# Symphony By **openai** ยท Software & Tools OpenAI's open-source agent orchestrator that converts project tasks into autonomous, isolated coding runs, so teams manage work, not coding agents. - Source: https://github.com/openai/symphony - Repository: https://github.com/openai/symphony - Tags: open-source, agent, orchestration, codex, automation, elixir, apache-2.0, engineering-preview - Pricing: free - Upvotes: 0 ## Features - Monitors a Linear board (or similar) for new work items - Spawns isolated, autonomous Codex agent runs per task - Generates CI status, PR review feedback, complexity analysis, and walkthrough videos as proof of work - Lands approved PRs automatically without manual supervision - Supports build-your-own implementation via a published SPEC.md - Elixir reference implementation included in the repo - Apache 2.0 licensed open-source project by OpenAI --- ## Why it matters Engineering teams spend significant time supervising AI coding agents step by step. Symphony inverts that dynamic: engineers define work at the task-board level and let autonomous agents handle implementation, verification, and merging. The result is fewer context switches and a higher ratio of shipped work per engineer. ## The big picture Symphony is OpenAI's open-source orchestration layer, built as the next step above harness engineering. Per the README, harness engineering is the prerequisite: once a codebase has reliable test and lint harnesses, Symphony can spawn isolated agent runs against each task and trust the harnesses to validate the output. ## How it works Symphony watches a project board, such as Linear, for incoming work. When a task appears, it spawns a Codex agent in an isolated run. The agent implements the change and produces proof of work: CI status, PR review feedback, complexity analysis, and a walkthrough video. Engineers review that evidence. When they accept, Symphony lands the PR safely. ## Zoom in Two setup paths exist. Option 1: point your preferred coding agent at SPEC.md and have it build Symphony in any language you choose. Option 2: use the Elixir-based reference implementation included in the repo under `elixir/README.md`. The reference implementation is explicitly marked experimental. ## Yes, but The README carries a clear warning: Symphony is a "low-key engineering preview for testing in trusted environments." It is not production-hardened software. Codebases without an established harness engineering foundation will see limited benefit because the proof-of-work signals depend on those harnesses being meaningful. ## The bottom line Symphony is a concrete bet that the next productivity unlock is not smarter agents but smarter orchestration: define work once, verify results, ship. If your codebase is already harnessed and your team is comfortable with agentic workflows, Symphony offers a direct path from task board to merged PR, with engineers in the loop at the review stage rather than at every keystroke. ## FAQ ### What is Symphony? Symphony is an open-source orchestration system from OpenAI that converts project-board tasks into isolated, autonomous coding runs. It monitors a task board such as Linear, spawns Codex agents to handle each task, collects proof-of-work evidence (CI status, PR review feedback, complexity analysis, and walkthrough videos), and lands approved pull requests automatically. The goal is to let engineers manage work rather than supervise individual coding agents. ### How do I set up and run Symphony? There are two paths. First, you can use the Elixir-based reference implementation included in the repository under `elixir/README.md`, which walks through environment setup. Second, you can point any coding agent at SPEC.md in the repo and ask it to build Symphony in the language of your choice. The README also suggests asking a coding agent to help with setup using the provided instructions. ### Is Symphony free and open source? Yes, Symphony is licensed under the Apache License 2.0 and published publicly by OpenAI on GitHub. The source code, spec, and Elixir reference implementation are all freely available. Note that running the underlying Codex agents that Symphony orchestrates may incur API costs separately. ### What is Symphony best for? Symphony is best for engineering teams that have already invested in harness engineering, meaning their codebase has reliable CI pipelines, tests, and lint checks. In that context, Symphony can spawn agents against task-board items and use those harnesses as meaningful proof-of-work signals. Teams managing high volumes of well-defined, bounded implementation tasks are the primary fit. ### How does Symphony differ from just running a coding agent directly? Running a coding agent directly requires an engineer to supervise each step: prompting, reviewing intermediate outputs, and deciding when to commit. Symphony adds an orchestration layer that automates the full cycle from task intake to PR merge, with structured proof-of-work artifacts replacing ad-hoc supervision. Per the README, the shift is from 'managing coding agents' to 'managing work that needs to get done,' which is a meaningful abstraction jump. ### What are Symphony's current limitations or risks? The README explicitly warns that Symphony is a 'low-key engineering preview for testing in trusted environments,' signaling it is not production-hardened. Its proof-of-work model depends entirely on the quality of a codebase's existing harnesses; weak or absent CI and tests mean the agents' output cannot be meaningfully verified before merge. It should not be run in untrusted or shared infrastructure at this stage. --- [View on Analog](https://analoghq.ai/openai/software-tools/symphony)