claude-mpm and claude-code-agents-orchestra

Multi-agent orchestration platforms that compete on the same use case (coordinating Claude-based agents for complex projects), with MPM emphasizing GitHub integration and plugin extensibility while the Orchestra focuses on specialized agent role differentiation and team dynamics.

claude-mpm
74
Verified
Maintenance 13/25
Adoption 19/25
Maturity 24/25
Community 18/25
Maintenance 10/25
Adoption 8/25
Maturity 15/25
Community 18/25
Stars: 95
Forks: 18
Downloads: 13,499
Commits (30d): 0
Language: Python
License:
Stars: 43
Forks: 12
Downloads:
Commits (30d): 0
Language:
License: MIT
No risk flags
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-agents-orchestra

0ldh/claude-code-agents-orchestra

Turn Claude Code into a coordinated team of 40+ specialized AI agents that work together like a world-class engineering organization.

Provides 47 pre-built AI agent personas organized into 10 specialized teams (architecture, development, QA, DevOps, etc.), each with tailored expertise across frameworks like Django/Rails, React/Vue, and domains like ML/Web3. Agents can be invoked individually for focused tasks or used with custom orchestration logic, enabling multi-agent workflows where specialized experts collaborate on complex engineering problems. Targets Claude Code integration with a modular, extensible design—each agent includes detailed capability specifications that can be consumed by orchestration systems or directly via prompting.

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