Agent skill · software engineering · aradotso
open-agent-sdk
Build and deploy autonomous AI agents in-process using Open Agent SDK, an open-source alternative to @anthropic-ai/claude-agent-sdk that works anywhere without CLI dependencies.
Why this skill is useful
Adds executable scripts and a comprehensive API for building and deploying autonomous AI agents that aren't covered by existing SDKs.
What it needs
Requires @shipany/open-agent-sdk installed locally. Requires anthropic, openrouter account access. About 7k tokens when loaded. Last updated 2026-07-09. 70 stars on the source repository.
What this skill does
Open Agent SDK Skill by ara.so — Daily 2026 Skills collection. Open Agent SDK (@shipany/open-agent-sdk) is a fully open-source, in-process AI agent framework for TypeScript/Node.js. It runs the complete Claude Code agent engine directly — no local CLI subprocess required — making it suitable for cloud servers, serverless functions, Docker containers, and CI/CD pipelines. It is API-compatible with @anthropic-ai/claude-agent-sdk. --- Installation Requires Node.js 18+. --- Authentication & Configuration Set the Anthropic API key as an environment variable: Or use a third-party provider (e.g. OpenRouter): These can also be passed programmatically via options.env or apiKey/baseURL in createAgent(). --- Core API query({ prompt, options }) — Streaming, compatible with official SDK Returns an AsyncGenerator<SDKMessage>. Drop-in replacement for @anthropic-ai/claude-agent-sdk. --- createAgent(options) — Reusable agent with session state --- Options Reference Option Type Default Description --- --- --- --- model string claude-sonnet-4-6 Claude model ID apiKey string ANTHROPICAPIKEY env API key baseURL string Anthropic API Override for third-party providers cwd string process.cwd() Working directory for file/shell tools systemPrompt string — Custom system prompt prepended to agent tools Tool[] All built-in Override the full tool list allowedTools string[] all Whitelist specific tools by name permissionMode string bypassPermissions acceptEdits, bypassPermissions, plan, default maxTurns number 100 Maximum agentic loop iterations maxBudgetUsd number — Spend cap in USD mcpServers object — MCP server configs (stdio/SSE/HTTP) agents object — Named subagent definitions hooks object — Lifecycle hooks: PreToolUse, PostToolUse, Stop thinking object — Extended thinking config env object — Environment variables passed to tools resume string — Resume prior session by session ID canUseTool function — Custom permission callback (tool, input) => boolean includePartialMessages boolean false Emi …
How to use it
Reference it in AdaL, Claude Code, Cursor or any coding agent — nothing to install:
@skills aradotso/open-agent-sdk