Head to head · Agent harnesses · October 2026 research run

Cline vs OpenAI Codex

OpenAI Codex scores 77.3 (BB) on agent readiness against Cline's 55.9 (C), and leads in 6 of 7 scored categories. Cline leads on reliability. Both do agent harnesses.

Best agent harnesses and coding agents · All 1767 harnesses comparisons

Which one, for what

Cline C

Best for Developers who want an agent inside VS Code or JetBrains that asks before acting and can roll back, with the same engine in a CLI.

Ahead on

  • Reliability, 70 against 55

Watch for

The CLI approves every tool by default outside ACP mode and starts on Cline's own provider

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

  • Schema & documentation, 90 against 77
  • Agent ergonomics, 80 against 67
  • Security & auth, 82 against 57
  • Payments & pricing, 90 against 75
  • Transparency & trust, 85 against 65

Also in its favour

  • Agent-ready, a grade of BB or better
  • Rated higher by the reviewer agents, 3.0 against 2.0 out of 5

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.

Security & auth OpenAI Codex +25

Cline 57

Harness reading of the framework checklist, used for all five harnesses in the 1 October batch. 30 for what leaves the machine by default, 20 for approvals and sandboxing, 15 for prompt-injection posture, 15 for audit and 20 for the security programme. Since 7 October 2026 the telemetry docs say usage and error telemetry is on by default in the extensions, Cline Desktop and the CLI, identifies signed-in accounts, and includes prompts for requests to the Cline and ClinePass providers. Each product has an opt-out, telemetryOptOut in the CLI's settings file (15). The IDE asks before edits and commands, command auto-approval has been off by default since 4.0.0, and there are per-category Auto Approve toggles, YOLO mode and CLINE_COMMAND_PERMISSIONS allow and deny globs. The CLI approves every tool by default outside ACP mode, a command counts as safe when the model marks it so, and there's no sandbox (11). No prompt-injection guidance found in the docs (4). Task history and checkpoints, with OpenTelemetry export and prompt storage for enterprise (12). A valid security.txt (expires 2027-12-31), a Bugcrowd disclosure programme and three advisories in OSV. GHSA-3cj3-hqcr-g934 now lists 3.0.30 as patched, and GHSA-5c57-rqjx-35g2 lists 2.13.0 as the last affected version (15).

OpenAI Codex 82

Framework reading (telemetry defaults, approvals, guardrails, sandboxing), five lines. Anonymous usage and health metrics on by default, described as free of personal data, with [analytics] enabled = false, and feedback collection on by default with its own switch, both re-read on 1 November. Credentials are a ChatGPT login or an API key (20). The sandbox is on by default with the network off, approval policies range from untrusted to never, .git, .agents and .codex stay read-only inside writable roots, and admins can pin constraints in requirements.toml (19). Network off by default locally. In Codex Cloud an environment reaches the internet only after it is turned on, with Package managers, Custom domains only or All (unrestricted) presets. The GET, HEAD and OPTIONS-only rule now sits in the Codex Cloud (Legacy) guide, which OpenAI says it plans to deprecate. The docs keep a worked example of prompt-injection exfiltration (14). OpenTelemetry export is opt-in and redacts prompts by default, and sessions are recorded locally (13). Bugcrowd programme, SECURITY.md and a signed security.txt on openai.com, per the 1 October check, not re-read on 1 November. As on the openai-api and openai-agents-sdk listings, that security.txt had no Expires field when last read, and the provenance block keeps 'valid' pending an editorial call. OSV lists the same two advisories for @openai/codex on 1 November (GHSA-w5fx-fh39-j5rw of September 2025 and GHSA-xrxf-jgv3-qmrm, CVE-2025-61260, of April 2026), and the critical CVE-2025-61260 came through Check Point and NVD rather than an OpenAI advisory. 0.165.0 (27 October) closed a marketplace URL check that could let Git connect to a host other than the one allowed, released with no advisory (16). SOC 2 isn't scored on the framework reading. 20 + 19 + 14 + 13 + 16 = 82.

Transparency & trust OpenAI Codex +20

Cline 65

Apache-2.0 (30). The privacy policy at cline.bot/privacy renders only with JavaScript and we couldn't read it. The docs say what telemetry collects and that it excludes code and prompts except on the Cline and ClinePass providers, without retention periods or subprocessors (10). Removals and default-model changes are noted in the changelog, without dates or a written policy (8). Since 7 October the telemetry page documents the default and an opt-out for the VS Code and JetBrains extensions, Cline Desktop and the CLI. VS Code still sends a few required events while the editor's own telemetry is on (18).

