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.

Symphony can be installed and configured through a coding agent.

Give your agent this instruction:

Install Symphony from https://github.com/DannyMac180/simphony, run the agent-readable setup flow, ask me only for missing required values, and use Symphony's CLI to save configuration. Do not hand-edit WORKFLOW.md unless Symphony reports that manual recovery is required.

The agent should run:

curl -fsSL https://github.com/DannyMac180/simphony/releases/latest/download/install.sh | SYMPHONY_AGENT_SETUP=1 sh
symphony setup schema --json
symphony setup status --json

SYMPHONY_AGENT_SETUP=1 installs the CLI without opening the manual setup screen. After the agent collects and saves the required values, symphony start opens the live dashboard at /.

After collecting the required values, the agent can save setup by passing JSON on stdin:

symphony setup apply --json < setup.json
symphony workflow validate
symphony start

Later, the user can ask their agent to inspect or change Symphony configuration:

symphony config get --json
symphony config set --json < patch.json
symphony workflow validate
symphony start

symphony config get --json never prints the Linear API key; it reports only whether the key is stored. Symphony remains the authority for settings, keychain storage, and generated WORKFLOW.md, while the agent mediates the conversation with the user.

The packaged path is designed for a local one-line install on macOS and Linux:

curl -fsSL https://github.com/DannyMac180/simphony/releases/latest/download/install.sh | sh

The installer downloads the matching release artifact, installs a symphony wrapper in ~/.local/bin, starts the local Phoenix server, and opens the setup wizard at http://127.0.0.1:7957/setup.

First-run setup asks for:

• Linear API key, stored in the OS keychain
• Linear project slug
• repository clone URL
• workspace root
• Codex command
• active and terminal Linear states

After setup, Symphony generates a local WORKFLOW.md in the user config directory and starts the orchestration runtime.

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 project is licensed under the Apache License 2.0.