claude-mpm and claude-code-sub-agent-collective

The Claude Multi-Agent Project Manager, with its multi-channel orchestration and GitHub-first SDK, likely serves as a foundational platform or framework that could orchestrate or manage sub-agents like the Context Engineering Research's "collective" using hub-and-spoke coordination, making them complements where one provides the infrastructure and the other offers specialized agent functionality.

Maintenance 13/25
Adoption 19/25
Maturity 24/25
Community 18/25
Maintenance 2/25
Adoption 10/25
Maturity 15/25
Community 18/25
Stars: 95
Forks: 18
Downloads: 13,499
Commits (30d): 0
Language: Python
License:
Stars: 520
Forks: 58
Downloads:
Commits (30d): 0
Language: JavaScript
License: MIT
No risk flags
Stale 6m No Package No Dependents

About claude-mpm

bobmatnyc/claude-mpm

Claude Multi-Agent Project Manager — multi-channel orchestration, GitHub-first SDK mode, and plugin system for Claude

Provides 47+ specialized agents, 56 bundled skills, and a hooks system that integrates with Claude Code CLI via plugin marketplace, while leveraging MCP for Google Workspace, Notion, Confluence, Slack, and semantic code search. Implements progressive skill disclosure to optimize token usage and features session resumption with automatic context summarization at configurable thresholds. Built as a service-oriented architecture with 100+ CLI commands, OAuth 2.0 authentication, and encrypted token storage for enterprise workflows.

About claude-code-sub-agent-collective

vanzan01/claude-code-sub-agent-collective

🧠 Context Engineering Research - Not just another agent collection, but using research and context engineering to function as a collective. Hub-and-spoke coordination through Claude Code.

Deploys 30+ specialized agents that enforce test-driven development through a hub-and-spoke routing model, where the `/van` command delegates to a central task-orchestrator that selects domain-specific agents (component, feature, infrastructure, testing). Agents integrate Context7 for real-time documentation lookup and enforce a RED → GREEN → REFACTOR contract, writing tests before implementation. Installation configures agent definitions, TDD enforcement hooks, and Vitest templates across the project's `.claude/` directory structure for use within Claude Code's MCP environment.

Scores updated daily from GitHub, PyPI, and npm data. How scores work