AI DevKit

v1.0.0Coding Agentsstable

Make AI coding agents follow a repeatable engineering workflow with planning, memory, verification, skills, and review. One config. All agents. Same workflow.

agent-frameworkagent-skillsaiai-agentsai-coding
Share:
1,204
Stars
0
Downloads
0
Weekly
0/5

What is AI DevKit?

AI DevKit is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to make ai coding agents follow a repeatable engineering workflow with planning, memory, verification, skills, and review. one config. all agents. same workflow.

Make AI coding agents follow a repeatable engineering workflow with planning, memory, verification, skills, and review. One config. All agents. Same workflow.

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

Features

  • Make AI coding agents follow a repeatable engineering workfl

Use Cases

Repeatable AI coding workflows
Planning, memory, verification, and review framework
codeaholicguy

Maintainer

LicenseMIT
Languagetypescript
Versionv1.0.0
UpdatedMay 21, 2026
Statushealthy
Maintenanceactive

Works with

ClaudeOpenAIwindowsmacoslinux

Installation

Manual Installation

npx ai-devkit

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 AI DevKit

AI DevKit is a CLI and MCP server that enforces a repeatable, structured engineering workflow across AI coding agents including Claude Code, Cursor, and OpenAI Codex CLI. It bundles eight built-in skills covering requirements, design, planning, implementation, TDD, debugging, documentation, and code simplification, and persists agent memory in a SQLite-backed knowledge base so context survives across sessions. A single configuration file synchronizes settings across all agents, and additional skills can be pulled from a community registry with contributions from Anthropic, Vercel, Supabase, and others.

Prerequisites

  • Node.js 18 or later installed
  • At least one AI coding agent installed: Claude Code, Cursor, or OpenAI Codex CLI
  • An MCP-compatible client that can run npx-based servers
  • Git initialized in the project directory where you run ai-devkit init
1

Initialize AI DevKit in your project

Run the init command from your project root. This creates the .ai-devkit.json master config, generates agent-specific folders (.claude/, .cursor/, .codex/), and scaffolds the docs/ai/ documentation structure.

npx ai-devkit@latest init
2

Review and customize the generated configuration

Open .ai-devkit.json to review the eight pre-installed skills (dev-lifecycle, verify, memory, tdd, structured-debug, document-code, simplify-implementation, technical-writer). Enable or disable skills to match your team's workflow.

3

Add the MCP server to your AI agent configuration

The init command populates each agent's settings.json automatically. For manual addition to Claude Code, add the server under mcpServers in your Claude configuration.

4

Install additional skills from the registry

Browse the community skill registry and install specialized skills from Anthropic, Vercel, Supabase, and other contributors. Skills are yaml files that define prompting patterns and tool sequences.

npx ai-devkit@latest init --template ./senior-engineer.yaml
5

Control running agent sessions

Use the agent subcommand to list active sessions, send instructions to a running agent, or pipe test output directly into an agent session for automated verification.

npx ai-devkit agent list
npx ai-devkit agent send "run tests and report" --id <agent-name> --wait
npm test 2>&1 | npx ai-devkit agent send --id <agent-name> --stdin

AI DevKit Examples

Client configuration

Add AI DevKit to Claude Desktop's mcpServers configuration to give Claude access to the skill and workflow enforcement tools.

{
  "mcpServers": {
    "ai-devkit": {
      "command": "npx",
      "args": ["ai-devkit"]
    }
  }
}

Prompts to try

Example prompts that leverage AI DevKit's structured workflow skills inside an AI coding agent session.

- "Follow the dev-lifecycle skill to gather requirements for a user authentication feature before writing any code"
- "Use the tdd skill to write failing tests for the payment module first, then implement until they pass"
- "Run the verify skill to confirm the build and test suite pass before marking this task complete"
- "Search the memory knowledge base for what we decided about the database schema last week"
- "Apply the structured-debug skill to reproduce and fix this null pointer exception"

Troubleshooting AI DevKit

The init command fails with a permissions error when creating .claude/ or .cursor/ directories

Run the command from your project root where you have write permissions. If running in a managed environment, check that the directories don't already exist with conflicting ownership.

Skills are not being followed by the agent — it ignores the dev-lifecycle workflow

Ensure the MCP server is listed in the agent's active settings.json and that the agent session was started after the config was written. Some agents require a restart to pick up new MCP servers.

The memory skill does not persist knowledge between sessions

AI DevKit stores memory in a SQLite file in the project directory. Verify the .ai-devkit.json config points to a writable path and that the file hasn't been deleted by a clean script.

Frequently Asked Questions about AI DevKit

What is AI DevKit?

AI DevKit is a Model Context Protocol (MCP) server that make ai coding agents follow a repeatable engineering workflow with planning, memory, verification, skills, and review. one config. all agents. same workflow. It connects AI assistants to external tools and data sources through a standardized interface.

How do I install AI DevKit?

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

Which AI clients work with AI DevKit?

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

Is AI DevKit free to use?

Yes, AI DevKit 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": { "ai-devkit": { "command": "npx", "args": ["-y", "ai-devkit"] } } }

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

Read the full setup guide →

Ready to use AI DevKit?

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