Embeds intelligent guidance into AI workflows to organize development and ensure quality.
Transform your AI agent from chaotic coder to intelligent workflow orchestrator with three powerful capabilities:
NPM Package β’ Docker Hub β’ Website
Add to your MCP client config
{
"mcpServers": {
"anubis": {
"command": "npx",
"args": ["-y", "@hive-academy/anubis"],
"env": {
"PROJECT_ROOT": "C:\\path\\to\\projects"
}
}
}
}
For Unix/Linux/macOS (mcp.json):
{
"mcpServers": {
"anubis": {
"command": "docker",
"args": [
"run",
"--rm",
"-i",
"-v",
"${PWD}:/app/workspace",
"-v",
".anubis:/app/.anubis",
"hiveacademy/anubis"
]
}
}
}
For Windows (mcp.json):
{
"mcpServers": {
"anubis": {
"command": "docker",
"args": [
"run",
"--rm",
"-i",
"-v",
"C:\\path\\to\\your\\project:/app/workspace",
"-v",
"C:\\path\\to\\your\\project\\.anubis:/app/.anubis",
"hiveacademy/anubis"
]
}
}
}
Once you get the mcp server running you need to initialize the rules (custom-modes) for the agent you are using
Supported Agents: cursor
β’ copilot
β’ roocode
β’ kilocode
Please initialize Anubis workflow rules for [your-agent-name] by calling the init_rules MCP tool
Begin a new workflow for [your-project] with Anubis guidance
1- install the MCP server:
{
"mcpServers": {
"anubis": {
"command": "npx",
"args": ["-y", "@hive-academy/anubis"],
"env": {
"PROJECT_ROOT": "C:\\path\\to\\projects"
}
}
}
}
2- then make sure you are on Code mode and ask it to generate the custom Anubis mode for you
Please initialize Anubis workflow rules for roocode by calling the init_rules MCP tool
3- reload the window and you should see the custom mode in the modes dropdown list. activate it and ask it to create your first task
4- also if you don't have a memory bank files, ask it to generate them for you as the first task.
For Cursor users, here's a complete setup example:
Cmd/Ctrl + ,
)"anubis": {
"command": "npx",
"args": ["-y", "@hive-academy/anubis"],
"env": {
"PROJECT_ROOT": "C:\\path\\to\\projects"
}
}
Please initialize Anubis workflow rules for cursor by calling the init_rules MCP tool
.000-workflow-core.mdc
Hint: an important first step task is to generate memory-bank files Ask the agent to
Please create a task to analyze codebase and generate memory-bank files (ProjectOverview.md, TechnicalArchitecture.md, and DeveloperGuide.md)
To install the mcp server use this command claude mcp add anubis npx -y @hive-academy/anubis
make sure you are on the poject root you want to install this into.
To make sure it's installed correctly run claude mcp list
you should see a server with name anubis
.
now you will need to do a very important step:
rules
and file name anubis-rules.md
.Anubis Workflow @rules/anubis-rules.md
225% Completion Rate - Exceeded target goals by migrating 9 services (target: 4 services)
Successfully Migrated Services:
workflow-guidance.service.ts
- Enhanced testability and maintainabilitystep-progress-tracker.service.ts
- Clean state managementworkflow-bootstrap.service.ts
- Simplified bootstrap processprogress-calculator.service.ts
- Pure business logic functionsstep-query.service.ts
- Flexible data access strategiesstep-execution.service.ts
- Reliable execution trackingrole-transition.service.ts
- Consistent role managementexecution-data-enricher.service.ts
- Efficient data aggregationworkflow-guidance-mcp.service.ts
- Standardized MCP operations95% Type Safety - Enhanced TypeScript compliance across the entire codebase
Zero Compilation Errors - Complete elimination of TypeScript build issues
75% Maintainability Improvement - Cleaner separation of concerns through repository pattern
Multi-Agent Support - Comprehensive template system for:
Database Optimization - 434,176 β 421,888 bytes (optimized storage)
Enhanced Query Performance - Repository pattern enables efficient data access
Improved State Management - ExecutionId-based workflow tracking
// Example: Service with Repository Pattern
@Injectable()
export class WorkflowGuidanceService {
constructor(
@Inject('IProjectContextRepository')
private readonly projectContextRepository: IProjectContextRepository,
@Inject('IWorkflowRoleRepository')
private readonly workflowRoleRepository: IWorkflowRoleRepository,
) {}
// 75% maintenance reduction through abstraction layer
}
Repositories: WorkflowExecution β’ StepProgress β’ ProjectContext β’ WorkflowBootstrap β’ ProgressCalculation β’ WorkflowRole
Your AI agent receives step-by-step intelligent rules for every development task:
// Before Anubis: Chaotic, directionless coding
"Create a user authentication system" β Where do I start?
