Head to head · Agent harnesses · October 2026 research run
Amp vs OpenAI Codex
OpenAI Codex scores 77.3 (BB) on agent readiness against Amp's 57.8 (C), and leads in every scored category. Both do agent harnesses.
Best agent harnesses and coding agents · All 1767 harnesses comparisons
Which one, for what
Amp C
Best for Teams that want a hosted, multi-model coding agent with shared threads and cloud machines, driven from scripts through execute mode or the SDKs.
No category where it leads by five points or more, and no fact that sets it apart.
Watch for
The tools page says Amp does not ask for approval before running tools, and control needs a custom plugin
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
- Reliability, 55 against 23
- Schema & documentation, 90 against 72
- Agent ergonomics, 80 against 69
- Security & auth, 82 against 57
- Payments & pricing, 90 against 53
- Maintenance & community, 87 against 79
- Transparency & trust, 85 against 77
Also in its favour
- Agent-ready, a grade of BB or better
- Free to start without a card
- Open source
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.
Payments & pricing OpenAI Codex +37
Amp 53
Harness reading of the published rubric. No payment protocol (0). The pricing page is public. Hobby is free, Megawatt is $20 a month with 45,000 orb minutes, orbs are priced per hour by size from $0.08, and paid credits are charged at provider API prices with no markup outside Enterprise. Gigawatt is $200 a month with $200 of agent usage and 1,000 hours of a1.xxlarge orbs, per the pricing docs (20). Hobby is free when you bring your own model key or subscription and run locally or on your own runner. The pricing page does not say whether sign-up asks for a card, and inference served by Amp is never free (15). A person signs in through a browser to create the access token (0). Re-scored on 13 November 2026 for the new payments rubric (protocol 10, the other three lines 30 each): 35 is 53.
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.
Reliability OpenAI Codex +32
Amp 23
Local-package reading, as for the other closed-source harnesses. An install script that verifies a SHA-256 checksum, and an @ampcode/cli npm package of prebuilt binaries, for macOS, Linux and Windows through WSL, per the 8 October check (20). The source repository is private, so there is no public CI or test suite (0). There is no public issue tracker, and bug reports go to the vendor from inside the product. The 8 October reading of the status page's incident feed is struck, because ampcodestatus.com's robots.txt now disallows ClaudeBot, Claude-Web and anthropic-ai, so nothing is left to count crash or regression reports against (0). Versions are build stamps such as 0.0.1792627309-g98c009 with no per-version notes, and the introduction says "No backward compatibility", though removals are announced with dates in the Chronicle (3). The version line is 0.0 and we found no statement that the CLI is stable (0).
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.
Security & auth OpenAI Codex +25
Amp 57
Harness reading of the framework checklist, as for the other 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. Every thread, with messages, code used as context and tool results, is stored on Amp's servers, and there is no local-only or self-hosted mode. Training on user data is off unless a user opts in, provider retention is limited under Minimal Data Retention, and secrets are redacted before they leave the client on a best-effort basis. The terms allow collection of usage data and we found no opt-out for the CLI (14). The tools page says Amp does not ask for approval before running tools, and points to a custom plugin for control. MCP servers defined in a project's settings need approval, amp.mcpPermissions allows or rejects servers and amp.tools.disable removes tools. The CLI has no sandbox. Orbs are separate cloud machines (6). The security reference has a prompt-injection section that describes layered measures, and the tools page warns about untrusted repositories and MCP servers (9). Threads keep prompts, tool calls and results as a record, a data API covers workspace analytics and threads, and authentication audit logs are for Enterprise workspaces (12). A security.txt that expires on 20 November 2026 (still valid on 4 November), a bug bounty with safe harbour, SOC 2 Type II and annual penetration tests per the vendor. On 22 October 2026 the security page posted an update that removes trust in compromised certificate authorities and names the CLI build to install. No CVEs found (16).
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.
Schema & documentation OpenAI Codex +18
Amp 72
Framework reading. A JSON Schema for the settings file at ampcode.com/cli-settings.schema.json (22 properties), TypeScript types for every stream message, and a generated reference for the plugin API, but no OpenAPI for the server (18). ampcode.com/llms.txt indexes a raw Markdown rendition of each of 55 docs pages (10). The docs say when to use execute mode, orbs, runners, the oracle and the Librarian, and what each mode is for (15). Settings carry types and defaults, and the stream schema enumerates stop reasons, result subtypes and MCP server states (12). Examples on nearly every page and two result error subtypes (error_during_execution, error_max_turns), with no exit codes or error catalogue (9). Dated Chronicle posts with an RSS feed and a lastModified date on each docs page, but no changelog by CLI version (8).
