# MAOS - Multi-Agent Orchestration System v0.7.0
**🚀 AUTONOMOUS MULTI-AGENT EXECUTION IS HERE!**
## 🎉 MAJOR BREAKTHROUGH in v0.7.0
**MAOS now runs Claude agents AUTONOMOUSLY in PARALLEL:**
- ✅ **REAL autonomous execution** using Claude SDK with `--dangerously-skip-permissions`
- ✅ **TRUE parallel processing** - multiple Claude instances run simultaneously
- ✅ **NO manual intervention** - fully automated orchestration
- ✅ **Session persistence** - resume conversations with `--resume`
- ✅ **Cost tracking** - see exactly how much each agent costs
- ✅ **Performance monitoring** - track execution times and turns
## How It Actually Works Now
1. **You describe your task** → "Analyze this codebase and write tests"
2. **MAOS decomposes into subtasks** → Creates batches for parallel execution
3. **MAOS spawns Claude SDK processes** → Each agent runs `claude -p "task" --dangerously-skip-permissions`
4. **Agents run AUTONOMOUSLY** → No manual intervention, no prompts, just execution
5. **Results returned in real-time** → See progress, costs, and outputs as they complete
## 🚀 What's New in v0.6.0
**Complete Architecture Rewrite:**
- ✅ **Proper Subagent Creation** - Creates `.claude/agents/*.md` files with YAML frontmatter
- ✅ **Task Tool Integration** - Generates delegation prompts for Claude Code
- ✅ **No Process Spawning** - Uses Claude's native subagent system
- ✅ **Parallel Execution Works** - Claude Code handles parallel tasks internally
- ✅ **Database Tracking** - Still tracks everything in SQLite
- ✅ **Clean Architecture** - Aligns with official Claude Code documentation
## 📦 Previous v0.4.0
**Enhanced Task Understanding & Visibility:**
- ✅ **Smart Task Decomposition** - Correctly parses explicit agent requests like "use 2 agents, one which understand requirements"
- ✅ **Explainable AI** - Shows task understanding and explains decomposition decisions
- ✅ **Real-time Monitoring** - Live progress updates for each agent during batch execution
- ✅ **Better Timeout Handling** - Detects stuck agents and provides clear timeout messages
- ✅ **Enhanced Database Logging** - All tasks and operations properly saved to database
- ✅ **Improved Error Messages** - Clear visibility into what each agent is doing
## 📦 Previous v0.3.2
**Bug Fix Release:**
- ✅ Fixed foreign key constraint issue in message bus
- ✅ Agents now properly created in database before messaging
- ✅ Prevents duplicate agent creation in database
## 📦 What's New in v0.3.1
**Bug Fix Release:**
- ✅ Fixed SQLite Row conversion issue for Python 3.13 compatibility
- ✅ Proper dictionary conversion from aiosqlite Row objects
- ✅ All database queries now return proper dictionaries
## 📦 What's New in v0.3.0
**Complete Orchestration System:**
- ✅ **SQLite Persistence** - All data stored in a robust database
- ✅ **Task Decomposition** - Automatically breaks tasks into parallel subtasks
- ✅ **Session Management** - Resume conversations, save/restore checkpoints
- ✅ **Inter-Agent Communication** - Agents coordinate and share information
- ✅ **Smart Agent Allocation** - Reuses existing agents when possible
- ✅ **Real SDK Mode** - Spawns Claude with `-p` for actual task execution
## What MAOS Does
MAOS orchestrates multiple Claude CLI instances to work on complex tasks in parallel:
```
User: "Implement the requirements in prd.md"
MAOS:
├─ Analyzes requirements
├─ Decomposes into subtasks
├─ Allocates agents (creates new or reuses existing)
├─ Executes tasks in parallel batches
└─ Coordinates inter-agent communication
```
## Installation
```bash
# Install with pipx (recommended)
pipx install maos-cli
# Or with pip
pip install maos-cli
```
## Quick Start
### 1. Basic Chat Interface
```bash
# Start the orchestrator
maos chat
# Now use natural language
MAOS> Build a REST API with authentication
```
### 2. How It Works
When you give MAOS a task, it:
1. **Decomposes** - Breaks your request into parallel subtasks
2. **Proposes Agents** - Shows which agents it will create/reuse
3. **Gets Approval** - You approve the execution plan
4. **Executes** - Spawns Claude processes in SDK mode
5. **Coordinates** - Manages inter-agent communication
6. **Reports** - Shows progress and results
### 3. Example Session
```
MAOS> Implement the requirements in prd.md
Analyzing request and creating task plan...