// With Anubis: Intelligent guidance at every step
"Create a user authentication system" β
Requirements Analysis (Researcher Role)
System Architecture (Architect Role)
Enhanced Implementation with Subtasks (Senior Dev Role)
Quality Validation (Code Review Role)
Delivery Preparation (Integration Engineer Role)
Benefits:
Never lose context when switching between roles or continuing tasks:
// Seamless context preservation across transitions
{
"currentRole": "architect",
"completedSteps": ["requirements", "design"],
"context": {
"decisions": ["JWT for auth", "PostgreSQL for storage"],
"rationale": "Scalability and security requirements",
"nextSteps": ["Enhanced Implementation with Subtasks by Senior Dev role"]
}
}
// β Switch roles without losing any context!
Features:
Role | Intelligent Purpose | Key Powers |
---|---|---|
Product Manager | Strategic Orchestration | Project setup, task creation, workflow management |
Architect | System Design | Technical architecture, implementation planning |
Senior Developer | Code Manifestation | High-quality implementation, testing |
Code Review | Quality Guardian | Security validation, performance review, approval |
// 1. Agent receives intelligent guidance
const guidance = await get_step_guidance({
executionId: 'auth-system-123',
roleId: 'senior-developer'
});
// 2. Anubis provides structured rules
{
"guidance": {
"step": "Implement JWT authentication",
"approach": [
"1. Create User model with Prisma",
"2. Implement password hashing with bcrypt",
"3. Create JWT token generation service",
"4. Add authentication middleware"
],
"qualityChecklist": [
"SOLID principles applied",
"Unit tests coverage > 80%",
"Security best practices",
"Error handling implemented"
],
"context": {
"previousDecisions": ["PostgreSQL", "JWT strategy"],
"nextRole": "code-review"
}
}
}
// 3. Agent executes with confidence and reports
await report_step_completion({
result: 'success',
metrics: {
filesCreated: 8,
testsWritten: 15,
coverage: 85
}
});
// 4. Quality delivery complete! β
Enterprise-Grade Architecture:
Production Ready:
# Development setup
npm install && npm run db:init && npm run start:dev
# Quality checks
npm run test && npm run lint
Standards: MCP compliance β’ SOLID principles β’ Domain-driven design β’ Evidence-based development
MIT License - see LICENSE file for details.
Transform your AI workflows from chaotic to intelligent. Give your agents the rules of the ancients with modern MCP-compliant architecture.
Ready to ascend? Add Anubis to your MCP config now!
A GraphQL server that supports the Model Context Protocol (MCP), enabling Large Language Models (LLMs) to interact with GraphQL APIs through schema introspection and query execution.
Provides Go language updates and best practices in a structured Markdown format for LLM coding agents.
A self-hosted MCP Server registry for private AI agents, supporting both PostgreSQL and SQLite databases.
A starter project with setup instructions and example MCP servers, including a weather server.
Installs other MCP servers from their source repositories, requiring npx for Node.js and uv for Python.
Generate images using Amazon Nova Canvas with text prompts and color guidance.
Query A/B test data using the Hackle API.
A simple note storage system with tools for adding notes and generating scripts from them.
Run Postman collections using Newman, with support for environment and global variables.
An MCP server for interacting with Autodesk Civil 3D, requiring a companion plugin and Node.js 18+.