{"data":{"slug":"hatayama-unity-cli-loop","name":"unity-cli-loop","tagline":"Let AI Drive Unity, from Editor to Play Mode","github_url":"https://github.com/hatayama/unity-cli-loop","owner":"hatayama","repo":"unity-cli-loop","owner_avatar_url":"https://avatars.githubusercontent.com/u/842587?v=4","primary_language":"C#","stars":567,"forks":48,"topics":["ai","automation","cli","mcp","unity","unity3d"],"archived":false,"github_pushed_at":"2026-09-20T04:04:36+00:00","maintenance_label":"Very active","stars_delta_30d":67,"url":"https://www.graphcanon.com/tools/hatayama-unity-cli-loop","markdown_url":"https://www.graphcanon.com/tools/hatayama-unity-cli-loop.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/hatayama-unity-cli-loop","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=hatayama-unity-cli-loop","description":"Let AI Drive Unity, from Editor to Play Mode.","homepage_url":null,"license":"MIT","open_issues":23,"watchers":1,"ai_summary":"hatayama/unity-cli-loop is a toolkit enabling users to automate and control Unity workflows with AI capabilities.","readme_excerpt":"### Step 1: Install the CLI\n\n**macOS, Windows Git Bash:**\n\n```sh\ncurl -fsSL https://raw.githubusercontent.com/hatayama/unity-cli-loop/main/scripts/install.sh | sh\n```\n\n**Windows PowerShell:**\n\n```powershell\nirm https://raw.githubusercontent.com/hatayama/unity-cli-loop/main/scripts/install.ps1 | iex\n```\n\n**Homebrew (macOS):**\n\n```bash\nbrew install hatayama/tap/uloop\n```\n\nCheck that the install worked:\n\n```bash\nuloop -v\n```\n\nThe install succeeded when the first line shows the CLI version (for example `3.0.1`).\n\n---\n\n### Step 2: Install the Unity package\n\nRun this in the root of your Unity project:\n\n```bash\nuloop package install\n```\n\nThis adds the OpenUPM scoped registry and the `io.github.hatayama.uloopmcp` dependency to `Packages/manifest.json`. Add `--version <x.y.z>` to pin a specific version.\n\nThen launch Unity. If Unity is already running, this focuses that window instead:\n\n```bash\nuloop launch\n```\n\nOnce Unity is up, the package is installed into the project. The next step reads the skills from the installed package.\n\nLater, once the project has been built at least once, `uloop compile-check` reports compile errors without launching Unity at all. See [docs/compile-check.md](docs/compile-check.md).\n\n---\n\n### Step 3: Install the skills\n\nRun the command for your LLM tool in the root of your Unity project:\n\n```bash\n\n---\n\n# Install globally instead of into the project\nuloop skills install --claude --global\n\n---\n\n### Step 1: Install the Unity package\n\nIn `Window > Package Manager`, press \"+\", choose **Add package from git URL**, and enter:\n\n```text\nhttps://github.com/hatayama/unity-cli-loop.git?path=/Packages/src\n```\n\n<details>\n<summary>Installing from the OpenUPM scoped registry</summary>\n\n1. In `Project Settings > Package Manager`, add this entry to Scoped Registries:\n```text\nName: OpenUPM\nURL: https://package.openupm.com\nScope(s): io.github.hatayama.uloopmcp\n```\n2. In `Window > Package Manager`, select OpenUPM under My Registries and install Unity CLI Loop.\n\n</details>\n\n---\n\n### Step 2: Install the CLI\n\nOpen `Window > Unity CLI Loop > Settings` and press **Install CLI**:\n\n<img width=\"350\" alt=\"Settings window before the CLI is installed, showing the Install CLI button\" src=\"Packages/src/Documentation~/images/settings-cli-not-installed.png\" />\n\nYou are done when the CLI version is shown and the button changes to **Uninstall CLI**:\n\n<img width=\"350\" alt=\"Settings window after CLI detection succeeds, showing a green indicator and the CLI version\" src=\"Packages/src/Documentation~/images/settings-cli-installed.png\" />\n\n---\n\n### Step 3: Install the skills\n\nIn the same Settings window, select your target — for example **Claude Code**, or **Common (.agents)** for Codex and other tools that read `.agents/skills` — and press **Install Skills**:\n\n<img width=\"350\" alt=\"The Skills section of the Settings window, with a target selected and the Install Skills button ready\" src=\"Packages/src/Documentation~/images/settings-skills-install.png\" />\n\n<details>\n<summary>Working alongside V2 projects</summary>\n\nProjects on the V2 package and V3 projects can coexist on the same machine. Keep the V3 CLI installed: in a V2 project, the `uloop` command automatically uses the V2 CLI (downloaded on first use; Node.js 22 or later is required).