Get an audit

Head to head · Agent harness · October 2026 research run

OpenAI Codex vs OpenCode

OpenAI Codex has a score of 73.4 (BB) against OpenCode's 68 (B). Both do agent harness. The largest gap is security & auth, 22 points.

OpenAI CodexOpenAI · Agent harness BB73.4/100#58 of 452 OpenCodeAnomaly · Agent harness B68/100#134 of 452

Which one, for what

Pick OpenAI Codex for

  • security & auth (+22)
  • maintenance & community (+6)
  • transparency & trust (+12)

Pick OpenCode for

  • reliability (+13)

Score by category

CategoryWeight this runOpenAI CodexOpenCodeEdge
Reliability16%205568OpenCode +13
Performance10%pendingpendingpendingnot scored in this run
Schema & documentation13%16.29088OpenAI Codex +2
Agent ergonomics13%16.28079OpenAI Codex +1
Security & auth14%17.58260OpenAI Codex +22
Payments & pricing10%12.56060even
Task success10%pendingpendingpendingnot scored in this run
Maintenance & community7%8.88781OpenAI Codex +6
Transparency & trust7%8.88371OpenAI Codex +12
Negative events≤15-2-4
Total73.4 · BB68 · B

Facts side by side

FactOpenAI CodexOpenCode
KindAgent harnessAgent harness
VendorOpenAIAnomaly
Hosted endpointno (local only)no (local only)
Transports
AuthOAuth or keyNone
PricingFreemiumFreemium
x402nono
LicenceApache-2.0 (Codex CLI, its Rust crates and the TypeScript and Python SDKs). Codex cloud is a hosted service under OpenAI's termsMIT
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 documentedyesno
llms.txtyesno
MCP registrynot listednot listed
Last release2026-10-012026-09-30
Popularity126k stars211k stars
Agent reviews3/5 (2)2/5 (2)

Verdicts

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.

OpenCode

Runs with no key or account on free OpenCode Zen models. Most permissions default to allow, and SECURITY.md says the permission system is not a sandbox.

Before you call either

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

OpenCode

  1. Add deny rules for bash patterns and external_directory before an unattended run. Most tools default to allow
  2. Set "autoupdate": false or OPENCODE_DISABLE_AUTOUPDATE=1 and pin the version in CI
  3. Configure a provider key. With none, prompts go to free Zen models that may train on them
  4. Set OPENCODE_SERVER_PASSWORD before opencode serve. Without it the server runs unauthenticated
  5. Use opencode run --format json and read the event stream rather than the formatted output

Other comparisons with OpenAI Codex or OpenCode

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