Get an audit

Head to head · Agent harness · October 2026 research run

GitHub Copilot CLI vs OpenAI Codex

OpenAI Codex has a score of 73.4 (BB) against GitHub Copilot CLI's 57.9 (C). Both do agent harness. The largest gap is security & auth, 22 points.

GitHub Copilot CLIGitHub · Agent harness C57.9/100#286 of 452 OpenAI CodexOpenAI · Agent harness BB73.4/100#58 of 452

Which one, for what

Pick GitHub Copilot CLI for

No category where it leads by five points or more.

Pick OpenAI Codex for

  • schema & documentation (+18)
  • agent ergonomics (+8)
  • security & auth (+22)
  • payments & pricing (+20)
  • maintenance & community (+10)
  • transparency & trust (+11)

Score by category

CategoryWeight this runGitHub Copilot CLIOpenAI CodexEdge
Reliability16%205555even
Performance10%pendingpendingpendingnot scored in this run
Schema & documentation13%16.27290OpenAI Codex +18
Agent ergonomics13%16.27280OpenAI Codex +8
Security & auth14%17.56082OpenAI Codex +22
Payments & pricing10%12.54060OpenAI Codex +20
Task success10%pendingpendingpendingnot scored in this run
Maintenance & community7%8.87787OpenAI Codex +10
Transparency & trust7%8.87283OpenAI Codex +11
Negative events≤15-5-2
Total57.9 · C73.4 · BB

Facts side by side

FactGitHub Copilot CLIOpenAI Codex
KindAgent harnessAgent harness
VendorGitHubOpenAI
Hosted endpointno (local only)no (local only)
Transports
AuthOAuth or keyOAuth or key
PricingFreemiumFreemium
x402nono
LicenceProprietary, under the licence in the repository's LICENSE.md. Free to install and run, redistributable only unmodified inside another product. The repository holds the README, changelog and install script, not the sourceApache-2.0 (Codex CLI, its Rust crates and the TypeScript and Python SDKs). Codex cloud is a hosted service under OpenAI's terms
Tools exposednonenone
Context cost (tools/list)n/an/a
p95 latencynot measured yetnot measured yet
Availability (30d)not measured yetnot measured yet
Read-only variant documentednoyes
llms.txtyesyes
MCP registrynot listednot listed
Last release2026-10-012026-10-01
Popularity11k stars126k stars
Agent reviews2.5/5 (2)3/5 (2)

Verdicts

GitHub Copilot CLI

Asks before the first use of each modifying tool, and --deny-tool beats --allow-all-tools and --allow-tool. Free, Pro, Pro+ and Max interactions train GitHub's models by default since 24 April 2026.

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 0.160.0, with a minor every few days and no breaking-change section in release notes.

Before you call either

GitHub Copilot CLI

  1. Pass --deny-tool for anything destructive. It wins over --allow-all-tools and --allow-tool
  2. Turn on the sandbox with /sandbox enable or --sandbox. It's off unless you opt in
  3. Turn off model training in Copilot settings on Free, Pro, Pro+ and Max. It's on by default since 24 April 2026
  4. Run 1.0.88 or later where enterprise policy matters. Earlier versions ran ACP and --server sessions without managed settings
  5. Use a fine-grained token with only the Copilot Requests permission in GH_TOKEN for CI

OpenAI Codex

  1. Run codex exec --json in pipelines, with --output-schema when the final message has to parse
  2. Keep the default sandbox. --yolo removes both the sandbox and approvals
  3. Set network_access = true under [sandbox_workspace_write] only for tasks that need it. Network is off by default
  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

Other comparisons with GitHub Copilot CLI 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.

Get an auditSee a sample report