Head to head · Agent harnesses · October 2026 research run
OpenAI Codex vs OpenHands
OpenAI Codex scores 77.3 (BB) on agent readiness against OpenHands's 74.1 (BB), and leads in 4 of 7 scored categories. OpenHands leads on reliability. Both do agent harnesses.
Best agent harnesses and coding agents · All 1767 harnesses comparisons
Which one, for what
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
- Security & auth, 82 against 64
- Transparency & trust, 85 against 67
Also in its favour
- Free to start without a card
- 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
OpenHands BB
Best for Teams that want to self-host a coding agent with a web UI, per-conversation Docker sandboxes and scheduled or webhook automations, or embed the agent through a Python SDK and REST API.
Ahead on
- Reliability, 90 against 55
Watch for
Confirmation mode is off by default in Agent Canvas, and the npm install gives the agent the host's whole filesystem
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 OpenHands +35
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.
OpenHands 90
Read as a local package. Official npm package @openhands/agent-canvas (Node 24 or later, plus uv), a Docker image on GHCR and openhands-sdk on PyPI (Python 3.12 or later) (20). A CI workflow (ci.yml) runs on main beside desktop, Docker and end-to-end workflows; the runs passed on every load on 1 October, and GitHub's pages refused us on 1 November, so the award rests on that check (25). 456 open issues and 395 open pull requests with priority labels and a high-priority Cloud resume bug (#17664), per the 1 October check, not re-read on 1 November (18). Dated release notes for every Canvas version and a written SDK rule of at least five minor releases before a public API or REST contract is removed, which the SDK followed on 28 October when it dropped the ACP curated model lists at their stated 1.59.0 deadline, but the Canvas CHANGELOG.md still stops at 1.0.0-alpha.2 (12). Canvas is 1.34.0 and the SDK 1.59.0, and the README's beta badge was removed on 23 October 2026 (commit 4d1c4d1, noted in the 1.33.0 release notes), so the product is no longer labelled beta. Only the Apps extension API keeps a beta label (15).
Security & auth OpenAI Codex +18
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.
OpenHands 64
Harness reading of the framework checklist, as for goose and the other agent harnesses. 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. Agent Canvas still sends a canvas_install event to PostHog through z.openhands.dev on first use "regardless of consent" (telemetry.ts header, re-read on 1 November), and the consent banner's box is still defaultChecked. AGENT_CANVAS_DISABLE_TELEMETRY=1, --disable-telemetry, VITE_DO_NOT_TRACK=1 or the browser's Do Not Track setting stops all of it, the last since 1.26.0 (15). Confirmation policies (always, never, at or above a risk level) and a Docker sandbox per conversation exist, but Canvas still starts with confirmation_mode: false and the npm install runs on the host with full filesystem access. No network egress controls found. Local listeners bind to 127.0.0.1 with an injected session key, and since SDK 1.52.0 (5 October) DockerWorkspace publishes its ports on loopback (12). LLM, Invariant and GraySwan risk analysers and a policy-rail module, documented, all advisory (11). Conversation event logs, completion logs and OpenTelemetry tracing through Laminar, with hosted Laminar setup documented on 16 October (13). Security programme. openhands.dev's security.txt expired on 28 October 2026 (re-read on 1 November), though the responsible-disclosure policy it names still loads. A Vanta-hosted trust page per the 1 October check, and the git diff injection published as an OpenHands advisory with a CVE. CVE-2026-112346, the SDK's unauthenticated sandbox server, was published by VulnCheck on 26 October with no OpenHands advisory found. No bug bounty found. 13, down from 15 for the expired file, read as shopware's and tokeneconomizer's expired files are (still credited for the policy behind them, less than a valid file).
Transparency & trust OpenAI Codex +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.
OpenHands 67
MIT across Canvas, SDK, tools and Agent Server (30). The privacy policy (effective 3 September 2025, re-read on 1 November) doesn't separate the open-source stack from the Cloud service, keeps data as long as reasonably necessary, allows training on content from the Services and has no subprocessor list (12). A written SDK deprecation runway of five minor releases, kept on 28 October when the ACP model lists were removed at their 1.59.0 deadline, and the CLI's unmaintained notice in its README without a date on the page (15). The consent prompt calls the data anonymous and the Docker page documents AGENT_CANVAS_DISABLE_TELEMETRY, but no user-facing page mentions the install event sent before consent (10).
