| What it does | Desktop workspace to run and review multiple Claude Code and Codex agents in parallel across projects
| Local MCP server manager for Claude, Cursor, VS Code and other AI clients
|
|---|
| Stage | Not given
| MVP
|
|---|
| Founded | Not given
| Not given
|
|---|
| Based in | SK
| SK
|
|---|
| Pricing model | Freemium
| Open source
|
|---|
| Pricing | Monthly $7.99 (then $9.99 after Jan 1, 2027), Yearly $79 billed annually (then $99 after Jan 1, 2027), Lifetime $249 (retires Jan 1, 2027). Team plans: $14.99 per seat monthly (then $19.99), $14.99 per seat monthly billed $99 yearly. All features included with all plans. 14-day free trial, no card r
| Free beta with no account or sign-up required. Source code available under MIT License.
|
|---|
| Key features | - Project task queues with parallel execution
- Saved sessions that can be resumed anytime
- Provider usage limits and rate limit tracking
- Plan Council: two agents review plans before code is written
- Mobile control to queue and review from phone
- Voice dictation for prompts and follow-ups
- Standup changelog feature to organize completed tasks
- Gamified progression with achievements and office customization
- Company mode for team visibility and collaboration
| - Server matrix showing which MCP servers are enabled across all supported AI clients
- Health checks and MCP Doctor to diagnose server connection failures
- Profiles to save and switch between different MCP stacks for different tasks
- Timestamped backups with atomic writes and external change detection
- Contract Guard to alert when servers change their tool definitions or descriptions
- Built-in catalog and support for custom JSON, JSONC and TOML configuration sources
- Context optimizer measuring tool-schema footprint and proximity to client limits
- Security scanning for invisible characters, credential exposure and malicious prompts in tool definitions
- Optional Gateway mode for supported stdio servers with local routing and native credential storage
- Live Activity logging with metadata-only recording and no payload capture
|
|---|
| What makes it different | - Each task gets its own fresh session to reduce hallucinations and token costs
- Nothing gets lost: every result waits for review before shipping
- Run 4-6 agents in parallel on average across projects
- Runs locally on your computer with your own credentials
- No tokens to buy: uses your own provider subscriptions
| - Works with any existing MCP server you already have configured without requiring migration or special catalog registration
- Detects and alerts when servers change what they tell your model between health checks
- Completely local with no cloud sync, no account, and no upload of configuration or API keys
- Public source code under MIT License so you can audit every request or build from source yourself
- Automatic timestamped backups before every change with the ability to browse and restore earlier versions
|
|---|
| Free plan | Not given
| Not given
|
|---|
| Open source | Not given
| Not given
|
|---|
| Platforms | Not given
| Not given
|
|---|
| Public API | Not given
| Not given
|
|---|
| Community votes | 0 | 0 |
|---|
| DR (Domain Rating by Ahrefs) | 2 ▼ −5 (down) since last check | 2 ● no change since last check |
|---|
| Trust Flow (Majestic) | 5 | 2 |
|---|
| Citation Flow (Majestic) | 23 | 17 |
|---|
| Referring domains (Majestic) | 6 | 51 |
|---|
VibeiDE
KyttoMCP