Stars
Forks
Watchers
Developer links
CPA Manager Plus
CPA Manager Plus is a self-hosted observability dashboard and management panel that tracks every AI request flowing through your CLI Proxy API gateway, breaking down failures, costs, and account health across providers like OpenAI, Anthropic, xAI, and Codex in one interface. When a request fails, drill into the persistent history to see status codes, affected models, latency, and redacted failure evidence without exposing raw response bodies. The cost analytics engine breaks down token consumption and estimated spend by model, provider, account, API key, project, channel, and time range while tracking input, output, reasoning, cache, and service-tier pricing semantics separately. Model prices sync automatically from models.dev with LiteLLM and OpenRouter fallbacks, and you can add local overrides for aliases or internal models. For teams running Codex or xAI accounts, the health inspector reads quota windows, reset evidence, credential state, and workspace status on a configurable schedule, routing credential failures into an action queue for review rather than letting them silently degrade throughput. Deploy the Lightweight Panel to replace your existing CPA management UI without adding another service, or run Full Mode as a single Docker container that adds the Manager Server with persistent SQLite storage for request history, historical analytics, and automated account inspections. Export or import request history as JSONL for external analysis, and back up the SQLite files alongside your encrypted management keys. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.
Benefits
- Complete AI Cost Visibility
- Breaks down token consumption and estimated spend across every dimension: model, provider, account, API key, project, channel, and time range, distinguishing input, output, reasoning, cache, and service-tier pricing.
- Proactive Account Health
- Inspects Codex and xAI accounts on a configurable schedule, reading quota windows, reset evidence, and credential state; routes failures into a review queue before they silently degrade throughput.
- Failure Diagnosis Without Exposure
- Shows status codes, latency, token counts, cache state, and trace context for every failed request with redacted evidence so operators diagnose problems without accessing raw response bodies.
- Flexible Deployment Modes
- Lightweight Panel replaces the existing CPA management UI with zero additional services, while Full Mode adds a Manager Server with persistent SQLite history, analytics, and scheduled automation in one Docker container.
Features
- Request Monitoring
- Persists every request from the CPA usage queue in local SQLite with searchable views by account, client API key, status, latency, and token counts.
- Cost Analytics
- Breaks down calls, tokens, cost, and latency by model, provider, account, credential, API key, project, channel, and time range with auto-synced model pricing.
- Account Health Inspector
- Reads quota windows, reset timestamps, credential state, and workspace status for Codex, Claude, xAI, Gemini, and OpenAI-compatible providers on configurable schedules.
- Provider Management
- Configures AI providers including Gemini, Codex, Claude, Vertex, xAI, and OpenAI-compatible endpoints with OAuth, auth files, model aliases, and key testing.
- Dashboard Overview
- Connection status, request counts, success rates, average latency, token totals, estimated cost, collector health, and alerts on a single landing page.