Agenite

v1.0.0Coding Agentsstable

🤖 Build powerful AI agents with TypeScript. Agenite makes it easy to create, compose, and control AI agents with first-class support for tools, streaming, and multi-agent architectures. Switch seamlessly between providers like OpenAI, Anthropic, AWS

agentagentic-aiaiai-agentsai-assistant
Share:
69
Stars
0
Downloads
0
Weekly
0/5

What is Agenite?

Agenite is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to 🤖 build powerful ai agents with typescript. agenite makes it easy to create, compose, and control ai agents with first-class support for tools, streaming, and multi-agent architectures. switch seamle...

🤖 Build powerful AI agents with TypeScript. Agenite makes it easy to create, compose, and control AI agents with first-class support for tools, streaming, and multi-agent architectures. Switch seamlessly between providers like OpenAI, Anthropic, AWS

This server falls under the Coding Agents category on MCPgee, the world's largest MCP server directory with 33,000+ servers.

Features

  • 🤖 Build powerful AI agents with TypeScript. Agenite makes it

Use Cases

Build AI agents with TypeScript and streaming
Multi-agent architectures with provider switching
subeshb1

Maintainer

LicenseMIT
Languagemdx
Versionv1.0.0
UpdatedMay 9, 2026
Statushealthy
Maintenanceactive

Works with

ClaudeOpenAIwindowsmacoslinux

Installation

Manual Installation

npx agenite

Configuration

Configuration Details

Config File

claude_desktop_config.json

Performance

Response Metrics

Response Time< 200ms
ThroughputMedium

Resource Usage

Memory UsageLow
CPU UsageLow

How to Set Up and Use Agenite

Agenite is a TypeScript framework for building production-grade AI agents with first-class support for tools, streaming, multi-agent orchestration, and the Model Context Protocol. It provides a provider-agnostic abstraction layer that lets you switch between Anthropic Claude, OpenAI, AWS Bedrock, and Ollama with a single config change. The @agenite/mcp package integrates any MCP server as a tool source, making Agenite a powerful foundation for building agents that combine LLMs with web, filesystem, database, and custom MCP-powered capabilities.

Prerequisites

  • Node.js 18 or later with npm or pnpm
  • API key for your chosen provider: ANTHROPIC_API_KEY for Claude, OPENAI_API_KEY for OpenAI, or AWS credentials for Bedrock
  • TypeScript knowledge (the framework is TypeScript-first)
  • An MCP-compatible client or custom agent host to run the built agents
1

Install Agenite core packages

Install the agent runtime, tool system, and LLM abstraction. Then add the provider package for whichever LLM you want to use (anthropic, openai, bedrock, or ollama).

npm install @agenite/agent @agenite/tool @agenite/llm
# Choose a provider:
npm install @agenite/anthropic
# or: npm install @agenite/openai
# or: npm install @agenite/bedrock
2

Install the MCP integration package

Add @agenite/mcp to enable your agent to connect to any MCP server and use its tools.

npm install @agenite/mcp
3

Set your provider API key

Export the API key for your chosen provider as an environment variable before running your agent.

export ANTHROPIC_API_KEY=your_anthropic_api_key
# or: export OPENAI_API_KEY=your_openai_api_key
4

Define a tool and create an agent

Create a TypeScript file that defines a tool using the Tool class and passes it to an Agent instance with your chosen provider.

import { Agent } from '@agenite/agent';
import { Tool } from '@agenite/tool';
import { AnthropicProvider } from '@agenite/anthropic';

const calculatorTool = new Tool({
  name: 'calculator',
  description: 'Perform math operations',
  inputSchema: {
    type: 'object',
    properties: { expression: { type: 'string' } },
    required: ['expression'],
  },
  execute: async ({ input }) => ({
    isError: false,
    data: String(eval(input.expression)),
  }),
});

const agent = new Agent({
  name: 'my-agent',
  provider: new AnthropicProvider({ model: 'claude-3-5-sonnet-20241022' }),
  tools: [calculatorTool],
});

const result = await agent.execute({ input: 'What is 1234 * 5678?' });
console.log(result);
5

Connect an MCP server as a tool source

Use @agenite/mcp to connect any running MCP server and automatically expose all its tools to your Agenite agent.

import { MCPClient } from '@agenite/mcp';

const mcpClient = new MCPClient({ serverCommand: 'npx', serverArgs: ['-y', '@modelcontextprotocol/server-filesystem', '/tmp'] });
await mcpClient.connect();
const mcpTools = await mcpClient.getTools();

const agent = new Agent({
  name: 'fs-agent',
  provider: new AnthropicProvider({ model: 'claude-3-5-sonnet-20241022' }),
  tools: mcpTools,
});

Agenite Examples

Client configuration

Example package.json dependencies and TypeScript setup for an Agenite agent using the Anthropic provider and MCP integration.

{
  "dependencies": {
    "@agenite/agent": "latest",
    "@agenite/tool": "latest",
    "@agenite/llm": "latest",
    "@agenite/anthropic": "latest",
    "@agenite/mcp": "latest"
  },
  "scripts": {
    "start": "ts-node src/agent.ts"
  }
}

Prompts to try

Example agent tasks and patterns well-suited to the Agenite framework.

- Build a research agent that uses @agenite/mcp to connect a web search MCP server and summarize results
- Create a multi-agent pipeline where a planner agent delegates subtasks to specialist subagents
- Use streaming to display intermediate reasoning steps to the user in real time
- Switch from Anthropic to AWS Bedrock by swapping only the provider import and model name
- Add a DuckDuckGo search tool from LangChain via the lc2mcp adapter and connect it as an Agenite tool

Troubleshooting Agenite

Agent throws authentication errors on first run

Make sure ANTHROPIC_API_KEY (or the relevant provider key) is exported in the shell session where you run the agent, or set it in a .env file loaded before the agent initializes.

TypeScript compilation errors with Agenite packages

Agenite requires TypeScript 5.0+ and 'strict' mode. Ensure your tsconfig.json has 'strict: true' and 'target' set to 'ES2020' or later. Run 'npm install typescript@latest' if you are on an older version.

MCP tools not appearing after mcpClient.connect()

Confirm the MCP server command runs correctly in isolation (run the serverCommand manually in a terminal). Check that getTools() is awaited and the returned array is spread or passed as the full tools array to the Agent constructor.

Frequently Asked Questions about Agenite

What is Agenite?

Agenite is a Model Context Protocol (MCP) server that 🤖 build powerful ai agents with typescript. agenite makes it easy to create, compose, and control ai agents with first-class support for tools, streaming, and multi-agent architectures. switch seamlessly between providers like openai, anthropic, aws It connects AI assistants to external tools and data sources through a standardized interface.

How do I install Agenite?

Follow the installation instructions on the Agenite GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.

Which AI clients work with Agenite?

Agenite works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.

Is Agenite free to use?

Yes, Agenite is open source and available under the MIT license. You can use it freely in both personal and commercial projects.

Browse More Coding Agents MCP Servers

Explore all coding agents servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.

Quick Config Preview

{ "mcpServers": { "agenite": { "command": "npx", "args": ["-y", "agenite"] } } }

Add this to your claude_desktop_config.json or .cursor/mcp.json

Read the full setup guide →

Ready to use Agenite?

Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.

33,000+ ServersFree & Open SourceStep-by-Step Guides