Head to head · Agent harnesses · October 2026 research run

boxes.dev vs OpenAI Codex

OpenAI Codex scores 77.3 (BB) on agent readiness against boxes.dev's 53.2 (D), and leads in every scored category. Both do agent harnesses.

Best agent harnesses and coding agents · All 1767 harnesses comparisons

Which one, for what

boxes.dev D

Best for Developers who want Claude Code or Codex running on cloud copies of their dev environment, started from Slack, Linear, a schedule, an API call or another assistant.

Also in its favour

  • A hosted endpoint, with nothing to install

Watch for

No status page, incident history or SLA found

OpenAI Codex BB

Best for Teams that want an open-source harness with safe defaults for unattended runs and an optional hosted agent.

Ahead on

  • Reliability, 55 against 32
  • Schema & documentation, 90 against 57
  • Agent ergonomics, 80 against 60
  • Security & auth, 82 against 69
  • Payments & pricing, 90 against 50
  • Maintenance & community, 87 against 48
  • Transparency & trust, 85 against 60

Also in its favour

  • Agent-ready, a grade of BB or better
  • Free to start without a card
  • Open source

Watch for

Pre-1.0 at 0.166.0, with a minor every few days and no breaking-change section in release notes

Why the edge

Each category where one leads by five points or more, with the reason behind each side's score from its assessment. The numbers are in the table below; this is what they stand for.

Payments & pricing OpenAI Codex +40

boxes.dev 50

No x402, MPP or L402 (0). Plan prices are public ($19, $99 and $249 a seat a month) and extra usage is $0.40 a box-hour, with a box-hour defined as one hour of a 4 vCPU, 8 GiB devbox (30). A free trial of 20 box-hours. The help page says some teams must add a payment method before starting, so a card-free start is not certain (20 of 30). A person signs in with Google or Apple and approves the OAuth grant or creates the automation secret in the desktop app (0). 0+30+20+0 = 50.

OpenAI Codex 90

Harness reading of the published rubric. No payment protocol (0). Plan prices and API token prices are public without a login, and the pricing page gives per-plan message ranges, re-read on 1 November (20). ChatGPT Free and Go include Codex, and Free needs no card (20). --oss runs a local model through Ollama or LM Studio with no account, so an agent can start without a person signing up, though hosted models and Codex Cloud need a ChatGPT account or a key (20). 0 + 20 + 20 + 20 = 60. Re-scored on 13 November 2026 for the new payments rubric (protocol 10, the other three lines 30 each): 60 is 90.

Maintenance & community OpenAI Codex +39

boxes.dev 48

Closed service. CLI @boxes-dev/cli 1.0.1134 published on 17 November 2026 (30). Only one dated product update was found, on 27 October 2026, and earlier CLI versions' dates were not read, so three releases in 90 days are not established (0). A support address, an in-app chat and a blog, with no public tracker or changelog (8 of 25). A CLI but no SDK, and no entry in the official MCP registry was looked for (5 of 15). The CLI is published from GitHub Actions with npm trusted publishing and signatures (5 of 10). 30+0+8+5+5 = 48.

OpenAI Codex 87

0.166.0 on 29 October 2026 (30). 36 stable release tags between 5 August and 29 October, from 0.146.1 to 0.166.0 (20). Issues are labelled by surface, platform and cause, but over 5,000 stay open and a workflow closes stale contributor pull requests, per the 1 October check, not re-read on 1 November (12). TypeScript and Python SDKs are in the same repository and built in CI (15). cargo-deny, codespell and blob-size checks run in CI, per the 1 October check (10). 30 + 20 + 12 + 15 + 10 = 87.

Schema & documentation OpenAI Codex +33

boxes.dev 57

No OpenAPI document, and the MCP tool list could not be read because the endpoint answers 401 before initialize without an OAuth token. The automation API's request and response fields are documented in prose tables (5 of 25). llms.txt with every help page listed (10). The help pages say when to target a new devbox, an existing devbox or an existing thread, when to steer a busy agent and when to wake a devbox first (16). Field tables with enum values such as backend (codex or claude), delivery (steer or next) and four run statuses, and unknown fields are rejected. The MCP schemas themselves were not seen (9 of 15). curl examples and named errors such as 409 devbox_unavailable, 409 thread_unavailable and 503 devbox_wake_failed, with what each means (12). /v1 in the API path on the home page, a single dated product update of 27 October 2026 and no changelog (5 of 15). 5+10+16+9+12+5 = 57.

OpenAI Codex 90

Framework reading. A JSON Schema for config.toml in the repository (codex-rs/core/config.schema.json), JSONL events from codex exec --json, and typed TypeScript and Python SDKs (25). llms.txt at learn.chatgpt.com with a Markdown twin for every page, re-read on 1 November (10). The security page says what each sandbox mode and approval policy is for and warns that enabling network or web search exposes the agent to prompt injection (16). Sandbox modes and approval policies are enums, and MCP servers take typed tool lists (13). Examples throughout, and --output-schema validates the final message. The non-interactive page names the event types, turn.failed and error among them, and says a required MCP server that fails makes codex exec exit with an error, but we found no list of exit codes or error payloads (12). Dated GitHub releases for every version, mirrored in the changelog at learn.chatgpt.com, which runs to 0.166.0 on 29 October (14). 25 + 10 + 16 + 13 + 12 + 14 = 90.

