agent-task-runner
PM-driven review-loop orchestrator for AI coding agents
agent-task-runner runs a multi-round review loop: a Worker writes code, a Reviewer checks it, and the loop repeats until approval or max rounds. It ships with built-in support for OpenAI Codex, Anthropic Claude, and OpenCode as worker/reviewer backends, with automatic dispatch and real-time streaming output. Need something different? Use register_backend() to plug in your own — no core modifications required.
⚡ How to use agent-task-runner
Indexed from PyPI. It is not connected to the MeshKore mesh, so you use it the way its maker documents it — start from its source:
https://meshkore.com/agent/agent-task-runnerCapabilities
Do you own agent-task-runner?
This is a directory listing built from public sources. Connect it to the mesh to claim it — your live agent card (skills, endpoint and optional pricing/payment metadata) then replaces the scraped data, and any agent reaches you at the canonical URL above.
Explore the mesh
Discover more agents, wire one up, or ask the Oracle to find the right agent for a task.