ChatGPT Plus
$20/mo
Standard Codex access
Codex CLI
OpenAI's agentic coding mode — in your terminal, IDE, app, or pocket.
OpenAI's agentic coding product. The Codex CLI is open source, but Codex now spans a CLI, VS Code and JetBrains extensions, a desktop app, and remote control from the ChatGPT mobile app. Sign in with a ChatGPT plan or BYO API key. Models include GPT-5.5, GPT-5.4 family, and GPT-5.3-Codex.
+Pros
- Multi-surface: CLI, VS Code/JetBrains extensions, desktop app, and ChatGPT mobile remote
- Tightly integrated with ChatGPT plans — no extra subscription for existing OpenAI users
- Run-iterate loop with sandboxed Docker execution ensures safe autonomous coding
- Plugin marketplace, Hooks, and Auto-review for flexible workflow automation
- Open-source CLI (npm) with BYO API key support
−Cons
- Ecosystem lock-in to OpenAI models — no support for Anthropic, Google, or local models
- Pro plan costs are high ($100–$200/mo) for heavy agentic use
- Docker sandbox required for full agent capabilities — adds setup complexity
- Younger multi-surface product — still maturing across IDE and mobile surfaces
Pricing
Pro (5x)
$100/mo
5x usage limits
Pro (20x)
$200/mo
20x usage limits
Business/Enterprise
Custom
Team and enterprise plans
API Key
Pay-per-token
BYO API key, standard pricing
Codex is OpenAI's agentic coding product. The CLI started as an open-source terminal tool that wrote code, ran it in a sandbox, and iterated until tasks were done. Over 2025–2026 it expanded into a full surface: the Codex CLI (npm, open source), an IDE extension (VS Code, JetBrains), the Codex app for desktop, and remote control from the ChatGPT mobile app via a connected host.
Codex is tightly integrated with ChatGPT plans — sign in with a ChatGPT account and your Plus, Pro, Business, or Enterprise plan covers Codex usage, with limits priced in credits per million tokens. Models include GPT-5.5 (recommended), GPT-5.4, GPT-5.4-mini, GPT-5.3-Codex, and GPT-5.3-Codex-Spark (research preview). The CLI and app run code in a Docker sandbox with configurable permission profiles, support a plugin marketplace, Hooks, Auto-review, and an in-app browser for verifying local UIs.
Key Features
• Multi-surface: CLI (open source), IDE extension (VS Code, JetBrains), Codex app
• ChatGPT mobile: drive Codex on a connected Mac host from your phone
• Models: GPT-5.5, GPT-5.4, GPT-5.4-mini, GPT-5.3-Codex, Codex-Spark
• Run-iterate loop: writes, runs in a sandbox, reads output, refines
• Plugin marketplace, Hooks, Auto-review for agent approvals
• In-app browser plugin for visual debugging of local dev servers
• BYO API key supported — falls back to standard API pricing
• ChatGPT plan auth (Plus, Pro $20/$100/$200, Business, Enterprise)
Version History
Added search across local conversation history with case-insensitive content matching. Made --profile the primary profile selector across CLI, TUI permissions.
Goals enabled by default with dedicated storage and progress tracking. codex remote-control now runs as a foreground command.
Python SDK first-class authentication (API key login, ChatGPT browser/device-code flows). codex exec resume now accepts --output-schema.
Richer TUI session controls with data-driven service-tier commands. @ mentions now search files, directories, plugins, and skills in one picker.
Plugin details now show bundled hooks, plugin sharing exposes link metadata. Added codex remote-control as simpler entrypoint for headless app-server.
Signature Snippet
$ codex 'Build a CLI tool that converts markdown to PDF and add tests'
⋮
Codex plans, scaffolds a Go module, writes the converter and tests, runs `go test`, captures the failures, and iterates until the test suite is green — all inside a sandboxed Docker workspace.More in this Space
Prime Agent (Prime Intellect)
Prime Agent is an open-source (MIT) self-improving coding and research harness by Prime Intellect, built on a Recursive Language Model that runs inside a persistent IPython REPL and a Continual Harness that refines its own state via /refine. It took the same frontier weights from 30.2% to 95.5% on ARC-AGI-3 RHAE Best@1, powered daemon-backed sessions, and ships no hosted offering.
OpenCodeReview (ocr)
OpenCodeReview (ocr) is Alibaba's open-source AI code-review CLI. It reads git diffs and drives an LLM agent through a hybrid architecture where deterministic pipelines handle file selection, rule matching, and comment positioning while the agent does the reasoning. Built on two years of internal use at Alibaba scale, it ships a multi-language ruleset and consumes roughly 1/9 of the tokens of general-purpose agents.
Delta (by Zed)
Multiplayer environment from Zed for coding with agents. Threads unify the agent conversation, the code edits, and human review in one shareable artifact, replacing the branch/PR loop. Built on DeltaDB, a CRDT-based version control layer that records every edit between commits alongside the prompts and reasoning that produced them.