Codex CLI and mistral-vibe, fact by fact
| Fact | Codex CLI | mistral-vibe |
|---|---|---|
| StarsCodex CLI has 123,287 more stars (25×). | 128,366Verified 8 Oct 2026 | 5,079Verified 8 Oct 2026 |
| Newest commitBoth committed on the same day. | 8 Oct 20260 days old when we read itVerified 8 Oct 2026 | 6 Oct 20262 days old when we read itVerified 8 Oct 2026 |
| ContributorsCodex CLI has 465 more contributors (40×). | 477Verified 8 Oct 2026 | 12Verified 8 Oct 2026 |
| LicenseBoth ship under Apache-2.0. | Apache-2.0Verified 8 Oct 2026 | Apache-2.0Verified 8 Oct 2026 |
| Latest stable releaseBoth released on the same day. | rust-v0.161.0published 7 Oct 2026Verified 8 Oct 2026 | v2.26.0published 6 Oct 2026Verified 8 Oct 2026 |
| npm downloads | 25,613,321 a week@openai/codexVerified 8 Oct 2026 | not tracked for mistral-vibe |
| PyPI downloads | not tracked for Codex CLI | 613,081 a weekmistral-vibeVerified 8 Oct 2026 |
| Homebrew installsCodex CLI has 104,399 more Homebrew installs in 30 days (716×). | 104,545 in 30 dayscodexVerified 8 Oct 2026 | 146 in 30 daysmistral-vibeVerified 8 Oct 2026 |
| VS Code installs | not tracked for Codex CLI | 42,329mistralai.mistral-vibe-codeVerified 8 Oct 2026 |
| Repository | openai/codexRustVerified 8 Oct 2026 | mistralai/mistral-vibePythonVerified 8 Oct 2026 |
What we know about Codex CLI
Codex CLI is the only agent in this set that confines itself in an OS-enforced sandbox on first run, with network access off and writes limited to the working directory.
“By default, the agent runs with network access turned off. Locally, Codex uses an OS-enforced sandbox that limits what it can touch (typically to the current workspace), plus an approval policy that controls when it must stop and ask you before acting.”
Point an agent at a repository you do not trust: in the default `workspace-write` mode Codex edits inside the working directory and must ask before touching anything outside it.
“Codex asks for approval to edit files outside the workspace or to run commands that require network access.”
Use a ChatGPT plan you already pay for instead of a second subscription, on Free, Go, Plus, Pro, Business, Edu or Enterprise.
“ChatGPT Work and Codex are included in your ChatGPT Free, Go, Plus, Pro, Business, Edu, or Enterprise plan”
Stop a team from disabling its own guard rails: an administrator can forbid `approval_policy = "never"` and `sandbox_mode = "danger-full-access"` in a requirements file.
“requirements.toml (for example, disallowing approval_policy = "never" or”
Subscription spend is unpredictable: the most-commented open issue, 630 comments since 2026-03-13, is that Codex burns the plan budget too fast, and a second reports the 5-hour budget gone in 2-3 prompts.
“Codex (gpt-5.5, Plus plan) — rate-limit cost per token jumped ~10-20x since June 16, draining the 5h budget in 2-3 prompts”
The agent cannot install a dependency until you edit the config, because the default sandbox keeps the network off.
“For the ChatGPT desktop app, Codex CLI, or IDE extension, the default workspace-write sandbox mode keeps network access turned off unless you enable it in your configuration:”
Windows is the weakest platform: an open issue with 106 comments reports the app freezing on Windows 11 Pro on hardware with resources to spare.
“Codex App frequently freezes/stutters on Windows 11 Pro despite sufficient system resources”
A developer who wants to run a local Ollama model should choose Crush or goose; Codex signs in with a ChatGPT account or an OpenAI API key.
“Run `codex` and select **Sign in with ChatGPT**. We recommend signing into your ChatGPT account to use Codex as part of your Plus, Pro, Business, Edu, or Enterprise plan.”
What Codex CLI costs
ChatGPT plans that include Codex run $0 for Free, $8 a month for Go, $20 a month for Plus, and from $100 a month for Pro.
“Plus · Power a few focused coding sessions each week. · $20 /month”
The Business plan is $20 per user per month for 2 or more users billed annually, and $25 per user per month billed monthly.
“*2+ users, billed annually. $25 per user per month when billed monthly.”
What we know about mistral-vibe
Mistral Vibe sets its risk level by picking one of four named agent profiles — ask, plan, accept-edits and auto-approve — rather than by editing a permission table, and accept-edits, which auto-approves edits but not shell commands, is the shipped default.
