-
Notifications
You must be signed in to change notification settings - Fork 1
Home
Alessio Rocchi edited this page Jan 29, 2026
·
3 revisions
Production-grade multi-agent orchestration for Claude Code with adversarial validation, persistent memory, and real-time web dashboard.
- Installation - Complete setup guide with troubleshooting
- Quick Start Tutorial - 5-minute first agent tutorial
- Configuration Guide - Environment variables, API keys, configuration schema
- First Agent Tutorial - Interactive walkthrough
- Troubleshooting - Common issues and solutions
- Understanding Agents - What agents are, how they work
- Memory System - Persistent storage, FTS5 search, vector search
- Task Coordination - Task queue, message bus, coordinator pattern
- Sessions and Context - Session management
- MCP Integration - How aistack integrates with Claude Code
- Agent Overview - Comparison of all 11 agents
- Coder Agent - Write, edit, refactor, debug code
- Researcher Agent - Search code, analyze patterns
- Tester Agent - Write tests, run tests, coverage
- Reviewer Agent - Code review, best practices
- Adversarial Agent - Attack surface analysis
- Architect Agent - System design, technical decisions
- Coordinator Agent - Multi-agent orchestration
- Analyst Agent - Data analysis, performance profiling
- DevOps Agent - Deployment, infrastructure
- Documentation Agent - Documentation writing
- Security Auditor Agent - Security audits, compliance
- Tools Overview - Complete list of 46 tools
- Agent Tools - 6 tools for agent management
- Memory Tools - 5 tools for memory operations
- Task Tools - 8 tools for task management + 5 consensus tools
- Session Tools - 4 tools for session management
- System Tools - 3 tools for system status
- GitHub Tools - 7 tools for GitHub integration
- Review Loop Tools - 6 tools for adversarial review
- Identity Tools - 8 tools for agent identity management
- Recipes Index - Categorized recipes by difficulty
- Code Review Workflow - Complete code review pattern
- Documentation Sync - Keep docs synchronized
- Multi-Agent Collaboration - Coordination patterns
- Adversarial Testing - Step-by-step adversarial review
- Full-Stack Feature Development - End-to-end feature
- Memory Patterns - Best practices for memory
- GitHub Integration Examples - Automate GitHub workflows
- Plugin Development - Create custom plugins
- Custom Agent Types - Register your own agents
- Workflow Engine - Multi-phase workflows
- Vector Search Setup - Enable vector embeddings
- Web Dashboard - Using the React dashboard
- Programmatic API - TypeScript/JavaScript API
- System Architecture - Architecture overview
- Data Model - Database schemas
- Security Model - Security controls
- Design Decisions - Architectural decisions
- CLI Commands - Complete CLI reference
- Configuration Schema - Full config options
- TypeScript API - Programmatic API reference
- Error Codes - Common errors
- Glossary - Terms and definitions
- FAQ - Frequently asked questions
aistack is a production-grade multi-agent orchestration framework that enables you to:
- Spawn specialized AI agents - 11 agent types with distinct capabilities
- Coordinate complex tasks - Hierarchical task management with message bus
- Maintain persistent memory - SQLite with FTS5 full-text and vector search
- Integrate with Claude Code - 46 MCP tools for seamless IDE integration
- Run adversarial validation - Coder ↔ Adversarial review loops
- Monitor in real-time - React web dashboard with live updates
11 agents · 46 MCP tools · 6 LLM providers · SQLite + FTS5 · Web dashboard · Adversarial review
Claude Code ←→ MCP Server ←→ Agent Manager ←→ 11 Agent Types
↓ ↓
Memory Manager Task Queue
↓ ↓
SQLite + FTS5 Message Bus
- Multi-Agent Orchestration: Coordinate coder, researcher, tester, reviewer, adversarial, architect, coordinator, analyst, devops, documentation, and security-auditor agents
- Adversarial Review Loop: Iterative code validation with coder ↔ adversarial feedback (max 3 iterations)
- Persistent Memory: SQLite with FTS5 full-text search and optional vector embeddings
- MCP Integration: 46 tools exposed via Model Context Protocol for Claude Code
- 6 LLM Providers: Anthropic, OpenAI, Ollama, ClaudeCode CLI, Gemini CLI, Codex
- Web Dashboard: React 18 + Material-UI with real-time WebSocket updates
- GitHub Integration: Issues, PRs, repo info via gh CLI
- Plugin System: Runtime extensibility without modifying core
- Drift Detection: Semantic drift monitoring with configurable thresholds to prevent task scope creep
- Consensus Checkpoints: Human-in-the-loop approval for high-risk tasks
- Agent Identity: Persistent agent identities with lifecycle management and audit trails
- Resource Monitoring: Track and limit agent resource consumption with automatic intervention
# Install
npm install @blackms/aistack
# Initialize
npx @blackms/aistack init
# Add to Claude Code
claude mcp add aistack -- npx @blackms/aistack mcp start
# Start web dashboard
npx @blackms/aistack web startSee Installation for detailed setup instructions.
- Quick Start Tutorial - Get up and running in 5 minutes
- Understanding Agents - Learn about agent types
- Memory System - How persistent memory works
- Agent Overview - Detailed agent capabilities
- Tools Overview - All 46 MCP tools
- Programmatic API - TypeScript SDK
- Plugin Development - Extend aistack
- Custom Agent Types - Create custom agents
- Workflow Engine - Multi-phase workflows
- GitHub Repository: https://github.com/blackms/aistack
- NPM Package: https://www.npmjs.com/package/@blackms/aistack
- Issues: https://github.com/blackms/aistack/issues
- Discussions: https://github.com/blackms/aistack/discussions
Contributions are welcome! See the Contributing Guide for details.
Last updated: 2026-01-29 | Version: 1.5.3
Getting Started
Core Concepts
Agent Guides
- Overview
- Coder
- Researcher
- Tester
- Reviewer
- Adversarial
- Architect
- Coordinator
- Analyst
- DevOps
- Documentation
- Security Auditor
MCP Tools
- Overview
- Agent Tools
- Memory Tools
- Task Tools
- Session Tools
- System Tools
- GitHub Tools
- Review Loop Tools
- Identity Tools
Recipes
- Index
- Code Review
- Doc Sync
- Multi-Agent
- Adversarial Testing
- Full-Stack Feature
- Memory Patterns
- GitHub Integration
Advanced
- Plugin Development
- Custom Agent Types
- Workflow Engine
- Vector Search Setup
- Web Dashboard
- Programmatic API
- Resource Monitoring
Reference