superplanehq/superplane

Open source factory for one-shot engineering

What it solves

SuperPlane automates routine engineering tasks by turning high-confidence backlog issues into verified, review-ready pull requests. It removes the need for engineers to manually project-manage every step of routine development, allowing them to focus on complex work that requires human judgment.

How it works

It operates as a "factory" that processes work orders through defined automation lines. These lines consist of ordered stages where AI agents are coordinated with source control, CI, and review systems. The system continuously evaluates backlog issues for confidence, applies workflow-level guardrails, and sends failures back to agents with actionable context. It integrates with existing stacks, including AI models (Claude, OpenAI), source control (GitHub, GitLab), and observability tools (Datadog, Sentry).

Who it’s for

Software engineering teams looking to automate repetitive development work and streamline the path from a backlog issue to a reviewed pull request.

Highlights

  • One-shot engineering: Automates the transition from backlog issue to pull request.
  • Durable execution: Preserves event history and execution state across retries so failed runs can resume without losing context.
  • Flexible deployment: Open source engine that can be run in the cloud or on-prem with a choice of AI models.
  • Broad integration ecosystem: Connects with major AI agents, CI/CD tools, cloud providers, and communication platforms.

Related

  • Project
    conductor-oss/conductor

    An open-source durable execution platform for microservices and AI agents that turns complex workflow graphs into persisted, inspectable, and recoverable executions.

  • 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
    taracodlabs/aiden

    Aiden is an open‑source autonomous AI engine (Node/TypeScript) that turns a natural‑language goal into a verifiable, multi‑step workflow across files, terminal, browser, APIs, and Git. It records every action in SQLite, supports risk‑tiered approvals, multiple LLM providers (OpenAI, Anthropic, Gemini, Ollama, etc.), and can run as a CLI, web workbench, or background daemon. Install via `npm i -g aiden-runtime` and start with `aiden`.

  • Project
    agentspan-ai/agentspan

    A durable runtime for AI agents that prevents execution loss during process crashes and supports long-running, event-driven workflows with human-in-the-loop approvals.

  • Project
    robzilla1738/supergoal

    An autonomous planning and execution framework for Claude Code and Codex CLI that transforms complex tasks into a single, self-healing autonomous run.