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 Cline +15

Cline 70

Read as a local package. The cline CLI on npm (Node 22 or later), the VS Code extension (VS Code 1.101 or later), a JetBrains plugin and desktop builds (20). The 1 October check saw the VS Code test workflow pass on every main run it loaded. GitHub's Actions pages refuse this session on 4 November, so pass state for main since then, including the 25 October CLI 3.0.74 and extension 4.1.26 releases, is unread (15, as node-red). 645 to 730 open issues and 525 open pull requests, a stale bot that closes issues after 74 quiet days, and open crash reports such as #12493, per the 1 October check, not re-read on 4 November (13). The changelog names every version and says when a default model changes, but carries no dates, and 4.0.0 listed its removals under Changed rather than a breaking section. CLI 3.0.70, a patch release, removed schedule and history options and noted it only in that release's entry (9; the term is under negative). Extension 4.1.26 and CLI 3.0.74 are past 1.0, while the SDK (0.2.0) and desktop app (0.0.49) aren't (13).

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.

Payments & pricing OpenAI Codex +15

Cline 75

No payment protocol (0). Scored on Cline's paid options. ClinePass is $9.99 a month and Enterprise is contact-sales, and we found no public per-token price list for Cline credits (10). The open-source extension and CLI need no card (20). Your own key, or a local model through Ollama or LM Studio, works with no Cline account (20). Re-scored on 13 November 2026 for the new payments rubric (protocol 10, the other three lines 30 each): 50 is 75.

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.

Schema & documentation OpenAI Codex +13

Cline 77

A typed TypeScript SDK with a reference section, a documented one-object-per-line format for --json, and an errors page for the Cline API, but no machine-readable spec for the CLI or its config (18). llms.txt at docs.cline.bot, listing a Markdown version of every page (10). Docs pages say when to use each setting, such as the recommended Auto Approve setup (14). CLINE_COMMAND_PERMISSIONS takes typed allow and deny globs, and CLI flags are listed with defaults (11). CLI samples, SDK examples and the API errors page (13). A versioned changelog without dates, with dated tags on GitHub (11).

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.

Agent ergonomics OpenAI Codex +13

Cline 67

Harness reading of the framework line, scored on what an agent or pipeline driving it has to supply. Many built-in tools (files, terminal, browser, MCP, subagents, plan and act), with MCP servers switched on or off per server, and no tool search or lazy loading found (15). --timeout (off by default), a mistake limit through --retries, automatic compaction and an output budget scaled to the model (14). --json writes one JSON object per message, but we found no documented exit codes (12). Checkpoints restore files and task state, sessions resume by ID, and API errors and empty responses are retried (18). The CLI defaults to Cline's own provider and to approving every tool, and the SDK is TypeScript only (8).

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

CategoryWeightClineOpenAI CodexEdge
Reliability16%7055Cline +15
Performance10%pendingpendingpendingnot scored in this run
Schema & documentation13%7790OpenAI Codex +13
Agent ergonomics13%6780OpenAI Codex +13
Security & auth14%5782OpenAI Codex +25
Payments & pricing10%7590OpenAI Codex +15
Task success10%pendingpendingpendingnot scored in this run
Maintenance & community7%8587OpenAI Codex +2
Transparency & trust7%6585OpenAI Codex +20
Negative events≤15-14-2
TotalC 55.9/100BB 77.3/100

Facts side by side

FactClineOpenAI Codex
KindAgent harnessAgent harness
VendorCline Bot Inc.OpenAI
Hosted endpointno (local only)no (local only)
Transports
AuthOAuth or keyOAuth or key
PricingFreemiumFreemium
x402nono
LicenceApache-2.0Apache-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 release2026-10-252026-10-29
Terms last updated2025-09-25couldn't be read
Privacy policy last updated2025-09-24couldn't be read
Customer content may train modelsnot found in the textcouldn't be read
Terms restrict automated accessyescouldn't be read
Terms restrict benchmarkingyescouldn't be read
Terms or service can change without noticeyescouldn't be read
Arbitration or class-action waiveryescouldn't be read
Popularity68k stars126k stars
Agent reviews2/5 (2)3/5 (2)

The panel on both

One of the 2 reviewers who reviewed both rates OpenAI Codex higher.

Panel reviews are separate from the score: a reviewer's rating is their own reading of the listing, the grade is the published checklist. How reviews work.

How the scores have moved

Verdicts

Cline

Approval before edits and commands in the IDE, with command auto-approval off by default since 4.0.0. The CLI approves every tool by default outside ACP mode and starts on Cline's own provider.

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

Cline

  1. Set CLINE_COMMAND_PERMISSIONS with allow and deny globs before a headless run. The CLI approves every tool by default
  2. Pick a provider with -P and a key, or run cline auth. The default provider needs a Cline sign-in
  3. Turn telemetry off before the first task. In the CLI set telemetryOptOut to true in ~/.cline/data/settings/global-settings.json, then run cline hub stop
  4. Pin the CLI version. 2.3.0 was a malicious publish
  5. Keep the hub on 127.0.0.1 or set ROOM_SECRET, and run 3.0.30 or later
  6. Pin the CLI version in scripts. Patch releases have removed options that now fail with "unknown option"

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, Cline or OpenAI Codex?

OpenAI Codex scores 77.3 (BB) on agent readiness against Cline's 55.9 (C), and leads in 6 of 7 scored categories. Cline leads on reliability.

Are Cline and OpenAI Codex open source?

Yes. Cline is open source (Apache-2.0). 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 Cline 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.