Symphony (GitHub Repo)

Tech aiagentsdevopsautomation Read original

OpenAI released Symphony, an experimental tool that autonomously manages coding tasks from project boards, allowing developers to oversee work outcomes rather than supervise AI coding agents.

What: Symphony is an open-source tool from OpenAI that integrates with project management systems like Linear to automatically spawn AI coding agents for tasks, which then complete implementation work, run CI, create PRs, and provide proof-of-work documentation including walkthrough videos and complexity analysis.

Why it matters: This represents a shift from treating AI as a coding assistant to treating it as an autonomous workforce, where developers focus on managing outcomes rather than supervising the coding process itself.

Takeaway: The tool is in early preview and requires codebases with "harness engineering" practices; teams can either build their own implementation from the spec or try the experimental Elixir reference version.

Deep dive

Symphony is an experimental tool from OpenAI that automates entire development workflows, not just individual coding tasks
It monitors project management boards like Linear and automatically spawns AI agents to handle incoming work items
Agents complete the full implementation cycle: writing code, running CI, creating PRs, and providing proof-of-work artifacts
Proof-of-work includes CI status, PR review feedback, complexity analysis, and walkthrough videos explaining changes
The goal is to elevate engineers from supervising AI assistants to managing work at a strategic level
Symphony requires codebases that have adopted harness engineering practices—infrastructure for automated testing and validation
Released as a low-key engineering preview intended for trusted environments only, not production-ready
Two implementation options: build your own from the specification, or use the experimental Elixir reference implementation
When agents' work is accepted, they can safely land PRs without human intervention in the coding process
Licensed under Apache 2.0, making it open for experimentation and customization

Decoder

Harness engineering: Infrastructure and practices that enable automated testing, validation, and deployment of code changes
Proof-of-Work: Documentation and artifacts that demonstrate the agent completed tasks correctly, including CI results, analysis, and videos
Linear: A project management and issue tracking tool popular with software development teams
Codex: Reference to the AI coding agent that executes the implementation work

Original article

Symphony

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

In this demo video, Symphony monitors a Linear board for work and spawns agents to handle the tasks. The agents complete the tasks and provide proof of work: CI status, PR review feedback, complexity analysis, and walkthrough videos. When accepted, the agents land the PR safely. Engineers do not need to supervise Codex; they can manage the work at a higher level.

Warning: Symphony is a low-key engineering preview for testing in trusted environments.

Running Symphony

Requirements

Symphony works best in codebases that have adopted harness engineering. Symphony is the next step -- moving from managing coding agents to managing work that needs to get done.

Option 1. Make your own

Tell your favorite coding agent to build Symphony in a programming language of your choice:

Implement Symphony according to the following spec: https://github.com/openai/symphony/blob/main/SPEC.md

Option 2. Use our experimental reference implementation

Check out elixir/README.md for instructions on how to set up your environment and run the Elixir-based Symphony implementation. You can also ask your favorite coding agent to help with the setup:

Set up Symphony for my repository based on https://github.com/openai/symphony/blob/main/elixir/README.md