claude-mpm and claude-octopus
Multi-agent project orchestration (A) and multi-LLM provider abstraction (B) are complementary tools—the first coordinates Claude-based workflows while the second enables those workflows to leverage diverse language models beyond Claude.
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-octopus
nyldn/claude-octopus
Multi-LLM orchestration plugin for Claude Code — 8 providers (Codex, Gemini, Claude, Perplexity, OpenRouter, Copilot, Qwen, Ollama), 47 commands, 50 skills, Double Diamond workflows
Implements a four-phase Double Diamond workflow (Discover → Define → Develop → Deliver) with 75% consensus gates across eight AI providers running in parallel for research, sequentially for scoping, and adversarially for review. Integrates with claude-mem for persistent memory across sessions and supports Dark Factory mode for autonomous end-to-end pipelines from spec to shipped code. Works as a Claude Code plugin with zero required external providers—Claude alone orchestrates, while Codex, Gemini, Perplexity, OpenRouter, Copilot, Qwen, and Ollama auto-activate when detected.
Related comparisons
Scores updated daily from GitHub, PyPI, and npm data. How scores work