mrkeyoor.com_
Sun 16 Aug 16:49 UTC
Self-Hostedevaluationupdated 16 Aug 2026

CPA-Manager-Plus

CPA Manager Plus is a self-hosted control panel and observability dashboard for CLIProxyAPI, an AI gateway commonly shortened to CPA. It helps operators manage providers and credentials while retaining request history, usage, estimated cost, quota, failures, and account health locally. The main README and full documentation are in English, with a Chinese README and bilingual release notes also available.

Verdict

CPA Manager Plus is the most compelling upgrade for a CLIProxyAPI operator who has outgrown a live status page and needs durable operational history. Full Mode earns its extra service with useful failure, cost, quota, and account views, but it is not a billing ledger or a security boundary. Adopt it if CPA is already strategic, and treat its SQLite data and management keys like production infrastructure.

Setup3/5Clear Docker path, but Full Mode adds a stateful second service
Docs5/5Strong bilingual setup, operations, migration, and recovery guides
Community4/5Fast issue and pull-request activity around a growing user base
Maturity3/5Useful operations stack with young storage and auth edge cases

Who it’s for

CLIProxyAPI operators who need searchable request history and cost analysis beyond the upstream management screen.
Teams managing several Gemini, Codex, Claude, Vertex, xAI, or OpenAI-compatible credentials through CPA.
Self-hosters who want quota inspection, account health signals, and controlled account automation without a hosted analytics service.
Administrators comfortable backing up SQLite and protecting management keys for a service that can alter gateway configuration.

Who it’s NOT for

Anyone not using CLIProxyAPI: the README says CPAMP does not replace the proxy or forward model traffic by itself.
Teams that need invoice-grade cost accounting for every media model: the dashboard reports estimated cost, and an open request says image and video billing units are not represented by its per-token price fields.
Operators requiring hard isolation between particular subscription accounts and client API keys: an open request explains that current prefix-based routing is soft isolation and enforcement depends on upstream CLIProxyAPI support.
Installations without disciplined database backups: the release notes require usage.sqlite, its WAL and SHM files, and data.key to be backed up together, while an open v1.11.12 report describes a corrupted database causing a restart loop before the HTTP server binds.
Users relying on CPAMP's Codex OAuth flow in every region: an open Windows report shows successful browser authorization followed by a region-related 403 during token exchange.

Setup reality

The Docker quick start is credible: run CPA and CPAMP as two containers, open port 18317, retrieve the admin key from the Manager Server log, then provide the CPA URL and Management Key. It is still a two-service system with separate ports, credentials, versions, storage, and failure modes. Lightweight mode can replace only CPA's web panel without another database, but persistent history and automation require Full Mode. Production setup also means binding the panel safely, preserving the SQLite WAL set with data.key, validating CPA version compatibility, and rehearsing recovery before upgrades.

The missing operations layer for CLIProxyAPI

CPA Manager Plus, or CPAMP, is easy to misunderstand from the name. CPA here means CLIProxyAPI, the separate gateway that exposes multiple AI providers through compatible endpoints. CPAMP does not carry model traffic. It manages that gateway and turns its usage queue into a persistent operational record.

If CLIProxyAPI is not already part of your stack, CPAMP has nothing to manage. If it is, the panel answers questions the basic upstream interface cannot answer well over time: which models or accounts are failing, where estimated cost is accumulating, which client key produced a request, how quota windows look, and whether a credential appears healthy.

Provider management covers Gemini, Codex, Claude, Vertex, xAI, and OpenAI-compatible services. Operators can work with auth files, OAuth logins, API keys, aliases, priorities, plugins, logs, and system settings. The dashboard then connects configuration to calls, tokens, latency, failure status, cache behavior, projects, channels, accounts, and credentials. That is a practical combination for a small internal gateway team.

Lightweight and Full Mode are different products

CPAMP offers a lightweight panel that replaces CLIProxyAPI's management page on port 8317. It adds no service or database, making it the sensible option when the goal is a different interface. The upstream CLI Proxy API Management Center remains an even more conservative choice because its UI stays maintained with the gateway project.

Full Mode runs a Manager Server, normally on port 18317, alongside CPA. This is where persistent request history, cost analytics, scheduled inspection, automation, and local SQLite storage appear. The supplied Compose example runs two containers with separate persistent volumes. After launch, you retrieve a CPAMP Admin Key from the Manager Server log and enter the CPA address and Management Key during setup.

That quick start still leaves an operator with two versions, credentials, health states, networking, and storage. The README recommends CPA v7.1.39 or newer and requires at least v6.10.8 for the HTTP usage queue. Upgrade planning must consider that compatibility instead of blindly pulling both latest images.

