Skip to main content

SPOQ: Multi-agent AI orchestration with wave-based parallel execution and quality gates

Project description

SPOQ

Specialist Orchestrated Queuing for multi-agent AI development.

SPOQ coordinates AI coding agents through wave-based parallel execution with structured quality gates. It provides an MCP server with 23 tools, a CLI for project scaffolding, and template generators for epics and maps.

Install

pip install spoq

Quick Start

1. Initialize a project

spoq init --target /path/to/project --with-mcp

This creates the SPOQ directory structure, skill stubs for Claude Code, and configures .mcp.json.

2. Use with Claude Code

Once initialized, these slash commands are available in Claude Code:

/epic-planning          Plan an epic with atomic tasks and dependency DAG
/epic-validation        Score epic quality (10 metrics, 95/90 threshold)
/agent-execution        Execute tasks with parallel agent swarms
/agent-validation       Score delivered code (10 metrics, 95/80 threshold)
/team-execution         Persona-specialized agent teams
/epic-planning --map    Coordinate multiple epics as a program

3. Run the MCP server directly

spoq mcp

Or configure in .mcp.json:

{
  "mcpServers": {
    "spoq": {
      "command": "spoq",
      "args": ["mcp"]
    }
  }
}

CLI Commands

Command Description
spoq mcp Run the MCP server (stdio transport)
spoq init Bootstrap SPOQ in a project directory
spoq init --full Include example epic and optional skills
spoq init --with-mcp Configure .mcp.json
spoq init --upgrade Upgrade existing installation
spoq template epic <name> <tasks> Generate an epic skeleton
spoq template map <name> <epics> Generate a map skeleton
spoq --version Show version

MCP Tools (23)

Epic Management: spoq_parse_epic, spoq_validate_epic, spoq_compute_waves, spoq_get_wave_tasks, spoq_analyze_dag, spoq_estimate_effort, spoq_generate_execution_plan, spoq_generate_skeleton

Map Management: spoq_parse_map, spoq_validate_map, spoq_compute_epic_waves, spoq_analyze_map_dag, spoq_estimate_map_effort, spoq_get_map_status, spoq_list_maps, spoq_generate_map_skeleton

Task Management: spoq_get_task, spoq_update_task_status, spoq_list_task_statuses

Team Execution: spoq_assign_personas, spoq_detect_conflicts

Utilities: spoq_get_timestamp, spoq_ping

Links

License

MIT

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

spoq-0.3.1.tar.gz (210.9 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

spoq-0.3.1-py3-none-any.whl (168.3 kB view details)

Uploaded Python 3

File details

Details for the file spoq-0.3.1.tar.gz.

File metadata

  • Download URL: spoq-0.3.1.tar.gz
  • Upload date:
  • Size: 210.9 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.13.7

File hashes

Hashes for spoq-0.3.1.tar.gz
Algorithm Hash digest
SHA256 be367cc2ece24bf09318a9e2ca50e8f1c0fe5682290d63018d6be41f92bfddc8
MD5 8abb73232fa3a38627e18a9640aee279
BLAKE2b-256 f866fc9a0fabfcdb70a37e202f921d3c909105e095c88758dced03bb795310fe

See more details on using hashes here.

File details

Details for the file spoq-0.3.1-py3-none-any.whl.

File metadata

  • Download URL: spoq-0.3.1-py3-none-any.whl
  • Upload date:
  • Size: 168.3 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.13.7

File hashes

Hashes for spoq-0.3.1-py3-none-any.whl
Algorithm Hash digest
SHA256 bb469a3b3bde6526c6e98ada6342f2365afee992b4e70f5d7d6ac42c7accc32b
MD5 dcac04d646a54219e4e1342423098bfa
BLAKE2b-256 c7da84192aa8e85b9b0695e774e4a2349b99c394225caaa0abe7875bd385f289

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page