JSPM

  • ESM via JSPM
  • ES Module Entrypoint
  • Export Map
  • Keywords
  • License
  • Repository URL
  • TypeScript Types
  • README
  • Created
  • Published
  • Downloads 2534
  • Score
    100M100P100Q103425F
  • License Apache-2.0

AI Agent Orchestration Platform

Package Exports

    This package does not declare an exports field, so the exports above have been automatically detected and optimized by JSPM instead. If any package subpath is missing, it is recommended to post an issue to the original package (@defai.digital/automatosx) to support the "exports" field. If that is not possible, create a JSPM override to customize the exports field for this package.

    Readme

    AutomatosX

    AI Agent Orchestration for Claude Code

    Transform Claude Code into a multi-agent powerhouse with persistent memory, intelligent delegation, and zero-cost knowledge management.

    npm version License TypeScript Tests

    Status: โœ… Production Ready ยท v5.0.8 ยท October 2025


    ๐ŸŽฏ Built for Claude Code

    AutomatosX extends Claude Code with specialized AI agents that remember context, delegate tasks, and collaborate autonomously.

    # In Claude Code, simply use /ax
    /ax run paris "Design authentication system with JWT"
    /ax run sofia "Implement the auth design"  # Sofia auto-receives Paris's design from memory
    /ax memory search "authentication"          # Instant search of all past decisions

    The result: Claude Code becomes a learning, coordinated team instead of a stateless assistant.


    ๐Ÿ’ก Why AutomatosX?

    The Problem with Stateless AI

    Traditional AI assistants (ChatGPT, vanilla Claude):

    • โŒ No memory between conversations
    • โŒ You repeat context every time
    • โŒ No coordination between tasks
    • โŒ Knowledge disappears after each session

    AutomatosX changes this:

    • โœ… Persistent memory: < 1ms search, zero cost, 100% local
    • โœ… Multi-agent delegation: Agents coordinate automatically
    • โœ… Context retention: Never explain the same thing twice
    • โœ… Knowledge accumulation: Your team gets smarter over time

    Real-World Impact

    Without AutomatosX:

    Day 1: You explain architecture to Claude โ†’ Response lost
    Day 2: You ask to implement โ†’ You re-explain architecture
    Day 3: Different task โ†’ You re-explain everything again

    With AutomatosX:

    Day 1: Paris designs architecture โ†’ Saved to memory
    Day 2: /ax run sofia "implement auth" โ†’ Sofia finds Paris's design automatically
    Day 3: /ax run steve "security audit" โ†’ Steve has full context from Day 1-2

    Time saved: Hours per week. Quality: Consistent. Cost: $0.


    ๐Ÿš€ What's New

    v5.0.8 (October 2025): Critical Fixes - Timeout & Memory

    • CRITICAL FIX: Multi-stage agents now respect --timeout flag
    • CRITICAL FIX: Memory system enforces maxEntries and autoCleanup limits
    • Timeout support: AbortSignal properly passed to all stage executors
    • Memory limits: Automatic cleanup prevents database growth issues
    • 100% backward compatible: Drop-in replacement for v5.0.7

    v5.0.6: File Operation Tools Enabled v5.0.5: Provider Parameters & Version Management v5.0.4: Memory saving now works automatically v5.0.3: Special character support in memory search v5.0.0: Agent template system for quick agent creation

    ๐Ÿ“‹ Full Changelog | ๐ŸŽ‰ Release Notes


    ๐Ÿง  Core Value: Persistent Memory

    AutomatosX remembers everything. Every agent conversation is automatically saved and searchable.