\n\nDo not press **Update CLI** or **Downgrade CLI** in a V2 project's Settings window, and do not reinstall the V2 CLI with `npm install -g uloop-cli`. The old npm `uloop` would hide the V3 CLI. If that has already happened, run `npm uninstall -g uloop-cli`, then run the CLI installer from Step 1 of \"Install from the terminal\" again or press **Install CLI** in the Settings window.\n\n</details>\n\nThat's it! After installing Skills, LLM tools can automatically handle instructions like these:\n\n| Your Instruction | Skill Used by LLM Tools |\n|---|---|\n| \"Launch Unity for this project\" | `/uloop-launch` |\n| \"Check whether it compiles without launching Unity\" | `/uloop-compile-check` |\n| \"Fix the compile errors\" | `/uloop-compi","github_created_at":"2025-06-15T13:54:05+00:00","created_at":"2026-07-15T10:57:45.717292+00:00","updated_at":"2026-09-20T04:58:07.561361+00:00","categories":[{"slug":"developer-tools","name":"Developer Tools","url":"https://www.graphcanon.com/categories/developer-tools","markdown_url":"https://www.graphcanon.com/categories/developer-tools.md","api_url":"https://www.graphcanon.com/api/graphcanon/categories/developer-tools"}],"tags":[{"slug":"ai","name":"ai"},{"slug":"automation","name":"automation"},{"slug":"cli","name":"cli"},{"slug":"mcp","name":"mcp"},{"slug":"unity","name":"unity"},{"slug":"unity3d","name":"unity3d"}],"trust":{"provenance":{"is_fork":false,"github_id":1002447118,"owner_type":"User","methodology":"github_public_v1","parent_repo":null,"near_duplicate_slugs":[]},"computed_at":"2026-09-20T04:58:05.738Z","maintenance":{"label":"Very active","score":96,"methodology":"github_public_v1","releases_90d":30,"days_since_push":0,"last_release_at":"2026-09-10T07:12:12Z","stars_delta_30d":67,"open_issues_delta_30d":0},"security_summary":{"status":"no_manifest","scanner":null,"low_count":0,"high_count":0,"last_scan_at":"2026-07-15T10:57:46.951Z","medium_count":0,"scan_profile":"mcp_manifest","critical_count":0}},"capability_facts":{"scan":{"source":"repo_scan","observed_at":"2026-09-20T04:58:06.740Z"},"languages":{"value":["c#"],"source":"github.language","observed_at":"2026-09-20T04:58:06.740Z"},"license_spdx":{"value":"MIT","source":"github.license","observed_at":"2026-09-20T04:58:06.740Z"}},"decision_facts":{"hosting":null,"pricing":null,"requirements":{"notes":["Requires Unity and familiarity with C# programming language.","Ensure that your development environment supports the AI capabilities unity-cli-loop leverages for full functionality."],"min_ram_gb":null,"requires_docker":false},"constraints":{"min_ram_gb":null,"requires_docker":false},"when_to_use":["You need to integrate AI functionalities directly into your Unity project's workflow from the editor state through to play mode.","Looking to streamline repetitive tasks within Unity using command-line interface commands, particularly with support for interactive loop-based operations."],"when_not_to_use":["Your task requires a GUI-driven approach that does not rely on CLI or does not fit well into a loop automation scheme.","If your development environment strictly prohibits or has restrictions against MIT-licensed tools due to licensing concerns, as unity-cli-loop is released under the MIT license."],"source":"enrich:decision_facts","observed_at":"2026-07-17T09:08:29.678Z"},"constraint_facets":{"min_ram_gb":null,"requires_docker":false},"decision_summary":[{"label":"Requirements","value":"Requires Unity and familiarity with C# programming language.; Ensure that your development environment supports the AI capabilities unity-cli-loop leverages for full functionality."},{"label":"Adopt for","value":"unity-cli-loop is a specialized kit for automating and AI-driving workflows in Unity environments across editor and play mode stages."}]}}