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.
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.
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
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
This fork includes guarded workspace cleanup, non-blocking tracker reconciliation, strict Codex turn handling, and deployment-isolated accounting. The opt-in Studio workflow starts with one worker and hands validated staging PRs to a human. See Studio operations for installation, preflight, rollout, and recovery.
Fresh workers can require a configurable remaining-token reserve. Readiness hook failures block before Codex startup, and stopped/retrying execution states persist without resetting issue budgets. Unfinished dependencies prevent new dispatches and retries across all active issue states; moving a ticket into implementation or review does not bypass its dependency gate.
This project is licensed under the Apache License 2.0.