mikeyobrien

    mikeyobrien/ralph-orchestrator

    An improved implementation of the Ralph Wiggum technique for autonomous AI agent orchestration

    ai
    ai-agents
    ai-agents-framework
    ai-developer-tools
    claude-code
    claude-code-cli
    codex-cli
    Rust
    MIT
    3.2K stars
    302 forks
    3.2K GitHub watchers
    Updated Nov 3, 2026
    View on GitHub

    Build with Backblaze B2

    SDKs, agent skills, IDE extensions, and reference pipelines from Backblaze Labs. All open source.

    Explore Backblaze Labs

    Loading star history...

    Where it stands

    Rank, growth pace and release cadence relative to everything GStars tracks.

    No releases in the last 90 days; the most recent was 133 days ago, with 37 contributors on GitHub.

    The biggest single-day gain in the last year, +147 stars on Jan 20, coincided with release v2.1.1.

    Use Cases & Benefits

    • Implements autonomous AI agent orchestration using the Ralph Wiggum technique to iteratively run agents until task completion or limits are reached.
    • Supports multiple AI agents with auto-detection, robust error recovery, async checkpointing, and persistent context for reliable, continuous autonomous workflows.
    • Use for automating complex software development tasks with AI agents like Claude, Kiro, Gemini, or ACP-compliant tools in a configurable loop.
    • Use for integrating AI-driven task orchestration into CI/CD pipelines with permission-controlled ACP agent execution and automatic retries.
    • Use for research or experimentation with autonomous AI agent orchestration leveraging rich terminal output, prompt archiving, and detailed metrics tracking.

    Should you depend on it?

    License terms, project hygiene and risks, from GitHub metadata and GStars' snapshots.

    License

    MIT

    Permissive: commercial use, modification and redistribution are allowed with attribution.

    Community files

    • README: present
    • Contributing guide: present
    • Code of conduct: present

    Watch-outs

    No watch-outs from GStars' checks.

    General guidance from repository metadata, not legal advice. How we score

    From the README

    A somewhat functional implementation of the Ralph Wiggum software engineering technique - putting AI agents in a loop until the task is done.

    "Me fail English? That's unpossible!" - Ralph Wiggum

    Excerpt from the mikeyobrien/ralph-orchestrator README on GitHub (MIT license). © its authors.Read the full README on GitHub

    Daily snapshots

    Stars gained per day, and how forks and open issues moved, from GStars' daily snapshots

    Forks

    302+16

    Open issues

    20+13

    Compared with peers in AI

    Fastest-growing repositories GStars tracks in this cohort for the week of Nov 1, by 7-day star growth

    mikeyobrien/ralph-orchestrator compared with AI repositories by stars, 7-day star growth, health score and last release
    RepositoryStars+7dHealthLast release
    thedotmack/claude-mem113.6K+8.8K35today
    D4Vinci/Scrapling98.1K+6.9K651 day ago
    Leonxlnx/taste-skill110.7K+5.2K551 day ago
    calesthio/OpenMontage77.2K+4.2K40—
    heygen-com/hyperframes79.6K+4.1K45today
    mikeyobrien/ralph-orchestrator3.2K—51133 days ago
    Category median98.1K+5.2K45—

    Discover Repositories

    Search across tracked repositories by name or description