Monitoring is the reason to install it

Full Mode persists CPA usage events in SQLite and makes them searchable by account, client API key, and realtime request views. Failure evidence is redacted, and normal APIs and JSONL exports do not expose stored raw failure bodies. History can be imported or exported as JSONL, which is useful for migration and incident work.

Cost analysis is unusually detailed. It groups calls, tokens, estimated cost, latency, and failures across model, provider, account, credential, API key, project, channel, and time. Pricing can sync from models.dev, with LiteLLM and OpenRouter fallbacks, and local overrides handle aliases or internal models. The word estimated matters: this is an operational view, not the provider's invoice.

An open request exposes a boundary. Its price rows were based on dollars per million tokens and could not represent per-image or per-video-second billing metadata. A matching pull request was active, but users should test the released behavior for non-token models. Finance reconciliation still belongs against provider billing records.

Account views add credential state, available quota signals, reset evidence, workspace state, and provider-specific health information when available. Controlled cooldowns and an account action queue can help recover from quota or credential failures. These are valuable operator tools, but provider OAuth behavior remains outside CPAMP's control. One open Windows report shows Codex browser authorization succeeding before the token exchange returned a country or region 403.

Local data brings privacy and chores

The project says it requires no account registration, contains no telemetry SDK, and keeps request history, configuration, model prices, inspection history, and automation state in local files. External requests are limited to CPA and integrations an operator configures or triggers, including OAuth, provider checks, plugin releases, and price synchronization. CPA Management Keys are encrypted before SQLite storage.

The encryption key creates a backup obligation. The latest release notes tell operators to copy usage.sqlite, usage.sqlite-wal, usage.sqlite-shm, and data.key together, and not to delete an active WAL. Lose data.key and the encrypted management keys cannot simply be recovered from the database. Large databases may also consume extra CPU, I/O, and disk while an upgrade backfills derived monitoring data.

Version 1.11.12 added better SQLite status reporting, bounded non-blocking WAL checkpoints, and rebuildable derived data for seven-day and thirty-day queries. Even so, an open report from that version describes a malformed 5.3 GB database that made the container exit before binding its HTTP port, producing an endless restart loop. The report concerns one installation and suspected damage in derived tables, but it is enough reason to monitor database checks, use appropriate storage, and rehearse restore procedures.

Access control has another boundary. An open request explains that assigning a subscription account exclusively to selected client API keys cannot be enforced by the panel alone because routing happens in CLIProxyAPI. Existing model-prefix routing provides only soft separation. Do not mistake a management view for tenant isolation. Likewise, put the panel behind your own firewall, private network, or authenticated reverse proxy rather than waiting for dashboard-level IP blocking.

Active, focused, and still young

CPA Manager Plus had about 2,600 stars and 41 open issues and pull requests on August 16, 2026. The repository was pushed August 15, release v1.11.12 arrived August 7, and issues and pull requests were active through August 16. That is strong momentum. The MIT license, native packages, container images, amd64 and arm64 support, and detailed English and Chinese documentation all lower adoption risk.

The project is moving quickly enough that production users should pin releases and read upgrade notes. Its current rough edges involve meaningful areas such as storage recovery, provider authentication, and access policy, not merely styling. Still, its scope is disciplined: it observes and manages CPA instead of pretending to replace it. For teams committed to CLIProxyAPI, that focus makes CPAMP worth running. For everyone else, a gateway-native dashboard or general observability platform is the cleaner purchase.

Alternatives

ProjectWhat it isPick it when
CLI Proxy API Management CenterThe upstream web interface for editing CLIProxyAPI configuration and viewing runtime status.pick this instead when you only need the official CPA management UI and do not need another service, database, or persistent analytics.
LiteLLMAn AI gateway that normalizes many model providers and includes routing, budgets, and usage controls.pick this instead when you need the gateway itself, not a management layer tied specifically to CLIProxyAPI.
LangfuseA self-hostable LLM observability platform with traces, evaluations, prompts, and datasets.pick this instead when deep application tracing and evaluation matter more than managing CPA credentials and quotas.

What people are saying

  1. [github-trending] seakee/CPA-Manager-Plus

Sources

  1. CPA Manager Plus README
  2. CPA Manager Plus v1.11.12 release notes
  3. Choosing a CPA panel
  4. Issue 523: SQLite corruption restart loop
  5. Issue 315: account to API key isolation
  6. Issue 554: Codex OAuth token exchange 403