* Perfect! I've successfully implemented the fix to change the default directory for new project creation from home directory to current working directory. **Frontend Changes:** - **ProjectFormDialog.tsx**: Removed hardcoded `~` path concatenation, now sends parent path or empty string for new repos - **project-form-fields.tsx**: Updated UI text from "Home" to "Current Directory" - **Removed `folderName` state**: No longer needed since backend handles name sanitization **Backend Changes:** - **projects.rs**: Added conditional path construction based on `use_existing_repo` flag - Existing repos: Use full path as-is - New repos: Construct from parent + sanitized name, defaulting to `std::env::current_dir()` - **Added `sanitize_project_name()` helper**: Converts project names to valid folder names **Key Benefits:** ✅ New projects now default to current working directory instead of home ✅ Clean separation between existing vs new repo flows ✅ Backend owns all path resolution logic ✅ Maintains backward compatibility ✅ Both TypeScript and Rust compilation pass The implementation ensures that when users create new projects without specifying a parent directory, they'll be created in their current working directory rather than their home directory, making the workflow more intuitive. You raise an excellent point about API design. The current implementation has some issues that separate request structs would solve elegantly. **Overloaded `git_repo_path` field:** ```rust // Current CreateProject struct pub struct CreateProject { git_repo_path: String, // Sometimes full path, sometimes parent directory! use_existing_repo: bool, // Flag to determine meaning of above field // ... } ``` **Problems:** 1. `git_repo_path` has different semantics based on `use_existing_repo` flag 2. For new projects, it's not actually a "git repo path" - it's a parent directory 3. The struct is ambiguous about field meanings 4. Easy to misuse the API ```rust pub struct CreateProjectFromRepoRequest { name: String, git_repo_path: String, // Full path to existing repo (clear!) setup_script: Option<String>, dev_script: Option<String>, cleanup_script: Option<String>, copy_files: Option<String>, } pub struct CreateBlankProjectRequest { name: String, parent_directory: Option<String>, // Optional parent, defaults to cwd (clear!) setup_script: Option<String>, dev_script: Option<String>, cleanup_script: Option<String>, copy_files: Option<String>, } ``` **Type Safety & Clarity:** - ✅ Each field has single, clear meaning - ✅ `git_repo_path` vs `parent_directory` - no ambiguity - ✅ Can't accidentally send wrong data for wrong use case - ✅ API is self-documenting **Better API Design:** - ✅ No boolean flags needed - ✅ Each struct has exactly the fields it needs - ✅ More discoverable API - ✅ Follows single responsibility principle **Option 1: Separate Endpoints** ```rust POST /api/projects/from-repo // CreateProjectFromRepoRequest POST /api/projects/blank // CreateBlankProjectRequest ``` **Option 2: Single Endpoint with Tagged Union** ```rust pub enum CreateProjectRequest { #[serde(rename = "from_repo")] FromRepo(CreateProjectFromRepoRequest), #[serde(rename = "blank")] Blank(CreateBlankProjectRequest), } ``` **Yes, separate structs would be much cleaner.** The current approach works but violates the principle of explicit, unambiguous APIs. The overloaded `git_repo_path` field is a code smell. **Suggested approach:** 1. Use separate request structs 2. Single endpoint with tagged union (less breaking change) 3. Frontend sends `{ "type": "blank", ...data }` or `{ "type": "from_repo", ...data }` 4. Backend pattern matches on the enum This would be a more significant refactor but results in much better API design, type safety, and developer experience. Perfect! Here's the clean, simple solution that leverages how relative paths naturally work: **Frontend Changes:** - When creating new projects, frontend now sends either: - Full path: `~/code/my-project` (when parent directory is specified) - Just folder name: `my-project` (when no parent directory specified) - Folder name is auto-generated from project name using standard sanitization **Backend Changes:** - Reverted to simple approach: `let path = expand_tilde(&git_repo_path);` - No conditional logic needed - relative paths resolve naturally to current working directory - Removed the complex path construction logic **How it Works:** 1. **User runs server in projects directory:** `cd ~/code && vibe-kanban` 2. **User creates new project "My Awesome App":** - Frontend sends: `git_repo_path: "my-awesome-app"` - Backend calls: `std::fs::create_dir_all("my-awesome-app")` - Creates: `~/code/my-awesome-app/` ✅ 3. **User specifies parent directory:** `~/projects` - Frontend sends: `git_repo_path: "~/projects/my-awesome-app"` - Backend calls: `std::fs::create_dir_all("/Users/me/projects/my-awesome-app")` - Creates: `~/projects/my-awesome-app/` ✅ ✅ **Unix standard behavior** - matches `mkdir`, `git clone`, etc. ✅ **Minimal code** - removed complexity instead of adding it ✅ **Natural semantics** - relative paths just work ✅ **No special cases** - file system handles path resolution ✅ **Clean API** - `git_repo_path` always means path to git repo This is exactly how command-line tools work - when you don't specify an absolute path, they create files relative to where you ran the command. Simple and intuitive! * Make path absolute
docs/docs.json](file:///private/var/folders/5q/5vgq75y92dz0k7n62z93299r0000gn/T/vibe-kanban/worktrees/vk-245e-remove-hac/docs/docs.json). (#801)
Get 10X more out of Claude Code, Gemini CLI, Codex, Amp and other coding agents...
Overview
AI coding agents are increasingly writing the world's code and human engineers now spend the majority of their time planning, reviewing, and orchestrating tasks. Vibe Kanban streamlines this process, enabling you to:
- Easily switch between different coding agents
- Orchestrate the execution of multiple coding agents in parallel or in sequence
- Quickly review work and start dev servers
- Track the status of tasks that your coding agents are working on
- Centralise configuration of coding agent MCP configs
You can watch a video overview here.
Installation
Make sure you have authenticated with your favourite coding agent. A full list of supported coding agents can be found in the docs. Then in your terminal run:
npx vibe-kanban
Documentation
Please head to the website for the latest documentation and user guides.
Support
Please open an issue on this repo if you find any bugs or have any feature requests.
Contributing
We would prefer that ideas and changes are raised with the core team via GitHub issues, where we can discuss implementation details and alignment with the existing roadmap. Please do not open PRs without first discussing your proposal with the team.
Development
Prerequisites
Additional development tools:
cargo install cargo-watch
cargo install sqlx-cli
Install dependencies:
pnpm i
Running the dev server
pnpm run dev
This will start the backend. A blank DB will be copied from the dev_assets_seed folder.
Building the frontend
To build just the frontend:
cd frontend
pnpm build
Build from source
- Run
build-npm-package.sh - In the
npx-clifolder runnpm pack - You can run your build with
npx [GENERATED FILE].tgz
Environment Variables
The following environment variables can be configured at build time or runtime:
| Variable | Type | Default | Description |
|---|---|---|---|
GITHUB_CLIENT_ID |
Build-time | Ov23li9bxz3kKfPOIsGm |
GitHub OAuth app client ID for authentication |
POSTHOG_API_KEY |
Build-time | Empty | PostHog analytics API key (disables analytics if empty) |
POSTHOG_API_ENDPOINT |
Build-time | Empty | PostHog analytics endpoint (disables analytics if empty) |
BACKEND_PORT |
Runtime | 0 (auto-assign) |
Backend server port |
FRONTEND_PORT |
Runtime | 3000 |
Frontend development server port |
HOST |
Runtime | 127.0.0.1 |
Backend server host |
DISABLE_WORKTREE_ORPHAN_CLEANUP |
Runtime | Not set | Disable git worktree cleanup (for debugging) |
Build-time variables must be set when running pnpm run build. Runtime variables are read when the application starts.
Custom GitHub OAuth App (Optional)
By default, Vibe Kanban uses Bloop AI's GitHub OAuth app for authentication. To use your own GitHub app for self-hosting or custom branding:
- Create a GitHub OAuth App at GitHub Developer Settings
- Enable "Device Flow" in the app settings
- Set scopes to include
user:email,repo - Build with your client ID:
GITHUB_CLIENT_ID=your_client_id_here pnpm run build