Determining agent allocation...
═══════════════════════════════════════════════════
Agent Allocation
───────────────────────────────────────────────────
Agent allocation proposal:
• Creating 3 new agents
• Reusing 2 existing agents
NEW: architect-a3f2b1c8 (architect)
→ Design system architecture based on PRD
NEW: developer-b4d5c2e9 (developer)
→ Implement backend services according to PRD
NEW: tester-c6e7d3fa (tester)
→ Write comprehensive tests for PRD features
REUSE: security-auditor [session: 4d5e6f7a]
→ Review for security vulnerabilities
REUSE: reviewer [session: 8b9c0d1e]
→ Review code quality and standards
═══════════════════════════════════════════════════
Estimated duration: 10.0 minutes
Estimated cost: $0.1500
Proceed with this plan? (y/n): y
Starting execution...
Spawning agents...
✓ Spawned architect-a3f2b1c8
✓ Spawned developer-b4d5c2e9
✓ Spawned tester-c6e7d3fa
↻ Resumed security-auditor
↻ Resumed reviewer
Executing batch 1/3
[Working... Agents collaborating]
💡 architect-a3f2b1c8 discovered: Database schema requires indexing
⚠️ developer-b4d5c2e9 needs from architect-a3f2b1c8: API endpoint specs
Execution complete!
```
## Features
### 🧠 Intelligent Task Decomposition
- Automatically breaks complex tasks into subtasks
- Identifies dependencies between tasks
- Groups tasks for parallel execution
### 🤖 Smart Agent Management
- Creates specialized agents for different task types
- Reuses existing agents when appropriate
- Manages Claude sessions with SDK mode (`claude -p`)
### 💬 Inter-Agent Communication
- Agents can send messages to each other
- Broadcast discoveries to all agents
- Request dependencies from other agents
### 💾 Persistence & Checkpoints
- SQLite database stores all orchestration data
- Save/restore checkpoints for long-running tasks
- Resume sessions across multiple days
### 📊 Real-Time Monitoring
- Track agent progress
- View inter-agent messages
- Monitor resource usage
## Commands
### Natural Language
Just type what you want:
- `"Build a REST API with authentication"`
- `"Review and optimize my codebase"`
- `"Fix all the failing tests"`
- `"Implement the requirements in prd.md"`
### System Commands
- `status` - Show current execution status
- `save checkpoint <name>` - Save current state
- `restore <name>` - Restore from checkpoint
- `list checkpoints` - Show available checkpoints
- `pause` - Pause execution
- `resume` - Resume execution
- `help` - Show available commands
- `exit` - Stop all agents and exit
## Architecture
```
┌─────────────────────────────────────────────┐
│ Natural Language Input │
└─────────────────────────────────────────────┘
↓
┌─────────────────────────────────────────────┐
│ Orchestrator Brain │
│ • Task Decomposer │
│ • Agent Allocator │
│ • Execution Planner │
└─────────────────────────────────────────────┘
↓
┌─────────────────────────────────────────────┐
│ Session Manager │
│ • Spawn Claude with -p <task> │
│ • Resume sessions with --resume │
│ • Manage process lifecycle │
└─────────────────────────────────────────────┘
↓
┌─────────────────────────────────────────────┐
│ Agent Message Bus │
│ • Inter-agent communication │
│ • Message routing │
│ • Discovery broadcasting │
└─────────────────────────────────────────────┘
↓
┌─────────────────────────────────────────────┐
│ SQLite Persistence │
│ • Agents, Sessions, Tasks │
│ • Messages, Checkpoints │
