[{"data":1,"prerenderedAt":140},["ShallowReactive",2],{"project-\u002Fprojects\u002Fopen-run":3,"project-writing-\u002Fprojects\u002Fopen-run":23,"mdc--ymxa1d-key":41},{"slug":4,"title":5,"description":6,"body":7,"category":8,"sources":9,"name":13,"order":14,"status":15,"stack":16,"website":20,"repository":12,"featured":21,"path":22},"open-run","Open Run — a project by Dennis Adriaansen","Schedule coding agents on your own machine and review what each run changes.","\n## Give repeatable work a place to run\n\nOpen Run schedules coding-agent CLIs on a local machine. A project is a Git repository, an instruction is a prompt, and a trigger decides when the work starts.\n\nIt uses the agent CLIs a developer already has configured. Open Run itself does not require model API keys. The selected agent can still send prompts and code to its provider according to that agent’s settings.\n\n## A run should leave something you can review\n\nThe project includes schedules, one-off runs and webhook-triggered work, along with conversation history and Git diff review. Repeated work gets an execution directory tied to a recorded base commit.\n\nA useful automation produces an understandable change. The review step connects the instruction, the result, the checks and the diff.\n\n## Examples of the kind of work it supports\n\nA scheduled prompt might ask an agent to inspect a flaky test, explain a dependency change or prepare a small maintenance patch. These are example workflows, not promises that the tool will resolve every task unattended.\n\nThe machine and worker must be running for local schedules to fire. Agent availability and provider limits still apply.\n\n## Explore the implementation\n\nThe [Open Run repository](https:\u002F\u002Fgithub.com\u002Fdennisadriaans\u002Fopenrun) documents the CLI, runtimes, triggers and security model. It is the best place to check current behavior before configuring an automation.\n\nOpen Run sits beside [cloudconfig](\u002Fprojects\u002Fcloudconfig) and [Nuxt Agentic](\u002Fprojects\u002Fnuxt-agentic) in my work on making agent-driven applications and workflows easier to understand.\n","Coding agents",[10],{"label":11,"url":12},"Open Run README and current setup instructions","https:\u002F\u002Fgithub.com\u002Fdennisadriaans\u002Fopenrun","Open Run",3,"Open source",[17,18,19],"TypeScript","Node.js","Local agents","https:\u002F\u002Fgetopenrun.dev",false,"\u002Fprojects\u002Fopen-run",[24],{"slug":25,"title":26,"description":27,"body":28,"category":29,"sources":30,"date":33,"tags":34,"language":39,"draft":21,"project":4,"path":40},"scheduling-coding-agents-with-open-run","Scheduling coding agents with Open Run","The project behind local coding-agent schedules, with a focus on explicit tasks, visible changes and reviewable results.","\nA coding agent can help with a repeatable task, but someone still needs to say what should happen, where it should happen and how to check the result.\n\nOpen Run is my project for scheduling that work on a local machine. It uses coding-agent CLIs and connects their runs to projects, triggers, conversations and Git changes.\n\n## A schedule needs a precise instruction\n\n“Improve the project” leaves too many decisions open for an unattended run. A smaller instruction gives the result a clearer shape.\n\nFor example:\n\n> Inspect the failing date-formatting test. Explain the cause, make the smallest correction and run the relevant test. Leave the change available for review.\n\nThis is an example task, not a guarantee that the agent will fix it. Its value is that the goal, scope and verification step are visible.\n\n## Keep execution separate from acceptance\n\nA run can produce a change without deciding that the change belongs in production.\n\nThe diff is the bridge between the agent’s work and a developer’s judgment. The developer should be able to see which files changed and whether the checks relate to the original problem.\n\nA successful process exit alone does not establish that the application behaves correctly.\n\n## A local schedule has real operating conditions\n\nThe machine must be awake and the worker must be running for a schedule to fire. The selected CLI also needs to be available and configured.