openai/symphony
Publicmirrored fromhttps://github.com/openai/symphonyAvailable
README.md
41lines · modecode
| 1 | # Symphony |
| 2 | |
| 3 | Symphony turns project work into isolated, autonomous implementation runs, allowing teams to manage |
| 4 | work instead of supervising coding agents. |
| 5 | |
| 6 | [](.github/media/symphony-demo.mp4) |
| 7 | |
| 8 | _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._ |
| 9 | |
| 10 | > [!WARNING] |
| 11 | > Symphony is a low-key engineering preview for testing in trusted environments. |
| 12 | |
| 13 | ## Running Symphony |
| 14 | |
| 15 | ### Requirements |
| 16 | |
| 17 | Symphony works best in codebases that have adopted |
| 18 | [harness engineering](https://openai.com/index/harness-engineering/). Symphony is the next step -- |
| 19 | moving from managing coding agents to managing work that needs to get done. |
| 20 | |
| 21 | ### Option 1. Make your own |
| 22 | |
| 23 | Tell your favorite coding agent to build Symphony in a programming language of your choice: |
| 24 | |
| 25 | > Implement Symphony according to the following spec: |
| 26 | > https://github.com/openai/symphony/blob/main/SPEC.md |
| 27 | |
| 28 | ### Option 2. Use our experimental reference implementation |
| 29 | |
| 30 | Check out [elixir/README.md](elixir/README.md) for instructions on how to set up your environment |
| 31 | and run the Elixir-based Symphony implementation. You can also ask your favorite coding agent to |
| 32 | help with the setup: |
| 33 | |
| 34 | > Set up Symphony for my repository based on |
| 35 | > https://github.com/openai/symphony/blob/main/elixir/README.md |
| 36 | |
| 37 | --- |
| 38 | |
| 39 | ## License |
| 40 | |
| 41 | This project is licensed under the [Apache License 2.0](LICENSE). |
| 42 | |