│ • Complete relational storage │
└─────────────────────────────────────────────┘
```
## Requirements
- Python 3.11+
- Claude CLI (optional, for actual execution)
```bash
npm install -g @anthropic-ai/claude-code
export ANTHROPIC_API_KEY="your-api-key"
```
## Advanced Usage
### Auto-Approve Mode
Skip manual approval for agent proposals:
```bash
maos chat --auto-approve
```
### Custom Database Location
```bash
maos chat --db-path /path/to/my/maos.db
```
### Configuration File
Create `.maos/config.yaml`:
```yaml
orchestrator:
max_agents: 20
auto_approve: false
persistence:
db_path: ./maos.db
session:
max_turns: 10
timeout: 600
```
## Troubleshooting
### Claude CLI Not Found
MAOS works without Claude CLI - it creates agent definition files. To actually run agents, install Claude:
```bash
npm install -g @anthropic-ai/claude-code
```
### Database Errors
Delete the database to start fresh:
```bash
rm maos.db
```
### Session Issues
List and manage sessions:
```bash
MAOS> status
MAOS> list checkpoints
MAOS> restore <checkpoint-name>
```
## Examples
### Code Review
```
MAOS> Review all Python files for security issues and performance problems
[Creates security-auditor and performance-optimizer agents]
[Runs them in parallel across your codebase]
[Reports findings with specific file locations]
```
### Test Generation
```
MAOS> Generate comprehensive tests for all modules
[Creates multiple tester agents]
[Each handles different modules in parallel]
[Produces test files with high coverage]
```
### Documentation
```
MAOS> Document all public APIs and create a user guide
[Creates documentation-writer agents]
[Analyzes code and generates docs]
[Produces markdown documentation]
```
## Version History
- **v0.3.2** - Fixed foreign key constraint issue in message bus
- **v0.3.1** - Fixed SQLite Row conversion for Python 3.13 compatibility
- **v0.3.0** - Complete orchestration with SQLite, parallel execution, checkpoints
- **v0.2.6** - Fixed agent spawning, improved natural language
- **v0.2.0** - Added Claude CLI integration
- **v0.1.0** - Initial release with agent definitions
## Contributing
PRs welcome! Check out our [contribution guidelines](CONTRIBUTING.md).
## License
MIT - See [LICENSE](LICENSE) file
## Support
- **Issues**: [GitHub Issues](https://github.com/yourusername/maos/issues)
- **Discussions**: [GitHub Discussions](https://github.com/yourusername/maos/discussions)
- **Documentation**: [Full Docs](https://maos.dev/docs)
---
**Built with ❤️ for the AI orchestration community**
Raw data
{
"_id": null,
"home_page": null,
"name": "maos-cli",
"maintainer": null,
"docs_url": null,
"requires_python": ">=3.11",
"maintainer_email": "Vincent Sider <vincent@maos.dev>",
"keywords": "agents, ai, automation, claude, llm, orchestration, sdk, swarm",
"author": null,
"author_email": "Vincent Sider <vincent@maos.dev>",
"download_url": "https://files.pythonhosted.org/packages/3f/e9/32b70896c2e6feff518cec9713535de136d0272ccf3825f4f6581f9a24d3/maos_cli-0.8.8.tar.gz",
"platform": null,