    How It Works

    // Automatic memory saving
    /ax run paris "Design calculator with add/subtract"
    โ†’ Task + Response saved to SQLite FTS5
    
    // Automatic memory retrieval
    /ax run sofia "Implement the calculator"
    โ†’ Memory searches "calculator" automatically
    โ†’ Sofia receives: "# Relevant Context from Memory: Paris's design..."
    โ†’ Sofia implements WITHOUT you repeating the spec

    The Technology

    • SQLite FTS5: Built-in full-text search
    • < 1ms search: 62x faster than v3.x vector search
    • $0 cost: No embedding APIs, no cloud calls
    • 100% local: Your data never leaves your machine
    • Automatic injection: Relevant context added to every agent

    Benefits

    โœ… Cross-day continuity: Pick up where you left off โœ… Cross-agent knowledge: All agents share the same knowledge base โœ… Learning from history: Agents avoid past mistakes โœ… Zero cost scaling: 10,000 entries = ~10MB, still < 1ms search

    Learn more: Memory System Guide | Memory Tutorial


    ๐Ÿค Core Value: Multi-Agent Orchestration

    Agents coordinate automatically. Natural language delegation creates complex workflows without manual orchestration.

    How It Works

    // Product Manager analyzes and delegates
    /ax run paris "Build authentication feature"
    
    Paris response:
      "I'll design the auth system with JWT + OAuth2.
    
       @sofia Please implement the JWT authentication API based on this design.
       @steve Please audit the implementation for security issues."
    
    // AutomatosX automatically:
    // 1. Sofia receives full spec, implements code
    // 2. Steve receives spec + code, performs audit
    // 3. Results aggregated back to Paris

    The Technology

    • 7 delegation syntaxes: @mention, DELEGATE TO, Please ask, etc.
    • Cycle detection: Prevents infinite loops
    • Depth limits: Default 2 levels (configurable)
    • Session tracking: Who did what, when
    • Workspace isolation: No file collisions

    Benefits

    โœ… Automatic coordination: No manual task switching โœ… Parallel execution: Multiple agents work simultaneously โœ… Transparent workflows: Full delegation chain visible โœ… Context preservation: Every agent has complete context

    Learn more: Multi-Agent Orchestration Guide


    ๐ŸŽญ 15 Specialized Agents, 4 Professional Teams

    Every agent optimized for their domain with the best AI provider:

    ๐Ÿ‘ฅ Core Team (OpenAI)

    General assistance and code generation

    • Alex - Versatile assistant for general tasks
    • Sofia - Senior software engineer (clean code, TDD, pragmatic)
    • Ryan - Code reviewer (quality, security, performance)
    • Danny - Debugger specialist
    • Wendy - Technical writer

    ๐Ÿ’ป Engineering Team (Claude)

    Deep reasoning for technical work

    • Bob - Backend expert (API design, databases, microservices)
    • Frank - Frontend specialist (React, UX, accessibility)
    • Oliver - DevOps engineer (infrastructure, CI/CD, cloud)
    • Steve - Security expert (threat modeling, security audit)
    • Queenie - QA specialist (testing strategies, test automation)

    ๐Ÿ“Š Business Team (Gemini)

    Strategic thinking and analysis

    • Eric - CEO (business strategy, organizational leadership)
    • Tony - CTO (technology strategy, technical leadership)
    • Daisy - Data Analyst (data analysis, ML, statistical modeling)

    ๐ŸŽจ Design Team (Gemini)

    Creative and design work

    • Paris - Product Manager (product strategy, user research)
    • Debbee - UX/UI Designer (user experience, visual design)

    ๐Ÿ“– Complete Agent Directory


    โšก Quick Start

    Installation

    npm install -g @defai.digital/automatosx

    In Claude Code

    # Initialize (first time only)
    /ax init
    
    # Run agents
    /ax run paris "Design REST API for users"
    /ax run sofia "Implement the API"           # Auto-receives Paris's design
    /ax run queenie "Write tests for the API"    # Auto-receives design + implementation
    
    # Search memory
    /ax memory search "API design"
    /ax memory list --agent paris
    
    # Manage agents
    /ax agent list
    /ax agent show sofia
    /ax agent create backend --template developer

    That's it! Agents now remember everything and coordinate automatically.

