codingsushirepo/local-dev-os — explained in plain English
Analysis updated 2026-05-18
Turn a product requirements document into trackable stories for an AI agent.
Let an AI coding agent find and execute the next ready task automatically.
Track which files an agent touched and log bugs it encounters.
Adapt the agent rulebook file to work with Cursor, Claude, or other AI tools.
| codingsushirepo/local-dev-os | 0xradioac7iv/tempfs | 52191314/web-agent-proxy-sdk | |
|---|---|---|---|
| Stars | 0 | 0 | 0 |
| Language | TypeScript | TypeScript | TypeScript |
| Setup difficulty | easy | moderate | moderate |
| Complexity | 2/5 | 3/5 | 4/5 |
| Audience | developer | developer | developer |
Figures from each repo's GitHub metadata at analysis time.
Requires Node.js and npm, runs a local backend and frontend on separate localhost ports.
Local Dev OS is a project tracker built specifically for autonomous AI coding agents rather than for humans. While tools like Jira or Linear are designed around people clicking through a browser, this tool gives AI assistants such as Claude, Codex, Gemini, or Cursor agents a structured way to read what a project needs, break it into trackable tasks, write the code, and log their own progress and bugs along the way, so an agent working alone does not lose track of what it is doing. It works as a small local application: you clone the repository, install its dependencies with npm, and start it with one command, which launches a backend server and a separate frontend client, each on its own local address. Once running, the intended workflow starts with writing a normal product requirements document describing the features and technical approach for an app you want built. You feed that document into Local Dev OS, and it automatically breaks it down into individual stories and milestones. An AI agent then checks the tool's API to find the next highest priority task marked as ready, writes the code for it, and when finished, updates that task's status, records which files it touched, and moves on to the next one. For an agent to actually behave this way, it needs a rulebook telling it how to use the system, and the project uses a file called GEMINI.md as its example rulebook, placed in the root of your project so the agent reads it as a guiding system prompt. Because the tool is not tied to any specific AI provider, you can adapt this same rulebook to other tools by copying its contents into whatever file your particular AI assistant automatically reads, such as a rules file for Cursor or a separate instructions file for another terminal based agent. The project is open to contributions from anyone in the open source community, who can submit issues or pull requests.
A local project tracker built for autonomous AI coding agents that turns a requirements document into trackable tasks the agent executes and logs itself.
Mainly TypeScript. The stack also includes TypeScript, Node.js, npm.
The README does not state a license for this project.
Setup difficulty is rated easy, with roughly 5min to a first successful run.
Mainly developer.
This repo across BitVibe Labs
Verify against the repo before relying on details.