"description": "# MAOS - Multi-Agent Orchestration System v0.7.0\n\n**\ud83d\ude80 AUTONOMOUS MULTI-AGENT EXECUTION IS HERE!**\n\n## \ud83c\udf89 MAJOR BREAKTHROUGH in v0.7.0\n\n**MAOS now runs Claude agents AUTONOMOUSLY in PARALLEL:**\n- \u2705 **REAL autonomous execution** using Claude SDK with `--dangerously-skip-permissions`\n- \u2705 **TRUE parallel processing** - multiple Claude instances run simultaneously\n- \u2705 **NO manual intervention** - fully automated orchestration\n- \u2705 **Session persistence** - resume conversations with `--resume`\n- \u2705 **Cost tracking** - see exactly how much each agent costs\n- \u2705 **Performance monitoring** - track execution times and turns\n\n## How It Actually Works Now\n\n1. **You describe your task** \u2192 \"Analyze this codebase and write tests\"\n2. **MAOS decomposes into subtasks** \u2192 Creates batches for parallel execution\n3. **MAOS spawns Claude SDK processes** \u2192 Each agent runs `claude -p \"task\" --dangerously-skip-permissions`\n4. **Agents run AUTONOMOUSLY** \u2192 No manual intervention, no prompts, just execution\n5. **Results returned in real-time** \u2192 See progress, costs, and outputs as they complete\n\n## \ud83d\ude80 What's New in v0.6.0\n\n**Complete Architecture Rewrite:**\n- \u2705 **Proper Subagent Creation** - Creates `.claude/agents/*.md` files with YAML frontmatter\n- \u2705 **Task Tool Integration** - Generates delegation prompts for Claude Code\n- \u2705 **No Process Spawning** - Uses Claude's native subagent system\n- \u2705 **Parallel Execution Works** - Claude Code handles parallel tasks internally\n- \u2705 **Database Tracking** - Still tracks everything in SQLite\n- \u2705 **Clean Architecture** - Aligns with official Claude Code documentation\n\n## \ud83d\udce6 Previous v0.4.0\n\n**Enhanced Task Understanding & Visibility:**\n- \u2705 **Smart Task Decomposition** - Correctly parses explicit agent requests like \"use 2 agents, one which understand requirements\"\n- \u2705 **Explainable AI** - Shows task understanding and explains decomposition decisions\n- \u2705 **Real-time Monitoring** - Live progress updates for each agent during batch execution\n- \u2705 **Better Timeout Handling** - Detects stuck agents and provides clear timeout messages\n- \u2705 **Enhanced Database Logging** - All tasks and operations properly saved to database\n- \u2705 **Improved Error Messages** - Clear visibility into what each agent is doing\n\n## \ud83d\udce6 Previous v0.3.2\n\n**Bug Fix Release:**\n- \u2705 Fixed foreign key constraint issue in message bus\n- \u2705 Agents now properly created in database before messaging\n- \u2705 Prevents duplicate agent creation in database\n\n## \ud83d\udce6 What's New in v0.3.1\n\n**Bug Fix Release:**\n- \u2705 Fixed SQLite Row conversion issue for Python 3.13 compatibility\n- \u2705 Proper dictionary conversion from aiosqlite Row objects\n- \u2705 All database queries now return proper dictionaries\n\n## \ud83d\udce6 What's New in v0.3.0\n\n**Complete Orchestration System:**\n- \u2705 **SQLite Persistence** - All data stored in a robust database\n- \u2705 **Task Decomposition** - Automatically breaks tasks into parallel subtasks\n- \u2705 **Session Management** - Resume conversations, save/restore checkpoints\n- \u2705 **Inter-Agent Communication** - Agents coordinate and share information\n- \u2705 **Smart Agent Allocation** - Reuses existing agents when possible\n- \u2705 **Real SDK Mode** - Spawns Claude with `-p` for actual task execution\n\n## What MAOS Does\n\nMAOS orchestrates multiple Claude CLI instances to work on complex tasks in parallel:\n\n```\nUser: \"Implement the requirements in prd.md\"\n\nMAOS:\n\u251c\u2500 Analyzes requirements\n\u251c\u2500 