Skip to content
Promptbook versus

Promptbook versus Codex

When to choose Promptbook

When you want Codex as a specialist in a broader operation. One agent can regularly triage requests and pass selected code changes to Codex within the same project.

When to choose Codex

When you mainly need to write or review a repository change and want to choose between a local environment and Codex Cloud.

Promptbook versus Codex
FeaturePromptbookCodex
Tasks and chats in project GitYes.book files in one repositoryPartialGit for code, separate tasks and sessions
Self-hostingYesYour computer or serverYesLocal CLI, optional cloud
Runs with your computer offConditionalWhen hosted elsewhereConditionalCodex Cloud
Where your data livesOn your host: project files with Git change history.Local project or Codex Cloud by mode; context at the model
AI modelsClaude, GPT, Gemini, Qwen, … including local. Automatic choice from available models for the task.Models available in Codex; custom provider via CLI configuration
Scheduled tasksYesRecurring agent tasksYesScheduled tasks in the app
IntegrationsUniversal browser. Web apps even without a connector.MCP, plugins, terminal and browser depending on environment
Passwords and credentialsLocal encrypted Wallet; passwords outside the agent’s context.Native sign-in/API keys and connected-environment credentials
Trust modelZero Trust: E2E App–engine. The relay cannot read working content.Local or cloud execution; selected model processes inputs
Mobile and remote controlYesApp over E2E to your own engineConditionalMobile host access or cloud tasks depending on environment
AI tools and selectionCodex, Claude Code, Gemini CLI, Qwen Code, OpenCode, … Automatic choice by task and availability.Codex CLI/app/cloud; capabilities vary by configuration

E2E protects the App–engine connection. External AI and services receive authorized inputs. Git keeps file history; it does not encrypt files or undo external actions. Wallet stays outside Git. Data and security ↗ Connection architecture ↗

Feature details

Self-hosting

PromptbookThe engine that runs and schedules agent work lives on your computer, company server or VPS under your control.

CodexCodex has a local mode for your development environment and Codex Cloud for tasks on OpenAI-managed computers.

Runs with your computer off

PromptbookClosing the controls leaves work running. Shutting down the engine host stops it. An engine on a running server can continue.

CodexShutting down a local host stops work on it. Codex Cloud runs independently of it.

Where your data lives

PromptbookAgents, tasks and conversations stay in project files on your host, with an auditable Git change history. Git does not encrypt files or undo actions in external services; Wallet stays outside it.

CodexLocal project or Codex Cloud by mode; context at the model

AI models

PromptbookClaude, GPT, Gemini, Qwen and other models through supported tools and extensible integrations, including local models depending on the adapter and task. You are not tied to one vendor. External models receive the inputs they need.

CodexModels available in Codex; custom provider via CLI configuration

Scheduled tasks

PromptbookGive a team of agents an ongoing responsibility, goal and rules. The engine runs one-off and recurring tasks.

CodexAlongside coding tasks in the app, CLI and cloud, you can schedule recurring work. Local project tasks need the machine and app running.

Integrations

PromptbookA universal browser operates web apps much like a person, including services without a ready-made connector or API. Capabilities depend on access, permissions and each service’s restrictions.

CodexMCP, plugins, terminal and browser depending on environment

Passwords and credentials

PromptbookWallet is an encrypted credential vault on your host, separate from Git. A protected integration fills verified sign-in forms without putting passwords in the agent’s context. Protection requires keeping Wallet isolated from agent tools.

CodexNative sign-in/API keys and connected-environment credentials

Trust model

PromptbookZero Trust for the App–engine connection: working content is encrypted between endpoints, and neither the relay nor central backend decrypts it. External AI and tools receive authorized inputs; account and operational metadata remain separate.

CodexLocal or cloud execution; selected model processes inputs

Mobile and remote control

PromptbookUse the control App to assign work, follow chats and manage the project over an authenticated E2E connection to your own engine. The local Console has separate access on the engine host. Closing the App does not stop the operation.

CodexMobile host access or cloud tasks depending on environment

AI tools and selection

PromptbookCodex, Claude Code, Gemini CLI, Qwen Code, OpenCode, GitHub Copilot, … A shared interface supports further integrations. Promptbook automatically chooses a suitable available tool and model for the task, capabilities and configured accounts, respecting your choices and limits.

CodexCodex CLI/app/cloud; capabilities vary by configuration