Easy Agent — AI skill for Claude Code
A very easy framework to make and use tool-wielding AI Agents in Typescript.
How to install Easy Agent
This entry records only its repository, not the path inside it, so there is no
exact command to give. Open zcaceres/easy-agent and copy the folder into
~/.claude/skills/, or the file into ~/.claude/agents/.
What Easy Agent does
A very easy framework to make and use tool-wielding AI Agents in Typescript.
Alternatives in AI
- Open Multi Agent — TypeScript multi-agent orchestration engine — one runTeam() call from goal to result 5.8k ★
- Anthropic SDK TypeScript — Access to Anthropic's safety-first language model APIs in TypeScript 2.1k ★
- Azure OpenAI TypeScript — Azure OpenAI for TypeScript 1.8k ★
README
easy-agent


What?
A very simple Typescript framework to build tool-wielding AI Agents.
`easy-agent` is a powerful, lightweight TypeScript framework designed for building AI agents with tool-use capabilities and prompt-caching. It supports Anthropic's Claude family of models.
Why?
- Simple: There's too much plumbing and setup in vanilla AI SDKs. You spend more time parsing JSON than iterating on your agent.
- Typescript First: TS > Python if you're already working in web apps.
- Minimal: You only need two concepts to make an awesome AI Agent: Agents and Tools. This package hides everything else and focuses on a good experience with those two concepts.
Features
- Hides configuration and plumbing behind two simple typesafe
AgentandToolclasses. - Start making a custom Agent with one function call in one file:
start-here.ts. - Sensible defaults which you can easily override
- Automatically handles the tool request/response cycle
- Supports message & stream modes
- Vigorous type-safety
- A few fun pre-baked Agents
- Use Agents in either CLI and Server Modes
- Prompt caching support
Setup
Make sure you have an ANTHROPIC_API_KEY key in your environment.
Install:
bun install
Run:
bun start
Usage
You can use `easy-agent` as project boilerplate or as a library.
Using As Project Boilerplate
Starting in CLI Mode
See `example.cli.ts` for a typical project setup in CLI Mode.
CLI Mode allows you to interact with your agents in a simple command-line interface.
Start it with `bun run start` or `bun run cli`.
Starting in Server Mode
Server Mode runs an Express server, allowing interaction with agents via HTTP requests.
See `example.server.ts` for a typical project setup in Server Mode.
Start the server:
bun run serverThe server will start on `http://localhost:3000`.
Related Skills
Easy LLM CLI
An open-source AI agent that is compatible with multiple LLM models
Free GPT4 WEB API
Not just GPT4! Easy to use, Self-Hosted, Unlimited and Free WEB API of the latest A.I. like Gemini, DeepSeek,
EasyCode
Easy Code (formerly DeepV Code) — A highly customizable AI coding assistant compatible with all major AI model
Agent Settings Backup Script
Git-versioned backup tool for AI coding agent config folders (Claude Code, Cursor, Codex, etc.) with size-base
Teampilot
A team-oriented and easy-to-use desktop client packaged based on the terminal AI Agent
Ethan Agent
A lightweight, high-performance personal AI agent. Fast async core, pluggable tools, and open integration with
Related Agents
Java API Compat Reviewer
easy-extension SDK 公共 API 兼容性审查专家。在改动可能涉及 public 类/方法/接口/异常时使用,仅审查 git diff 中的公共 API 变更。
Easy Peasy Ease Implementer
Use this agent when the user needs help implementing new features, understanding existing functionality, or ex
Dnp TDD Developer Easy
⚡ Fast TDD for routine .NET tasks: clear requirements, low-risk changes, well-defined scope. Writes both tests