Decomposes into subtasks\n\u251c\u2500 Allocates agents (creates new or reuses existing)\n\u251c\u2500 Executes tasks in parallel batches\n\u2514\u2500 Coordinates inter-agent communication\n```\n\n## Installation\n\n```bash\n# Install with pipx (recommended)\npipx install maos-cli\n\n# Or with pip\npip install maos-cli\n```\n\n## Quick Start\n\n### 1. Basic Chat Interface\n\n```bash\n# Start the orchestrator\nmaos chat\n\n# Now use natural language\nMAOS> Build a REST API with authentication\n```\n\n### 2. How It Works\n\nWhen you give MAOS a task, it:\n\n1. **Decomposes** - Breaks your request into parallel subtasks\n2. **Proposes Agents** - Shows which agents it will create/reuse\n3. **Gets Approval** - You approve the execution plan\n4. **Executes** - Spawns Claude processes in SDK mode\n5. **Coordinates** - Manages inter-agent communication\n6. **Reports** - Shows progress and results\n\n### 3. Example Session\n\n```\nMAOS> Implement the requirements in prd.md\n\nAnalyzing request and creating task plan...\nDetermining agent allocation...\n\n\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\n Agent Allocation\n\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\nAgent allocation proposal:\n \u2022 Creating 3 new agents\n \u2022 Reusing 2 existing agents\n\n NEW: architect-a3f2b1c8 (architect)\n \u2192 Design system architecture based on PRD\n NEW: developer-b4d5c2e9 (developer) \n \u2192 Implement backend services according to PRD\n NEW: tester-c6e7d3fa (tester)\n \u2192 Write comprehensive tests for PRD features\n REUSE: security-auditor [session: 4d5e6f7a]\n \u2192 Review for security vulnerabilities\n REUSE: reviewer [session: 8b9c0d1e]\n \u2192 Review code quality and standards\n\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\n\nEstimated duration: 10.0 minutes\nEstimated cost: $0.1500\n\nProceed with this plan? (y/n): y\n\nStarting execution...\nSpawning agents...\n \u2713 Spawned architect-a3f2b1c8\n \u2713 Spawned developer-b4d5c2e9\n \u2713 Spawned tester-c6e7d3fa\n \u21bb Resumed security-auditor\n \u21bb Resumed reviewer\n\nExecuting batch 1/3\n[Working... Agents collaborating]\n\n\ud83d\udca1 architect-a3f2b1c8 discovered: Database schema requires indexing\n\u26a0\ufe0f developer-b4d5c2e9 needs from architect-a3f2b1c8: API endpoint specs\n\nExecution complete!\n```\n\n## Features\n\n### \ud83e\udde0 Intelligent Task Decomposition\n- Automatically breaks complex tasks into subtasks\n- Identifies dependencies between tasks\n- Groups tasks for parallel execution\n\n### \ud83e\udd16 Smart Agent Management\n- Creates specialized agents for different task types\n- Reuses existing agents when appropriate\n- Manages Claude sessions with SDK mode (`claude -p`)\n\n### \ud83d\udcac Inter-Agent Communication\n- Agents can send messages to each other\n- Broadcast discoveries to all agents\n- Request dependencies from other agents\n\n### \ud83d\udcbe Persistence & Checkpoints\n- SQLite database stores all orchestration data\n- Save/restore checkpoints for long-running tasks\n- Resume sessions across multiple days\n\n### \ud83d\udcca Real-Time Monitoring\n- Track agent progress\n- View inter-agent messages\n- Monitor resource usage\n\n## Commands\n\n### Natural Language\nJust type what you want:\n- `\"Build a REST API with authentication\"`\n- `\"Review and optimize my codebase\"`\n- `\"Fix all the failing