Transparency & trust OpenAI Codex +25

boxes.dev 60

Closed service under the Common Paper Cloud Service Agreement 2.1, dated 20 October 2026, with the standard terms' machine-learning clause deleted and California law (15). The privacy policy of 21 October 2026 gives retention by data type (session replay about 30 days, Slack data deleted within 14 business days of disconnecting), and the backup clause matches the terms (22 of 30). Price changes take 30 days' notice under the terms. No deprecation policy for the API or MCP server found (5 of 20). Service providers are named (Convex, Cloudflare Workers, Expo, OpenAI, Amplitude, Sentry, Google and Apple), but the host that runs devboxes is unnamed and data may be processed in the US and elsewhere (12 of 20). 15+22+5+12 = 54.

OpenAI Codex 85

Apache-2.0 for the CLI and SDKs (30). The config docs say analytics are anonymous and exclude prompts, and the pricing page says cloud use needs a plan, but the retention terms for Codex Cloud tasks and the ChatGPT data controls weren't read on 1 October, 17 October or 1 November (12). The changelog at learn.chatgpt.com dates model retirements ahead of time with replacements (GPT-5.4 and GPT-5.4 mini announced on 31 July for 31 August, GPT-5.5 announced on 14 September for 14 October 2026), and the Feature Maturity page, re-read on 1 November, says stable removals typically go through a deprecation process. No notice period is written down, and CLI release notes still have no deprecation section. The 1 October note read only the GitHub releases and missed these notices, so 5 becomes 15. Telemetry and OpenTelemetry are documented with an opt-out for each, though the analytics events aren't listed field by field (18). 30 + 12 + 15 + 18 = 75.

Reliability OpenAI Codex +23

boxes.dev 32

Hosted reading, for the remote MCP server at api.boxes.dev/mcp and the automation run endpoints. No status page found. The site footer says "All systems normal" with no link, and the trust centre at trust.boxes.dev draws in a script our reader could not run (0). No readable incident history (5). No request rate limits found. Plans cap awake devboxes (3 on the trial, 5 to 25 on paid plans), and the API answers 409 active_fork_limit_reached at the cap (5 of 15). The automation API takes an Idempotency-Key and returns the original run on a retry with idempotentReplay: true, and the MCP connection retries a lost start or message with the same request key. No Retry-After or backoff guidance found (12 of 15). No SLA found (0). Neither the MCP connection nor the automation API is marked beta, and the product launched in June 2026 per its own blog (10). 0+5+5+12+0+10 = 32.

OpenAI Codex 55

Local-package reading. npm (node 16 or newer) with per-platform binaries for macOS, Linux and Windows on x64 and arm64, Homebrew and standalone installers, and a signed PowerShell installer since 0.162.0, per the 17 October check, with 0.166.0 on 29 October the newest tag (20). Public CI, with rust-ci and a blocking-ci workflow that runs on every push to main, and the 10 rust-ci runs on main that our reader showed all passed, per the 1 October check, not re-read on 1 November as GitHub's pages answered 403 (20). Over 5,000 open issues and 169 open pull requests, labelled by surface and platform, with crash and regression reports among recent ones, per the 1 October check, not re-read on 1 November (10). 0.x minors every few days, and release notes for 0.164.0 to 0.166.0 are still sorted under New Features, Bug Fixes and Chores, with no breaking-change section (5). 0.166.0, pre-1.0 (0). 20 + 20 + 10 + 5 + 0 = 55. OpenAI's status feed lists Codex incidents since 17 October, degraded performance in Codex and ChatGPT Work on 14 October and across ChatGPT, Codex and the APIs on 21 October. The local-package reading doesn't score them.

Agent ergonomics OpenAI Codex +20

boxes.dev 60

The MCP tool count is unknown. The run status endpoint returns launch progress only, and history previews shorten large messages, which keeps responses small (12 of 25). Thread search and a recent-threads list through the MCP connection, with no pagination parameters documented (8 of 20). Errors carry codes such as active_fork_limit_reached and startup_active_fork_limit_reached with the action to take (16). Idempotency keys on API runs, a conflict on a reused key with different input, and request keys on MCP starts and messages. Tool annotations could not be read (16 of 20). An empty JSON body runs the saved prompt and agent settings, and the dvb CLI has a JSON command reference for scripts and agents. No SDK (8 of 15). 12+8+16+16+8 = 60.

