automagik-dev/genie

Wishes in, PRs out. CLI agent that interviews you, plans the work, dispatches parallel agents in isolated worktrees, and reviews code before you see it.

What it solves

Genie provides a planning-and-execution layer for AI coding agents, transforming a single-sentence request into a structured development process. It solves the problem of fragmented AI coding by introducing a rigorous workflow of brainstorming, design, planning, and independent review, ensuring that the final output meets specific acceptance criteria before being merged.

How it works

Genie uses a combination of plain-markdown documents stored in git (for wishes, designs, and brainstorms) and a single per-repository SQLite database (for tasks, boards, and execution state). It operates as a lightweight CLI that requires no background daemons or heavy databases.

When a user invokes a skill, Genie coordinates the process: it interviews the user to create a design, turns that design into a scoped "wish" with execution groups, and then dispatches the active AI agent's native subagents to build the feature in parallel. To ensure quality, it employs an independent review process where a reviewer subagent—distinct from the engineer subagent—must provide a verdict (SHIP, FIX-FIRST, or BLOCKED) based on the wish criteria.

Who it’s for

It is designed for developers using AI coding agents (such as Claude Code, Codex, Goose, or Windsurf) who want a more structured, professional software engineering lifecycle than simple prompting.

Highlights

  • Structured Workflow: Implements a strict sequence: brainstorm → design review → wish → plan review → work → implementation review.
  • Agent Agnostic: Delivers skills to multiple agent homes (Claude Code, Codex, Goose, Windsurf) using a runtime-neutral delegation contract.
  • Lightweight State: Uses a single SQLite file and git-based markdown files; no resident processes or external database servers are required.
  • Independent Review: Enforces a separation between the agent that writes the code and the agent that reviews it.
  • WhatsApp Integration: Includes an "Omni" bridge allowing users to handle approvals and one-shot tasks via WhatsApp.

Related

  • Project
    whitelonng/mancode

    An AI coding agent workflow orchestration tool that adds a layer of engineering discipline, structured planning, and cross-session continuity to existing AI agents.

  • Project
    BloopAI/vibe-kanban

    A management layer for AI coding agents that combines kanban planning with dedicated workspaces for agent execution, review, and app previewing.

  • Project
    soumatheusgomes/vibe-coding-toolkit

    A documented workflow and set of tools (plugins, prompts, lint rules, sub‑agent orchestration, memory handling) that let developers use Claude Code / Codex as a disciplined coding teammate. Includes a “Superpowers” discipline, parallel sub‑agents, quality‑gate ESLint config, and a full onboarding Playbook.

  • Project
    google/agents-cli

    A CLI and skill set that enables developers and AI coding assistants to build, evaluate, and deploy enterprise-grade agents on the Gemini Enterprise Agent Platform.

  • Project
    umputun/cc-thingz

    cc‑thingz is a marketplace of Claude Code plugins that add higher‑level developer workflows—brainstorming, PR review, structured planning, release automation, and assorted thinking tools. Install via Claude’s `/plugin` command, configure a few JSON hooks, and invoke the new slash commands (e.g., `/brainstorm:do`, `/review:pr`, `/planning:make`). The plugins use Claude sub‑agents, hooks, and editor overlays to automate planning, code review, and even autonomous plan execution, making Claude Code a more powerful coding assistant.