tests\"`\n- `\"Implement the requirements in prd.md\"`\n\n### System Commands\n- `status` - Show current execution status\n- `save checkpoint <name>` - Save current state\n- `restore <name>` - Restore from checkpoint\n- `list checkpoints` - Show available checkpoints\n- `pause` - Pause execution\n- `resume` - Resume execution\n- `help` - Show available commands\n- `exit` - Stop all agents and exit\n\n## Architecture\n\n```\n\u250c\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2510\n\u2502 Natural Language Input \u2502\n\u2514\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2518\n \u2193\n\u250c\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2510\n\u2502 Orchestrator Brain \u2502\n\u2502 \u2022 Task Decomposer \u2502\n\u2502 \u2022 Agent Allocator \u2502\n\u2502 \u2022 Execution Planner \u2502\n\u2514\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2518\n \u2193\n\u250c\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2510\n\u2502 Session Manager \u2502\n\u2502 \u2022 Spawn Claude with -p <task> \u2502\n\u2502 \u2022 Resume sessions with --resume \u2502\n\u2502 \u2022 Manage process lifecycle \u2502\n\u2514\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2518\n \u2193\n\u250c\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2510\n\u2502 Agent Message Bus \u2502\n\u2502 \u2022 Inter-agent communication \u2502\n\u2502 \u2022 Message routing \u2502\n\u2502 \u2022 Discovery broadcasting \u2502\n\u2514\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2518\n \u2193\n\u250c\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2510\n\u2502 SQLite Persistence \u2502\n\u2502 \u2022 Agents, Sessions, Tasks \u2502\n\u2502 \u2022 Messages, Checkpoints \u2502\n\u2502 \u2022 Complete relational storage \u2502\n\u2514\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2518\n```\n\n## Requirements\n\n- Python 3.11+\n- Claude CLI (optional, for actual execution)\n ```bash\n npm install -g @anthropic-ai/claude-code\n export ANTHROPIC_API_KEY=\"your-api-key\"\n ```\n\n## Advanced Usage\n\n### Auto-Approve Mode\n\nSkip manual approval for agent proposals:\n\n```bash\nmaos chat --auto-approve\n```\n\n### Custom Database Location\n\n```bash\nmaos chat --db-path /path/to/my/maos.db\n```\n\n### Configuration File\n\nCreate `.maos/config.yaml`:\n\n```yaml\norchestrator:\n max_agents: 20\n auto_approve: false\n \npersistence:\n db_path: ./maos.db\n \nsession:\n max_turns: 10\n timeout: 600\n```\n\n## Troubleshooting\n\n### Claude CLI Not Found\nMAOS works without Claude CLI - it creates agent definition files. To actually run agents, install Claude:\n```bash\nnpm install -g @anthropic-ai/claude-code\n```\n\n### Database Errors\nDelete the database to start fresh:\n```bash\nrm maos.db\n```\n\n### Session Issues\nList and manage sessions:\n```bash\nMAOS> status\nMAOS> list checkpoints\nMAOS> restore <checkpoint-name>\n```\n\n## Examples\n\n### Code Review\n```\nMAOS> Review all Python files for security issues and performance problems\n\n[Creates security-auditor and performance-optimizer agents]\n[Runs them in parallel across your codebase]\n[Reports findings with specific file locations]\n```\n\n### Test Generation\n```\nMAOS> Generate comprehensive tests for all modules\n\n[Creates multiple tester agents]\n[Each handles different modules in parallel]\n[Produces test files with high