https://github.com/openai/symphony
Symphony turns project work into isolated, autonomous implementation runs, allowing teams to manage work instead of supervising coding agents.
https://github.com/openai/symphony
Last synced: 3 months ago
JSON representation
Symphony turns project work into isolated, autonomous implementation runs, allowing teams to manage work instead of supervising coding agents.
- Host: GitHub
- URL: https://github.com/openai/symphony
- Owner: openai
- License: apache-2.0
- Created: 2026-02-26T21:54:00.000Z (4 months ago)
- Default Branch: main
- Last Pushed: 2026-03-05T01:24:58.000Z (3 months ago)
- Last Synced: 2026-03-09T23:37:06.440Z (3 months ago)
- Language: Elixir
- Size: 28.8 MB
- Stars: 10,269
- Watchers: 80
- Forks: 746
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
- License: LICENSE
- Notice: NOTICE
Awesome Lists containing this project
- awesome-agent-orchestrators - symphony - Turns project work into isolated, autonomous implementation runs. (Parallel Agent Runners)
- awesome-opensource-ai - Symphony - Turns project work into isolated, autonomous implementation runs. Monitors work boards, spawns agents to handle tasks, and provides proof of work including CI status, PR reviews, and walkthrough videos. Engineering preview for managing work instead of supervising coding agents. Apache 2.0 licensed.  (4. Agentic AI & Multi-Agent Systems)
- awesome-harness-engineering - Symphony - issue workspaces, and surfaces proof-of-work artifacts (CI status, review feedback, walkthrough videos) as the handoff signal. The spec deliberately leaves sandbox and approval policies implementation-defined so teams can match trust posture to environment, and the in-repo `WORKFLOW.md` pattern versions agent runtime policy alongside code.  (Design Primitives / Task Runners & Orchestration)
- Awesome-GitHub-Repo - Symphony - OpenAI 出品的 Agent 协作框架。 (AI开源项目 / AI Agent)
- awesome-rainmana - openai/symphony - Symphony turns project work into isolated, autonomous implementation runs, allowing teams to manage work instead of supervising coding agents. (Elixir)
- awesome-codex-workflows - OpenAI/symphony - Open-source Codex orchestration spec with an Elixir reference implementation, defining issue-tracker-driven workflows where each issue claims a workspace and is driven to a review handoff. (Foundations & Standards)
- awesome-claude-code - openai/symphony - square&logo=github) | OpenAI's framework for managing isolated, autonomous coding-agent runs | (Agent Orchestration)
README
# Symphony
Symphony turns project work into isolated, autonomous implementation runs, allowing teams to manage
work instead of supervising coding agents.
[](.github/media/symphony-demo.mp4)
_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._
> [!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](https://openai.com/index/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](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
---
## License
This project is licensed under the [Apache License 2.0](LICENSE).