    ๐Ÿ“– Full Installation Guide | Quick Start Tutorial


    ๐Ÿ“š Documentation

    Getting Started

    Core Features

    Tutorials

    Reference


    ๐Ÿ”ฌ The Technical Advantage

    Feature Traditional AI Chat Claude Code Claude Code + AutomatosX
    Memory No No โœ… SQLite FTS5 (< 1ms)
    Cost $20/month Included โœ… $0 (100% local)
    Multi-Agent No No โœ… 15 specialized agents
    Coordination Manual Manual โœ… Automatic delegation
    Context Retention Copy-paste Session only โœ… Persistent (days/weeks)
    Knowledge Sharing No No โœ… Cross-agent memory
    Privacy Cloud Claude servers โœ… 100% local data
    Speed Web UI Terminal โœ… Instant CLI

    ๐Ÿ’ผ Real-World Use Cases

    ๐Ÿ—๏ธ Feature Development

    /ax run paris "Design user authentication feature"
    # Paris creates spec โ†’ Saved to memory
    
    /ax run sofia "Implement auth based on spec"
    # Sofia auto-receives spec โ†’ Implements code
    
    /ax run steve "Security audit the auth implementation"
    # Steve auto-receives spec + code โ†’ Performs audit
    
    /ax run wendy "Document the auth system"
    # Wendy auto-receives everything โ†’ Creates docs

    Result: 4-step workflow, zero context re-explanation, complete audit trail

    ๐Ÿ› Bug Investigation

    /ax run danny "Debug the payment timeout issue"
    # Danny analyzes, saves findings to memory
    
    /ax run sofia "Fix the issue Danny found"
    # Sofia reads Danny's analysis โ†’ Implements fix
    
    /ax run queenie "Test the payment fix"
    # Queenie knows the bug + fix โ†’ Comprehensive testing

    Result: Coordinated debugging with full context preservation

    ๐Ÿ“Š Research & Analysis

    /ax run daisy "Analyze user behavior patterns"
    # Daisy analyzes data โ†’ Findings in memory
    
    /ax run paris "Design features based on Daisy's analysis"
    # Paris reads analysis โ†’ Creates product spec
    
    /ax run eric "Business case for Paris's proposal"
    # Eric has analysis + spec โ†’ Strategic evaluation

    Result: Data-driven decision making with complete context


    ๐ŸŽฏ Why Teams Choose AutomatosX

    For Solo Developers

    • Extend Claude Code with persistent memory
    • Never repeat context - agents remember everything
    • Coordinate complex tasks with multi-agent workflows
    • 100% local - your data stays private

    For Teams

    • Shared knowledge base - export/import memory across team
    • Consistent quality - agents learn from past work
    • Faster onboarding - new members inherit team knowledge
    • Audit trail - complete history of all decisions

    For Claude Code Power Users

    • Slash command integration - /ax for instant access
    • Terminal-native - no context switching
    • CLI-based - scriptable and automatable
    • Zero latency - local memory = instant search

    ๐Ÿ› ๏ธ Production-Ready

    โœ… 1,149 tests passing (100% pass rate) โœ… TypeScript strict mode (zero errors) โœ… 84% test coverage (comprehensive testing) โœ… 46MB bundle (87% smaller than v3.x) โœ… < 1ms memory search (62x faster than v3.x)

    Performance Metrics

    Memory Search: < 1ms (10,000 entries)
    Bundle Size:   46MB (down from 340MB in v3.x)
    Dependencies:  158 packages (down from 589 in v3.x)
    Test Coverage: 84.19% (1,149 tests)
    Memory Cost:   $0 (no API calls)

    Technology Stack

    • Runtime: Node.js 20+
    • Language: TypeScript 5.3 (strict mode)
    • Memory: SQLite + FTS5 (built-in full-text search)
    • Testing: Vitest 2.x (1,149 tests)
    • Build: tsup/esbuild
    • Providers: Claude CLI, Gemini CLI, OpenAI Codex

    ๐Ÿšง Coming Soon

    • Enhanced Claude Code integration
    • Visual workflow builder
    • Advanced memory analytics
    • Cross-project knowledge sharing
    • Plugin system for custom providers

    ๐Ÿค Contributing

    We welcome contributions! AutomatosX is built in the open.

    Join the community:


    ๐Ÿ“„ License

    AutomatosX is Apache 2.0 licensed.



    Transform Claude Code into an intelligent, coordinated team with AutomatosX. ๐Ÿš€

    Built with โค๏ธ by the AutomatosX team