coverage]\n```\n\n### Documentation\n```\nMAOS> Document all public APIs and create a user guide\n\n[Creates documentation-writer agents]\n[Analyzes code and generates docs]\n[Produces markdown documentation]\n```\n\n## Version History\n\n- **v0.3.2** - Fixed foreign key constraint issue in message bus\n- **v0.3.1** - Fixed SQLite Row conversion for Python 3.13 compatibility\n- **v0.3.0** - Complete orchestration with SQLite, parallel execution, checkpoints\n- **v0.2.6** - Fixed agent spawning, improved natural language\n- **v0.2.0** - Added Claude CLI integration\n- **v0.1.0** - Initial release with agent definitions\n\n## Contributing\n\nPRs welcome! Check out our [contribution guidelines](CONTRIBUTING.md).\n\n## License\n\nMIT - See [LICENSE](LICENSE) file\n\n## Support\n\n- **Issues**: [GitHub Issues](https://github.com/yourusername/maos/issues)\n- **Discussions**: [GitHub Discussions](https://github.com/yourusername/maos/discussions)\n- **Documentation**: [Full Docs](https://maos.dev/docs)\n\n---\n\n**Built with \u2764\ufe0f for the AI orchestration community**",
"bugtrack_url": null,
"license": "MIT",
"summary": "Orchestrate swarms of Claude subagents with natural language",
"version": "0.8.8",
"project_urls": {
"Documentation": "https://github.com/vincentsider/maos-cli#readme",
"Homepage": "https://github.com/vincentsider/maos-cli",
"Issues": "https://github.com/vincentsider/maos-cli/issues",
"Repository": "https://github.com/vincentsider/maos-cli",
"Source Code": "https://github.com/vincentsider/maos-cli"
},
"split_keywords": [
"agents",
" ai",
" automation",
" claude",
" llm",
" orchestration",
" sdk",
" swarm"
],
"urls": [
{
"comment_text": null,
"digests": {
"blake2b_256": "40dd9c4006cb33456d65aa30b6e9edf7b09a239946b69c8b3e13ad757d51db18",
"md5": "b58d13aa33369f6ec97fc1ace5f5aae9",
"sha256": "36a47dc47774ba546b3592e640c52c973985598418a840e05f2da6315a731fb6"
},
"downloads": -1,
"filename": "maos_cli-0.8.8-py3-none-any.whl",
"has_sig": false,
"md5_digest": "b58d13aa33369f6ec97fc1ace5f5aae9",
"packagetype": "bdist_wheel",
"python_version": "py3",
"requires_python": ">=3.11",
"size": 276935,
"upload_time": "2025-08-17T11:57:40",
"upload_time_iso_8601": "2025-08-17T11:57:40.226144Z",
"url": "https://files.pythonhosted.org/packages/40/dd/9c4006cb33456d65aa30b6e9edf7b09a239946b69c8b3e13ad757d51db18/maos_cli-0.8.8-py3-none-any.whl",
"yanked": false,
"yanked_reason": null
},
{
"comment_text": null,
"digests": {
"blake2b_256": "3fe932b70896c2e6feff518cec9713535de136d0272ccf3825f4f6581f9a24d3",
"md5": "7ec6bba7d5e36ef4b4075ecc348e0fb7",
"sha256": "2df00f9d32452d8e5edb95dfe5a5349b03547bf396f6c202572ccc983b023fa1"
},
"downloads": -1,
"filename": "maos_cli-0.8.8.tar.gz",
"has_sig": false,
"md5_digest": "7ec6bba7d5e36ef4b4075ecc348e0fb7",
"packagetype": "sdist",
"python_version": "source",
"requires_python": ">=3.11",
"size": 1039605,
"upload_time": "2025-08-17T11:57:42",
"upload_time_iso_8601": "2025-08-17T11:57:42.060047Z",
"url": "https://files.pythonhosted.org/packages/3f/e9/32b70896c2e6feff518cec9713535de136d0272ccf3825f4f6581f9a24d3/maos_cli-0.8.8.tar.gz",
"yanked": false,
"yanked_reason": null
}
],
"upload_time": "2025-08-17 11:57:42",
"github": true,
"gitlab": false,
"bitbucket": false,
"codeberg": false,
"github_user": "vincentsider",
"github_project": "maos-cli#readme",
"github_not_found": true,
"lcname": "maos-cli"
}
JSON
