agents with tool integration, permissions, and human oversight. \n \n Core agent loop architecture with think-decide-act-observe cycle; supports multi-model selection for different task types \n Tool design patterns including file operations, code understanding, terminal execution, and browser automation with schema-based definitions \n Permission system with four levels (auto, ask-once, ask-each, never) and risk assessment for approval workflows \n

Skill by ara.so — Daily 2026 Skills collection

Skill by ara.so — Daily 2026 Skills collection

Use this skill when working with applications, agents, workflows, or migrations built on Microsoft Agent Framework.

This skill covers setting up a secure email inbox that allows your application or AI agent to receive and respond to emails, with content safety measures in place.

Skill by ara.so — Daily 2026 Skills collection.