symphony

Overview

Symphony is an experimental tool that monitors task boards like Linear and spawns autonomous coding agents. It handles PR creation, CI checks, and review feedback, enabling teams to manage work at a higher level.

README Preview

# Symphony\n\nSymphony turns project work into isolated, autonomous implementation runs, allowing teams to manage\nwork instead of supervising coding agents.\n\n[](.github/media/symphony-demo.mp4)\n\n_In this [demo video](.github/media/symphony-demo.mp4), 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._\n\n> [!WARNING]\n> Symphony is a low-key engineering preview for testing in trusted environments.\n\n## Running Symphony\n\n### Requirements\n\nSymphony works best in codebases that have adopted\n[harness engineering](https://openai.com/index/harness-engineering/). Symphony is the next step --\nmoving from managing coding agents to managing work that needs to get done.\n\n### Option 1. Make your own\n\nTell your favorite coding agent to build Symphony in a programming language of your choice:\n\n> Implement Symphony according to the following spec:\n> https://github.com/openai/symphony/blob/main/SPEC.md\n\n### Option 2. Use our experimental reference implementation\n\nCheck out [elixir/README.md](elixir/README.md) for instructions on how to set up your environment\nand run the Elixir-based Symphony implementation. You can also ask your favorite coding agent to\nhelp with the setup:\n\n> Set up Symphony for my repository based on\n> https://github.com/openai/symphony/blob/main/elixir/README.md\n\n---\n\n## License\n\nThis project is licensed under the [Apache License 2.0](LICENSE).\n