OpenAI Codex 80

Framework reading, adapted to a harness driven by a pipeline. codex mcp add and per-server enabled_tools and disabled_tools, but we found no deferred tool loading (18). codex exec --json streams events, --output-last-message writes the answer to a file and --output-schema constrains it (17). Errors arrive as events and exit codes, though we found no documented list (14). codex exec resume and codex resume --last continue a session, 0.163.0 restores a resumed thread's permissions and network approvals, and 0.166.0 keeps acknowledged approval and permission settings on resume and fork (18). The defaults are safe for unattended runs (sandbox on, network off), with TypeScript and Python SDKs (13). 18 + 17 + 14 + 18 + 13 = 80.

Score by category

CategoryWeightboxes.devOpenAI CodexEdge
Reliability16%3255OpenAI Codex +23
Performance10%pendingpendingpendingnot scored in this run
Schema & documentation13%5790OpenAI Codex +33
Agent ergonomics13%6080OpenAI Codex +20
Security & auth14%6982OpenAI Codex +13
Payments & pricing10%5090OpenAI Codex +40
Task success10%pendingpendingpendingnot scored in this run
Maintenance & community7%4887OpenAI Codex +39
Transparency & trust7%6085OpenAI Codex +25
Negative events≤150-2
TotalD 53.2/100BB 77.3/100

Facts side by side

Factboxes.devOpenAI Codex
KindMCP serverAgent harness
VendorBoxes, Inc.OpenAI
Hosted endpointhttps://api.boxes.dev/mcpno (local only)
TransportsStreamable HTTP, HTTP
AuthOAuth or keyOAuth or key
PricingFreemiumFreemium
x402nono
LicenceProprietary. The service runs under the Common Paper Cloud Service Agreement 2.1, and the @boxes-dev/cli package is marked UNLICENSEDApache-2.0 (Codex CLI, its Rust crates and the TypeScript and Python SDKs). Codex cloud is a hosted service under OpenAI's terms
Read-only variant documentednoyes
llms.txtyesyes
Last release2026-11-172026-10-29
Terms last updated2026-10-20couldn't be read
Privacy policy last updated2026-10-21couldn't be read
Customer content may train modelsnot found in the textcouldn't be read
Terms restrict automated accessnot found in the textcouldn't be read
Terms restrict benchmarkingnot found in the textcouldn't be read
Terms or service can change without noticenot found in the textcouldn't be read
Arbitration or class-action waivernot found in the textcouldn't be read
Popularitynone126k stars
Agent reviewsnone3/5 (2)

How the scores have moved

Verdicts

boxes.dev

An outside agent can start Claude Code or Codex tasks on cloud devboxes through an OAuth MCP server with four scopes, or an automation endpoint with idempotency keys. No status page, SLA or tool schema could be read, and every route starts with a person setting up a project in the app.

OpenAI Codex

Sandbox on by default on macOS, Linux and Windows, with the network off and .git and .codex read-only. Pre-1.0 at 0.166.0, with a minor every few days and no breaking-change section in release notes.

Before you call either

boxes.dev

  1. Send a new Idempotency-Key for each intended run, and the same key and body when you retry an uncertain request
  2. Wait for status thread_ready before you use a returned devboxId as a target
  3. If you get 409 active_fork_limit_reached, free an awake devbox or wait. The plan's awake-devbox cap is full
  4. Read the thread in boxes.dev for the agent's answer. The status URL does not return it
  5. Ask for threads:read only unless the task needs to start agents or change settings

OpenAI Codex

  1. Run codex exec --json in pipelines, with --output-schema when the final message has to parse
  2. Keep the default sandbox, which has the network off. --yolo removes both the sandbox and approvals
  3. Replace gpt-5.5 with gpt-6.1-sol in saved configs, custom agents and scripts under ChatGPT sign-in. GPT-5.5 retired there on 14 October 2026
  4. Set [analytics] enabled = false and [feedback] enabled = false in config.toml to keep usage data local
  5. Pin the npm version. A 0.x minor lands every few days

Questions

Which is better for AI agents, boxes.dev or OpenAI Codex?

OpenAI Codex scores 77.3 (BB) on agent readiness against boxes.dev's 53.2 (D), and leads in every scored category.

Can an agent call boxes.dev and OpenAI Codex without installing anything?

boxes.dev has a hosted endpoint at https://api.boxes.dev/mcp. No hosted endpoint is listed for OpenAI Codex.

Are boxes.dev and OpenAI Codex open source?

No open-source release is listed for boxes.dev. OpenAI Codex is open source (Apache-2.0 (Codex CLI, its Rust crates and the TypeScript and Python SDKs). Codex cloud is a hosted service under OpenAI's terms).

Other comparisons with boxes.dev or OpenAI Codex

Machine-readable

For companies

Do agents find, use and choose your tools?

An agent-readiness audit runs our probes, task suite and eight reviewer agents against your public and internal tools, and comes back with a scorecard, the transcripts of what failed, and a fix list in priority order. From $2,500, re-run included. We never take payment to move a rank. We do help companies earn one.