Back to directory

Symphony

A tool that turns project work into isolated, autonomous coding-agent runs so a team can manage the work itself rather than supervise each agent, with an experimental Elixir reference implementation.

Symphony

Symphony turns project work into isolated, autonomous implementation runs, so a team manages work instead of supervising individual coding agents. In an example workflow, Symphony watches a project board such as Linear for work, spawns agents to handle the tasks, and the agents complete the work and provide proof such as CI status, PR review feedback, complexity analysis and walkthrough videos before landing the change once it is accepted.

It is described as best suited to codebases that have already adopted harness engineering practices. A team can either implement Symphony itself from its published specification, or use the project's own experimental reference implementation, written in Elixir, following its setup instructions.

The project describes itself as a low-key engineering preview meant for testing in trusted environments. It is licensed under the Apache License 2.0.

More in Coding agents

See all 793
  • The City

    github.com

    A native macOS app that shows Claude Code runs as a city, with each project as a building, each team as a floor of robots, and every animation driven by a real event from the claude CLI's stream.

  • rig

    tryrig.ai

    A small, single-binary agent runtime that points at any OpenAI-compatible model, local or hosted, reads and edits a repository's code, runs its tests and remembers what it learned, with a loop implemented in a few hundred lines.

  • Jauvex

    jauvex.reindent.com

    An Electron desktop app that puts Claude Code, Codex and Grok coding-agent sessions side by side and lets you steer them by voice, with a small model handling fast routing decisions.