A Control Plane for Running Many Coding Agents
victormustar · x · 2026-07-20
The author says testing many models across many agent harnesses has become hard to manage.
Their current approach uses an orchestrator such as Hermes or OpenClaw to coordinate hundreds of agent sessions, but it is losing track and not working well. They are considering building a custom control flow that can plug into existing agents and make delegated runs a tracked, verified primitive rather than ad hoc SSH glue.
More from coding & agent
- A roundup of AI agents and MCP resources, including how to evaluate agents — _jaydeepkarale · 2026-07-21
- A full course shows how to build and deploy an AI agent with OpenAI and LangChain — _jaydeepkarale · 2026-07-21
- A beginner guide to AI agents points readers to a Stanford webinar — _jaydeepkarale · 2026-07-21
- A practical guide on how to evaluate AI agents — _jaydeepkarale · 2026-07-21
- MCP is headed toward easier scale, event-driven extensions, and workable file uploads — EricBuess · 2026-07-21
- Developers debate the missing composition model for AI agents — threepointone · 2026-07-21