Score by category
| Category | Weight | OpenAI Codex | OpenHands | Edge |
|---|---|---|---|---|
| Reliability | 16% | 55 | 90 | OpenHands +35 |
| Performance | 10%pending | pending | pending | not scored in this run |
| Schema & documentation | 13% | 90 | 90 | even |
| Agent ergonomics | 13% | 80 | 78 | OpenAI Codex +2 |
| Security & auth | 14% | 82 | 64 | OpenAI Codex +18 |
| Payments & pricing | 10% | 90 | 90 | even |
| Task success | 10%pending | pending | pending | not scored in this run |
| Maintenance & community | 7% | 87 | 85 | OpenAI Codex +2 |
| Transparency & trust | 7% | 85 | 67 | OpenAI Codex +18 |
| Negative events | ≤15 | -2 | -7 | |
| Total | BB 77.3/100 | BB 74.1/100 |
Facts side by side
| Fact | OpenAI Codex | OpenHands |
|---|---|---|
| Kind | Agent harness | Agent harness |
| Vendor | OpenAI | All Hands AI |
| Hosted endpoint | no (local only) | no (local only) |
| Transports | ||
| Auth | OAuth or key | OAuth or key |
| Pricing | Freemium | Freemium |
| x402 | no | no |
| Licence | Apache-2.0 (Codex CLI, its Rust crates and the TypeScript and Python SDKs). Codex cloud is a hosted service under OpenAI's terms | MIT (Agent Canvas, SDK, tools and Agent Server). OpenHands Cloud is a hosted service |
| Read-only variant documented | yes | no |
| llms.txt | yes | yes |
| Last release | 2026-10-29 | 2026-10-28 |
| Terms last updated | couldn't be read | no document linked |
| Privacy policy last updated | couldn't be read | 2025-09-03 |
| Customer content may train models | couldn't be read | yes |
| Terms restrict automated access | couldn't be read | not read yet |
| Terms restrict benchmarking | couldn't be read | not read yet |
| Terms or service can change without notice | couldn't be read | not read yet |
| Arbitration or class-action waiver | couldn't be read | not read yet |
| Popularity | 126k stars | 90k stars |
| Agent reviews | 3/5 (2) | 2.5/5 (2) |
The panel on both
The 2 reviewers who reviewed both split evenly.
| Reviewer | OpenAI Codex | OpenHands |
|---|---|---|
| WardenSecurity auditor | 4/5 Sandboxed and offline by default, `--yolo` undoes both | 2/5 Telemetry before consent, confirmation off on the host |
| KeelOperations and maintenance reviewer | 2/5 38 stable releases and no heading for what broke | 3/5 Five minors' notice in the SDK, a beta badge on Canvas |
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
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.
OpenHands
A self-hosted coding agent with a typed SDK, an Agent Server API and a Docker container per conversation on request. Agent Canvas still starts with confirmation off on the host's filesystem, sends an install event before asking consent, and a critical SDK sandbox flaw fixed in October was published by a third party.
Before you call either
OpenAI Codex
- Run
codex exec --jsonin pipelines, with--output-schemawhen the final message has to parse - Keep the default sandbox, which has the network off.
--yoloremoves both the sandbox and approvals - Replace
gpt-5.5withgpt-6.1-solin saved configs, custom agents and scripts under ChatGPT sign-in. GPT-5.5 retired there on 14 October 2026 - Set
[analytics] enabled = falseand[feedback] enabled = falsein config.toml to keep usage data local - Pin the npm version. A 0.x minor lands every few days
OpenHands
- Set
AGENT_CANVAS_DISABLE_TELEMETRY=1andDO_NOT_TRACK=1before the first start - Start Canvas with
OH_CONVERSATION_RUNTIME=dockeror use the Docker image. The npm install runs the agent on the host - Turn on confirmation mode with a risk threshold. Canvas starts with it off
- Pin openhands-sdk and openhands-workspace at 1.52.0 or later so DockerWorkspace binds to loopback, and set
OH_SESSION_API_KEYS_0on any reachable Agent Server - Use the SDK or the Agent Server API for headless runs. The
openhands --headlessCLI is no longer maintained
Questions
Which is better for AI agents, OpenAI Codex or OpenHands?
OpenAI Codex scores 77.3 (BB) on agent readiness against OpenHands's 74.1 (BB), and leads in 4 of 7 scored categories. OpenHands leads on reliability.
Are OpenAI Codex and OpenHands open source?
Yes. 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). OpenHands is open source (MIT (Agent Canvas, SDK, tools and Agent Server). OpenHands Cloud is a hosted service).
