Enables MCP clients to plan, queue, run, poll, cancel, and retry typed local media jobs, with resource-aware supervision, verified outputs, progress events, and structured errors—without arbitrary shell access.
Enables MCP clients to delegate background subagent jobs to an IDE's local agent engine, queue and monitor them, and retrieve results while the orchestrator continues working.
Enables agents to submit and manage persistent, dependency-aware task graphs with immutable artifacts, resource reservations, durable event streaming, and retryable process execution over MCP.
Enables MCP clients to submit tasks to a local file-backed queue and later read or cancel them by ID, with results produced by a separately run worker.
Durable MCP server for managing long-running jobs locally, over SSH, or on Slurm clusters. Jobs survive client disconnects and return exit codes, bounded logs, and JSON artifacts.
Enables MCP clients to drive Codex Desktop and codex-app-server as a durable async worker for long-running tasks: submit work and get an operation or workflow ID immediately, then poll status, handle approvals and Plan Mode, and read final reports, diagnostics, and history. It adds retry-safe submission, duplicate prompt protection, restart recovery, and worker/queue concurrency management so orchestration never requires holding a single MCP call open for hours.