You're the boss, agents are your team. They handle tasks on their own, message e
47d979a43d
- Added a retry mechanism for checking authentication status in the CliInstallerService to handle stale locks after Ctrl+C interruptions. - Introduced constants for maximum retries and delay between attempts to improve robustness. - Updated logging to provide detailed feedback on retry attempts and outcomes. |
||
|---|---|---|
| .claude | ||
| .github | ||
| .husky | ||
| bin | ||
| build | ||
| docker | ||
| docs | ||
| public | ||
| resources | ||
| scripts | ||
| src | ||
| test | ||
| .gitignore | ||
| .prettierignore | ||
| .prettierrc.json | ||
| CLAUDE.md | ||
| electron.vite.config.ts | ||
| eslint.config.js | ||
| LICENSE | ||
| package.json | ||
| pnpm-lock.yaml | ||
| pnpm-workspace.yaml | ||
| postcss.config.cjs | ||
| README.md | ||
| tailwind.config.js | ||
| tsconfig.json | ||
| tsconfig.node.json | ||
| vitest.config.ts | ||
| vitest.critical.config.ts | ||
Claude Agent Teams UI
You're the CTO, agents are your team. They handle tasks themselves, message each other, review each other's code. You just look at the kanban board and drink coffee.
100% free, open source. No API keys. No configuration.
What is this
A new approach to task management with AI agents.
- Assemble your team — create agent teams with different roles that work autonomously in parallel
- Agents talk to each other — they communicate, create and manage their own tasks, and leave comments
- Sit back and watch — tasks change status on the kanban board while agents handle everything on their own
- Review changes like in Cursor — see what code each task changed, then approve, reject, or comment
- Full tool visibility — inspect exactly which tools an agent used to complete each task
- Stay in control — send a direct message to any agent or drop a comment on a task whenever you want to clarify something or add new work
Installation
No prerequisites — Claude Code can be installed and configured directly from the app.
|
May trigger SmartScreen — click "More info" → "Run anyway" |
|
Development
Build from source
Prerequisites: Node.js 20+, pnpm 10+
git clone https://github.com/777genius/claude_agent_teams_ui.git
cd claude_agent_teams_ui
pnpm install
pnpm dev
The app auto-discovers your Claude Code projects from ~/.claude/.
Build for Distribution
pnpm dist:mac:arm64 # macOS Apple Silicon (.dmg)
pnpm dist:mac:x64 # macOS Intel (.dmg)
pnpm dist:win # Windows (.exe)
pnpm dist:linux # Linux (AppImage/.deb/.rpm/.pacman)
pnpm dist # macOS + Windows + Linux
Scripts
| Command | Description |
|---|---|
pnpm dev |
Development with hot reload |
pnpm build |
Production build |
pnpm typecheck |
TypeScript type checking |
pnpm lint:fix |
Lint and auto-fix |
pnpm test |
Run all tests |
pnpm test:watch |
Watch mode |
pnpm test:coverage |
Coverage report |
pnpm check |
Full quality gate (types + lint + test + build) |
TODO
- Run not only on a local PC but in any headless/console environment (web UI), e.g. VPS, remote server, etc.
- 2 modes: current (agent teams), and a new mode: regular subagents (no communication between them)
Contributing
See CONTRIBUTING.md for development guidelines. Please read our Code of Conduct.
Security
IPC handlers validate all inputs with strict path containment checks. File reads are constrained to the project root and ~/.claude. Sensitive credential paths are blocked. See SECURITY.md for details.