\n\nOpen Run does not require model API keys itself, but its agent CLIs still use their own subscriptions or provider configuration. “Local” describes where the orchestration runs; it does not mean the selected agent performs every model operation offline.\n\n## Make the history useful\n\nThe history of a run should help answer a few practical questions: what was requested, which agent ran, what changed and what was checked?\n\nThat is the reason I care about connecting instructions, conversations and diffs. It makes repeatable work easier to follow when someone returns to it later.\n\nRead the [Open Run repository](https:\u002F\u002Fgithub.com\u002Fdennisadriaans\u002Fopenrun) for current commands and runtime details, or visit [the project overview](\u002Fprojects\u002Fopen-run).\n","Backend & agents",[31],{"label":32,"url":12},"Open Run README, CLI and security details","2026-10-12",[13,35,36,37,38],"coding agents","automation","Git","scheduling","en","\u002Fblog\u002Fscheduling-coding-agents-with-open-run",{"data":42,"body":43},{},{"type":44,"children":45},"root",[46,55,61,66,72,77,82,88,93,98,104,119],{"type":47,"tag":48,"props":49,"children":51},"element","h2",{"id":50},"give-repeatable-work-a-place-to-run",[52],{"type":53,"value":54},"text","Give repeatable work a place to run",{"type":47,"tag":56,"props":57,"children":58},"p",{},[59],{"type":53,"value":60},"Open Run schedules coding-agent CLIs on a local machine. A project is a Git repository, an instruction is a prompt, and a trigger decides when the work starts.",{"type":47,"tag":56,"props":62,"children":63},{},[64],{"type":53,"value":65},"It uses the agent CLIs a developer already has configured. Open Run itself does not require model API keys. The selected agent can still send prompts and code to its provider according to that agent’s settings.",{"type":47,"tag":48,"props":67,"children":69},{"id":68},"a-run-should-leave-something-you-can-review",[70],{"type":53,"value":71},"A run should leave something you can review",{"type":47,"tag":56,"props":73,"children":74},{},[75],{"type":53,"value":76},"The project includes schedules, one-off runs and webhook-triggered work, along with conversation history and Git diff review. Repeated work gets an execution directory tied to a recorded base commit.",{"type":47,"tag":56,"props":78,"children":79},{},[80],{"type":53,"value":81},"A useful automation produces an understandable change. The review step connects the instruction, the result, the checks and the diff.",{"type":47,"tag":48,"props":83,"children":85},{"id":84},"examples-of-the-kind-of-work-it-supports",[86],{"type":53,"value":87},"Examples of the kind of work it supports",{"type":47,"tag":56,"props":89,"children":90},{},[91],{"type":53,"value":92},"A scheduled prompt might ask an agent to inspect a flaky test, explain a dependency change or prepare a small maintenance patch. These are example workflows, not promises that the tool will resolve every task unattended.",{"type":47,"tag":56,"props":94,"children":95},{},[96],{"type":53,"value":97},"The machine and worker must be running for local schedules to fire. Agent availability and provider limits still apply.",{"type":47,"tag":48,"props":99,"children":101},{"id":100},"explore-the-implementation",[102],{"type":53,"value":103},"Explore the implementation",{"type":47,"tag":56,"props":105,"children":106},{},[107,109,117],{"type":53,"value":108},"The ",{"type":47,"tag":110,"props":111,"children":114},"a",{"href":12,"rel":112},[113],"nofollow",[115],{"type":53,"value":116},"Open Run repository",{"type":53,"value":118}," documents the CLI, runtimes, triggers and security model. It is the best place to check current behavior before configuring an automation.",{"type":47,"tag":56,"props":120,"children":121},{},[122,124,130,132,138],{"type":53,"value":123},"Open Run sits beside ",{"type":47,"tag":110,"props":125,"children":127},{"href":126},"\u002Fprojects\u002Fcloudconfig",[128],{"type":53,"value":129},"cloudconfig",{"type":53,"value":131}," and ",{"type":47,"tag":110,"props":133,"children":135},{"href":134},"\u002Fprojects\u002Fnuxt-agentic",[136],{"type":53,"value":137},"Nuxt Agentic",{"type":53,"value":139}," in my work on making agent-driven applications and workflows easier to understand.",1794481660797]