“- **`ask`**: Requires approval for tool executions. · - **`plan`**: Read-only agent for exploration and planning. Auto-approves safe tools like `grep` and `read`. · - **`accept-edits`**: The default agent. Auto-approves file edits only (`write_file`, `edit`). Useful for code refactoring. · - **`a…”
Refactor with edits applied but shell commands still gated: that is the shipped default, the `accept-edits` agent.
“- **`accept-edits`**: The default agent. Auto-approves file edits only (`write_file`, `edit`). Useful for code refactoring.”
Run two agent sessions on one repository at once: `--worktree` claims a fresh git worktree per session on a `vibe/<name>` branch, so the checkouts cannot collide.
“Unlike the named form, this never reuses an existing worktree: Vibe claims a free name, adding `-2`, `-3` and so on if needed, so two sessions started at once can never land in the same checkout. The branch is always `vibe/<name>`, matching the worktrees Le Chat Desktop creates.”
Hand the agent a screenshot: `.png`, `.jpg`, `.jpeg`, `.gif` and `.webp` attach through `@` mentions as native multimodal content.
“- Image attachments via `@` mentions — `.png`, `.jpg`, `.jpeg`, `.gif`, `.webp` files are sent to vision-capable models (e.g. Mistral Medium 3.5) as native multimodal content.”
Windows is not a supported target, only a working one; Mistral tests and aims at UNIX.
“> [!WARNING] · > Mistral Vibe works on Windows, but we officially support and target UNIX environments.”
There is no bring-your-own-provider path in the default setup: Vibe asks for a Mistral API key from console.mistral.ai and stores it in `~/.vibe/.env`.
“To use Vibe, you'll need a Mistral API key. You can obtain one by signing up at [https://console.mistral.ai](https://console.mistral.ai).”
Interrupting the agent can break the turn: after an interrupt Vibe emits two user messages in a row, which the Devstral 2 template rejects, and the issue is open with 16 comments.
“bug: Mistral-Vibe produces multiple user messages in a row after interrupts, which the Devstral 2 template does not allow”
A Windows-first team should pick Crush, whose built-in Bash interpreter makes the same config run on Windows as on Linux.
“Because Crush has a native, built-in Bash interpreter, Bash-based config works identically across all platforms, including Windows.”
What mistral-vibe costs
Mistral's Free plan includes Vibe with limited coding sessions and $10 a month of API credits.
“Limited coding sessions. · State-of-the-art image generation. · Test Mistral models in Studio. · $10 /mo in API credits.”
The Pro plan is $14.99 a month, lifts the cap to all-day coding in the CLI, and carries $30 a month of API credits; Team is $24.99 per user per month.
“All-day coding in the CLI, IDE, or on web. · More image generations. · $30 /mo in API credits.”
Questions people ask
- Are Codex CLI and mistral-vibe still maintained?
- Codex CLI committed to openai/codex (main) on 8 Oct 2026. mistral-vibe committed to mistralai/mistral-vibe (main) on 6 Oct 2026. Both readings come from the default branch of each repository, on the date shown beside them.
- What do Codex CLI and mistral-vibe cost?
- Codex CLI: ChatGPT plans that include Codex run $0 for Free, $8 a month for Go, $20 a month for Plus, and from $100 a month for Pro. The Business plan is $20 per user per month for 2 or more users billed annually, and $25 per user per month billed monthly. mistral-vibe: Mistral's Free plan includes Vibe with limited coding sessions and $10 a month of API credits. The Pro plan is $14.99 a month, lifts the cap to all-day coding in the CLI, and carries $30 a month of API credits; Team is $24.99 per user per month. Every figure here is quoted from the vendor's own page and linked beside the claim.
- Is Codex CLI or mistral-vibe open source?
- Codex CLI's repository openai/codex reports the Apache-2.0 licence. mistral-vibe's repository mistralai/mistral-vibe reports the Apache-2.0 licence. We read the licence GitHub reports for the repository, which is not the same question as whether the hosted product is free.
How we check this page
- Machine facts. Stars, contributors, the newest commit on the default branch, the licence GitHub reports and the latest stable release come from the GitHub API, and download counts from npm, PyPI, Homebrew and the VS Code Marketplace. Each value carries the day it was last confirmed, never the day this page was built. The line under each label is arithmetic on those two values.
- Judgments. Every claim about what a tool suits, what it is bad at and what it costs is quoted from a page we read, and that page is linked beside the claim. Where there is no link, we wrote no claim.
- Index status. Both Codex CLI and mistral-vibe carry claims we read, quoted and linked. So this page is offered to search engines.
Related comparisons
Pairs we can answer for come first.
