| What it does | Canary rollouts for prompts and models with automatic quality gates and rollback
| Mac proxy client for Claude Code and Codex with local token usage tracking and API configuration management
|
|---|
| Stage | Not given
| MVP
|
|---|
| Founded | Not given
| Not given
|
|---|
| Based in | Not given
| Not given
|
|---|
| Pricing model | Free trial
| Free
|
|---|
| Pricing | 7-day free trial with 1,000 judged evaluations (no card required). Indie: $20/month or ₹1,699/month (3,000 judged evaluations/month). Starter: $49/month or ₹4,099/month (10,000 judged evaluations/month). Pro: $149/month or ₹12,499/month (100,000 judged evaluations/month). Enterprise: custom pricing.
| Not given
|
|---|
| Key features | - Canary deployments for prompts and models with progressive traffic steps
- LLM judge scoring responses on helpfulness, accuracy and clarity
- Automatic rollback when quality drops below threshold
- Drop-in replacement for OpenAI-compatible clients
- Support for OpenAI, Anthropic, Gemini, OpenRouter and Vercel AI Gateway
- Request log with prompts, responses, cost and judge verdict
- Failover and routing across providers
- Alerts via email, Slack and webhooks
- Dashboard and API for managing rollouts
- Controller makes routing decisions every 30 seconds
| - TUN interception for system-wide proxy routing without environment variables
- Split traffic by domain, IP address, and application
- Multiple API configuration profiles with one-click switching
- Local token usage and cost estimation by date, model, and session
- Session analysis with context length warnings and cost breakdown
- Support for VLESS, VMess, Trojan, Hysteria2, AnyTLS, Shadowsocks, and Base64 subscriptions
- Automatic detection of claude and codex process traffic
- DeepSeek Harness usage tracking
- Configuration file auto-write for Claude Code settings.json and Codex config.toml
|
|---|
| What makes it different | - Automatically detects and rolls back silent quality failures that don't trigger errors or alerts
- Quality decisions based on real traffic and LLM judging, not health checks alone
- Minimal latency overhead of about 0.4ms median in request path
- Every decision audited with exact metrics that triggered routing changes
- Can run in the cloud or inside customer's own network for data privacy
| - All three functions—proxy routing, API management, and usage tracking—integrated into one Mac app designed for Claude Code and Codex developers
- Local cost estimation based on actual token usage read from local logs, no forwarding gateway required
- Support for switching between official and custom relay APIs without environment variable changes
|
| Community votes | 0 | 0 |
| DR (Domain Rating by Ahrefs) | Not checked yet ● no change since last check | Not checked yet ● no change since last check |
| Trust Flow (Majestic) | 0 | 0 |
| Citation Flow (Majestic) | 15 | 0 |
| Referring domains (Majestic) | 2 | 0 |