openai/symphony

Symphony turns project work into isolated, autonomous implementation runs, allowing teams to manage work instead of supervising coding agents.

What it solves

Symphony shifts the focus of software engineering teams from supervising individual coding agents to managing high-level project work. It transforms project tasks into isolated, autonomous implementation runs that can be completed without constant human oversight.

How it works

Symphony monitors work tracking systems (such as Linear) to identify tasks. It then spawns autonomous agents to handle these tasks. These agents perform the implementation and provide "proof of work," which includes CI status, PR review feedback, complexity analysis, and walkthrough videos. Once the work is accepted, the agents merge the pull request.

Who it’s for

Software engineering teams who have adopted harness engineering and want to move toward managing autonomous work streams rather than supervising AI coding assistants.

Highlights

  • Autonomous task handling: Spawns agents to complete tasks from a project board.
  • Proof of work: Provides CI status, PR reviews, and complexity analysis to verify results.
  • Isolated implementation runs: Treats project work as distinct, autonomous runs.
  • Reference implementation: Includes an experimental Elixir-based version for setup.

Related

  • Dispatch
    Symphony: Open‑Source Spec for Codex Orchestration

    OpenAI released Symphony, an open‑source specification that turns issue trackers like Linear into always‑on orchestrator for Codex coding agents, enabling teams to automate routine implementation work and increase PR throughput.

  • Project
    the-open-engine/zeroshot

    A multi-agent orchestration engine that turns software goals into explicit graphs to separate code implementation from independent verification and delivery.

  • Project
    Agent-Field/SWE-AF

    An autonomous software engineering factory that coordinates a full team of AI agents (PMs, architects, coders, and QA) to scope, build, and ship complex code changes via a single API call.

  • Project
    AmazingAng/old-coder

    A workflow and set of instructions for coding agents that replaces manual code review with a rigorous automated testing gauntlet and an evidence report.

  • Project
    SynkraAI/aiox-core

    An open-source AI orchestration framework that implements an agentic agile workflow to prevent context loss and planning inconsistency in AI-assisted software development.