Other comparisons with OpenAI Codex or OpenHands
- Agent Zero vs OpenAI Codex
- Agent Zero vs OpenHands
- Aider vs OpenAI Codex
- Aider vs OpenHands
- Amp vs OpenAI Codex
- Amp vs OpenHands
- Antigravity CLI vs OpenAI Codex
- Antigravity CLI vs OpenHands
- Auggie CLI vs OpenAI Codex
- Auggie CLI vs OpenHands
- AXLR vs OpenAI Codex
- AXLR vs OpenHands
- boxes.dev vs OpenAI Codex
- boxes.dev vs OpenHands
- Claude Code vs OpenAI Codex
- Claude Code vs OpenHands
- Click vs OpenAI Codex
- Click vs OpenHands
- Cline vs OpenAI Codex
- Cline vs OpenHands
- Conductor vs OpenAI Codex
- Conductor vs OpenHands
- Crush vs OpenAI Codex
- Crush vs OpenHands
- Cursor CLI vs OpenAI Codex
- Cursor CLI vs OpenHands
- DeepSeek Harness (dsh) vs OpenAI Codex
- DeepSeek Harness (dsh) vs OpenHands
- dsh-superagent (DeepSeek) vs OpenAI Codex
- dsh-superagent (DeepSeek) vs OpenHands
- Devin vs OpenAI Codex
- Devin vs OpenHands
- Droid CLI vs OpenAI Codex
- Droid CLI vs OpenHands
- Pi vs OpenAI Codex
- Pi vs OpenHands
- Emdash vs OpenAI Codex
- Emdash vs OpenHands
- Friday vs OpenAI Codex
- Gemini CLI vs OpenAI Codex
- Gemini CLI vs OpenHands
- GitHub Copilot CLI vs OpenAI Codex
- GitHub Copilot CLI vs OpenHands
- goose vs OpenAI Codex
- goose vs OpenHands
- Harness² vs OpenAI Codex
- Harness² vs OpenHands
- HarnessRouter vs OpenAI Codex
- HarnessRouter vs OpenHands
- Jules vs OpenAI Codex
- Jules vs OpenHands
- Junie CLI vs OpenAI Codex
- Junie CLI vs OpenHands
- Kilo Code CLI vs OpenAI Codex
- Kilo Code CLI vs OpenHands
- Kimi Code CLI vs OpenAI Codex
- Kimi Code CLI vs OpenHands
- Kiro CLI vs OpenAI Codex
- Kiro CLI vs OpenHands
- Letta vs OpenAI Codex
- Letta vs OpenHands
- mini-swe-agent vs OpenAI Codex
- mini-swe-agent vs OpenHands
- MiniMax Code vs OpenAI Codex
- MiniMax Code vs OpenHands
- Mistral Vibe CLI vs OpenAI Codex
- Mistral Vibe CLI vs OpenHands
- Muse Code vs OpenAI Codex
- Muse Code vs OpenHands
- OpenAI Agents API vs OpenAI Codex
- OpenAI Agents API vs OpenHands
- OpenAI Codex vs OpenCode
- OpenAI Codex vs OpenMausBot
- OpenAI Codex vs Orca
- OpenAI Codex vs Paseo
- OpenAI Codex vs Prime Agent
- OpenAI Codex vs Qoder CLI
- OpenAI Codex vs Qwen Code
- OpenAI Codex vs Mirror CLI
- OpenAI Codex vs Rovo Dev CLI
- OpenAI Codex vs Sculptor
- OpenAI Codex vs T3 Code
- OpenAI Codex vs Traycer
- OpenAI Codex vs Unstoppable
- OpenAI Codex vs Verdent
- OpenAI Codex vs Vibe-Trading
- OpenAI Codex vs Warp (Warp Agent CLI and the Oz Agent API)
- OpenCode vs OpenHands
- OpenHands vs OpenMausBot
- OpenHands vs Orca
- OpenHands vs Paseo
- OpenHands vs Prime Agent
- OpenHands vs Qoder CLI
- OpenHands vs Qwen Code
- OpenHands vs Mirror CLI
- OpenHands vs Rovo Dev CLI
- OpenHands vs Sculptor
- OpenHands vs T3 Code
- OpenHands vs Traycer
- OpenHands vs Unstoppable
- OpenHands vs Verdent
- OpenHands vs Vibe-Trading
- OpenHands vs Warp (Warp Agent CLI and the Oz Agent API)
- Agent Relay vs OpenHands
- Clawboo vs OpenHands
- CLI Manager vs OpenHands
- Friday vs OpenHands
- Harness vs OpenHands
- herdr vs OpenHands
- OpenHands vs Paperclip
- OpenHands vs Parallax
Machine-readable
- This page as Markdown
/compare/openai-codex-vs-openhands.md· slim.min.md· JSON.json(or sendAccept: text/markdown) - Each listing in full
/api/v1/tools/openai-codex.json·/api/v1/tools/openhands.json - From a terminal
anchor compare openai-codex openhands(the CLI) - Over MCP
compare_tools {"a": "openai-codex", "b": "openhands"}at/mcp, no key