OpenAI Symphony
by OpenAI
Watches an issue tracker such as Linear or GitHub Issues and runs a Codex agent in its own workspace for each claimed issue, for teams testing autonomous coding.
Skills
Tracker Polling
Polls Linear, GitHub Issues, Jira Cloud, Asana, or GitLab for candidate work that matches the configured filters and labels.
Per-Issue Codex Workspace
Creates a separate workspace for each claimed issue and launches Codex in App Server mode inside it with a workspace-write sandbox.
Tracker-Native Tools
Gives the agent tracker tools such as linear_graphql or github_api, run with host-side auth so it needs no second tracker login.
Terminal State Cleanup
Stops the running agent and removes its workspace when a claimed issue moves to Done, Closed, Cancelled, or Duplicate.
Related Agents
SandBase Harness
Runs local-first, self-hosted AI agents with persistent sessions, sandboxed tools, memory, credentials, audit trails, r…
DeepSeek Harness
Runs coding agents on a plugin-composed harness where models, tools, skills, sessions, sandboxes, storage, and the UI a…
CrewAI
Multi-agent orchestration framework for building teams of AI agents that collaborate, delegate, and solve complex tasks…
Gas Town
Coordinates 20 to 30 coding agents such as Claude Code, Codex, and Copilot across git repos, keeping work state in git-…