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-data:/app/data",
"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\\data:/app/data",
"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
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)
Implementation Plan (Senior Dev Role)
Quality Validation (Code Review Role)
Progress Report (Auto-generated)
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": ["Implementation by Senior Dev role"]
}
}
// β Switch roles without losing any context!
Features:
Transform your workflow data into stunning, interactive reports:
What you get:
Role | Intelligent Purpose | Key Powers |
---|---|---|
Boomerang | Strategic Orchestration | Project setup, task creation, workflow management |
Researcher | Knowledge Gathering | Evidence-based research, feasibility analysis |
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. Beautiful report auto-generated! π
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!
Enable your code gen agents to create & run 0-config end-to-end tests against new code changes in remote browsers via the Debugg AI testing platform.
An intelligent codebase search engine that transforms local codebases into a natural language queryable knowledge base.
An AI-driven platform for frontend semantic cognition and automation.
An MCP server that enables Large Language Models to make HTTP requests and interact with web APIs. It supports automatic tool generation from OpenAPI/Swagger specifications.
Execute shell commands with structured output via a powerful CLI server.
Create crafted UI components inspired by the best 21st.dev design engineers.
Navigate your OpenTelemetry resources, investigate incidents and query metrics, logs and traces on Dash0.
Popular MCP server that enables AI agents to scaffold, build, run and test iOS, macOS, visionOS and watchOS apps or simulators and wired and wireless devices. It has powerful UI-automation capabilities like controlling the simulator, capturing run-time logs, as well as taking screenshots and viewing the accessibility hierarchy.
Obtains latest dependency details for Clojure libraries.
Share code context with LLMs via Model Context Protocol or clipboard.