Show HN: AgentRun – open-source, Self-improving Managed Agents
AgentRun is an open-source platform that supercharges agents with self-improvement, durable execution, and a control plane, making them smarter, more fault-tolerant, and more efficient. It supports popular agent harnesses such as Claude Code, Codex, OpenCode, and pi, and can be self-hosted or used through a hosted version. The platform includes features like self-improvement, web-grounded workflows, sandboxes, and detailed analytics, and can be customized with a model key. Users can create their own templates and run agents with ease, and the platform also supports Docker for sandboxing and file operations.
Read the full article at github.com →