Head to head · Agent harnesses · October 2026 research run

goose vs OpenAI Codex

OpenAI Codex scores 77.3 (BB) on agent readiness against goose's 75 (BB), and leads in 4 of 7 scored categories. goose leads on reliability. Both do agent harnesses.

Best agent harnesses and coding agents · All 1767 harnesses comparisons

Which one, for what

goose BB

Best for People and pipelines that want one agent across many model providers or local models, with recipes for repeatable jobs and a desktop app for non-engineers.

Ahead on

  • Reliability, 77 against 55

Also in its favour

  • No key needed to call it

Watch for

Autonomous mode, which approves every tool call, is the default

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 81
  • Security & auth, 82 against 77
  • Transparency & trust, 85 against 67

Also in its favour

  • Rated higher by the reviewer agents, 3.0 against 2.5 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.

Reliability goose +22

goose 77

Read as a local package, which is how the 1 October dossier read it. Desktop builds and a CLI for macOS, Linux and Windows (a Windows NSIS installer from 1.56.0), Homebrew casks, a download script on GitHub releases, an npm package that installs the binary (@aaif/goose-acp) and a GHCR image, with Rust 1.94.1 as the minimum for source builds (20). A CI workflow runs on every push to main, with cargo-deny, cargo-machete, MCP and tool-call conformance and an OpenSSF Scorecard job beside it. The Actions page loaded on 1 October showed only passing runs from March 2026, and GitHub pages refused our requests on 6 and 17 October and 1 November, so the current state is unconfirmed (18). 266 to 271 open issues on 1 October, many from that week with no reply, including open reports that the default mode approves every tool call (#12567) and that schedules can overwrite each other (#12613), per the 1 October check, not re-read since (15). Weekly minor releases with notes written by a release-notes workflow whose sections are Features, Bug Fixes, Improvements and Documentation, with no breaking-change section. 1.55.0 dropped background subagents (delegate(..., async: true) and GOOSE_MAX_BACKGROUND_TASKS) and 1.57.0 dropped the developer tools that delegated file reads and terminal commands to an ACP editor, each edited out of the code and docs with no earlier notice (9). 1.57, stable (15).

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.

Transparency & trust OpenAI Codex +18

goose 67

Apache-2.0 (30). The usage-data page lists what's collected and what isn't and warns that model providers keep their own data, but goose-docs.ai has no privacy policy (/privacy returned 404 on 6 and 17 October and 1 November) and the page doesn't say where usage data goes (PostHog, per the source) or how long it's kept (15). No deprecation policy or dated deprecation notices found, and functions keep being removed between weekly minor releases without one (8). Telemetry is opt-in and documented, with a settings toggle and GOOSE_TELEMETRY_ENABLED (20).

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.

Schema & documentation OpenAI Codex +9

goose 81

Recipes have a documented schema with typed parameters and a response JSON Schema for structured output, and config and environment variables are documented in tables, but we found no OpenAPI spec for the goose server (18). llms.txt at goose-docs.ai, which now covers goose and the goose Development Kit (10). Permission modes come with a best-for column and the security pages say what each guard catches and misses (15). Recipe parameters take types and requirement levels, and retries take typed success checks (12). Many tutorials, a headless guide that tells scripts to check exit codes, and a known-issues page (13). Dated, written notes on every GitHub release, with no changelog file (13).

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.

Security & auth OpenAI Codex +5

goose 77

Harness reading of the framework checklist, used for all five harnesses in this 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. Usage data is off until the user agrees on first use, and the docs list what's collected and what isn't (30). Four modes (autonomous, smart approval, manual approval, chat only), per-tool always, ask or never rules, and an extension allowlist fetched from GOOSE_ALLOWLIST, which from 1.57.0 must be HTTPS and blocks installs when the policy can't be read, but autonomous is the default (the first-run prompt for the mode still preselects Auto in 1.57.0) and there's no sandbox, with the docs pointing to a VM or container (11). Pattern and optional ML prompt-injection detection and an adversary reviewer for shell calls, both off until turned on, plus a prompt-injection caution in SECURITY.md (11). Session logs, a diagnostics report and a Langfuse tracing guide (12). SECURITY.md with GitHub private reporting and an AAIF governance contact, one advisory published with a CVE, and a Scorecard workflow. A second CVE, CVE-2026-109561 (low, Manual Approval bypassed by persisted read-only annotations after Smart Approval, fixed in 1.44.0), was published by NVD on 12 October from a third party, with no goose advisory of its own. No bug bounty, and goose-docs.ai/.well-known/security.txt returned 404 on 6 and 17 October and 1 November (13).

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.

Score by category

CategoryWeightgooseOpenAI CodexEdge
Reliability16%7755goose +22
Performance10%pendingpendingpendingnot scored in this run
Schema & documentation13%8190OpenAI Codex +9
Agent ergonomics13%8280goose +2
Security & auth14%7782OpenAI Codex +5
Payments & pricing10%9090even
Task success10%pendingpendingpendingnot scored in this run
Maintenance & community7%8687OpenAI Codex +1
Transparency & trust7%6785OpenAI Codex +18
Negative events≤15-5-2
TotalBB 75/100BB 77.3/100

Facts side by side

FactgooseOpenAI Codex
KindAgent harnessAgent harness
VendorAgentic AI Foundation (originally Block)OpenAI
Hosted endpointno (local only)no (local only)
Transports
AuthNoneOAuth or key
PricingFreeFreemium
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 release2026-10-272026-10-29
Terms last updatedno document linkedcouldn't be read
Privacy policy last updatedno document linkedcouldn't be read
Customer content may train modelsnot read yetcouldn't be read
Terms restrict automated accessnot read yetcouldn't be read
Terms restrict benchmarkingnot read yetcouldn't be read
Terms or service can change without noticenot read yetcouldn't be read
Arbitration or class-action waivernot read yetcouldn't be read
Popularity55k stars126k stars
Agent reviews2.5/5 (2)3/5 (2)

The panel on both

The 2 reviewers who reviewed both split evenly.

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

goose

Telemetry off until the user opts in, with the collected fields listed. Autonomous mode, which approves every tool call, is the default.

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

goose

  1. Set GOOSE_MODE=smart_approve or approve before a run. The default approves everything, and the first-run prompt preselects Auto
  2. Pass --max-turns with a real limit. The default is 1000
  3. Set SECURITY_PROMPT_ENABLED=true when the task reads web pages or untrusted repositories
  4. Use --output-format json and --no-session in CI, and check the exit code
  5. Pin the goose version in CI. Minor releases have removed functions, such as delegate(..., async: true) in 1.55.0, without notice

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, goose or OpenAI Codex?

OpenAI Codex scores 77.3 (BB) on agent readiness against goose's 75 (BB), and leads in 4 of 7 scored categories. goose leads on reliability.

Are goose and OpenAI Codex open source?

Yes. goose 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 goose 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.