maestro-gemini and oh-my-gemini-cli
These are competitors offering different architectural approaches to multi-agent orchestration on Gemini CLI—maestro-gemini emphasizes parallel dispatch with 12 specialized subagents across four phases, while oh-my-gemini-cli focuses on context-engineering techniques for sequential team workflows—making them alternative choices rather than complementary tools.
About maestro-gemini
josstei/maestro-gemini
Turn Gemini CLI into a multi-agent platform — 12 specialized subagents, parallel dispatch, 4-phase orchestration, and standalone dev tools for code review, debugging, security, and performance
Extends Gemini CLI with 22 domain-specialist subagents orchestrated through complexity-adaptive workflows (Express for simple tasks, Standard 4-phase for medium/complex), using native parallel execution, persistent YAML+Markdown session state, and MCP-first operations. Includes standalone audit commands (code review, security, performance, SEO, accessibility, compliance) with least-privilege tool access enforced through agent frontmatter and 4-tier permission tiers.
About oh-my-gemini-cli
Joonghyun-Lee-Frieren/oh-my-gemini-cli
Context-engineering-powered multi-agent team workflow pack for Gemini CLI.
Implements a structured multi-agent workflow with role-separated agents (director, planner, executor, reviewer, verifier) that coordinate through explicit state files (workspace.json, taskboard.md) and slash commands, using Claude-derived prompt-hardening techniques like critical-path delegation rules and read-before-modify policies. Integrates as a native Gemini CLI extension with retained deep-work skills, model-routing strategies across Gemini 3.1-pro/flash/lite, and workspace lanes to maintain context separation across planning, execution, and review cycles.
Related comparisons
Scores updated daily from GitHub, PyPI, and npm data. How scores work