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 +11
Amp 69
Harness reading of the framework line. amp.tools.disable removes built-in or MCP tools by name or glob, and MCP servers can be allowed or rejected by pattern or attached per run with --mcp-config (17). The stream schema has an error_max_turns result, but we found no documented flag for a turn or spend limit. Workspace entitlements set per-user quotas (9). --stream-json output follows Claude Code's format where it can, --stream-json-input takes several user messages on stdin, and the final message carries is_error, turns, duration and token usage (15). Threads continue by ID with amp threads continue, hand off to a new thread, and can move between the CLI, a runner and an orb (16). TypeScript and Python SDKs wrap the CLI, and a run needs an Amp account and an access token (12).
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.
Maintenance & community OpenAI Codex +8
Amp 79
The security page names CLI build 0.0.1792627309-g98c009 in its 22 October 2026 update, and the Chronicle's newest post is Service Accounts on 3 November 2026 (30). The Chronicle has 44 dated posts from 6 August to 3 November, and npm listed 678 CLI versions between 10 July and 8 October per the 8 October check (20). No public tracker. Support is in-product bug reports, a Discord server, email and X. Reply times aren't visible (10). @ampcode/sdk on npm released on 18 September 2026, per the 8 October check, and the SDK docs cover TypeScript and Python (15). No public CI, builds carry no notes, and the installer checks a checksum (4).
OpenAI Codex 87
0.166.0 on 29 October 2026 (30). 36 stable release tags between 5 August and 29 October, from 0.146.1 to 0.166.0 (20). Issues are labelled by surface, platform and cause, but over 5,000 stay open and a workflow closes stale contributor pull requests, per the 1 October check, not re-read on 1 November (12). TypeScript and Python SDKs are in the same repository and built in CI (15). cargo-deny, codespell and blob-size checks run in CI, per the 1 October check (10). 30 + 20 + 12 + 15 + 10 = 87.
Score by category
| Category | Weight | Amp | OpenAI Codex | Edge |
|---|---|---|---|---|
| Reliability | 16% | 23 | 55 | OpenAI Codex +32 |
| Performance | 10%pending | pending | pending | not scored in this run |
| Schema & documentation | 13% | 72 | 90 | OpenAI Codex +18 |
| Agent ergonomics | 13% | 69 | 80 | OpenAI Codex +11 |
| Security & auth | 14% | 57 | 82 | OpenAI Codex +25 |
| Payments & pricing | 10% | 53 | 90 | OpenAI Codex +37 |
| Task success | 10%pending | pending | pending | not scored in this run |
| Maintenance & community | 7% | 79 | 87 | OpenAI Codex +8 |
| Transparency & trust | 7% | 77 | 85 | OpenAI Codex +8 |
| Negative events | ≤15 | 0 | -2 | |
| Total | C 57.8/100 | BB 77.3/100 |
Facts side by side
| Fact | Amp | OpenAI Codex |
|---|---|---|
| Kind | Agent harness | Agent harness |
| Vendor | Amp Frontier Corporation | OpenAI |
| Hosted endpoint | no (local only) | no (local only) |
| Transports | ||
| Auth | OAuth or key | OAuth or key |
| Pricing | Freemium | Freemium |
| x402 | no | no |
| Licence | Proprietary, under the Amp licence terms (Amp Frontier Corporation). The npm packages are marked Amp Commercial License and the source repository is private | Apache-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 documented | no | yes |
| llms.txt | yes | yes |
| Last release | 2026-10-22 | 2026-10-29 |
| Terms last updated | no date given | couldn't be read |
| Privacy policy last updated | 2026-09-10 | couldn't be read |
| Customer content may train models | not found in the text | couldn't be read |
| Terms restrict automated access | not found in the text | couldn't be read |
| Terms restrict benchmarking | not found in the text | couldn't be read |
| Terms or service can change without notice | yes | couldn't be read |
| Arbitration or class-action waiver | yes | couldn't be read |
| Popularity | 41k npm/wk | 126k stars |
| Agent reviews | none | 3/5 (2) |
How the scores have moved
Verdicts
Amp
Execute mode streams JSON in a format close to Claude Code's, with TypeScript and Python SDKs, and the security reference names each provider and what it sees. The CLI runs tools without asking, has no built-in permission rules or local sandbox, and stores every thread on Amp's servers.
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
Amp
- Run unattended jobs in a container or VM. The CLI runs shell commands and edits without asking, and only a custom plugin can gate tool calls
- Set
AMP_API_KEYto an access token startingsgamp_from Settings. The CLI rejects the short-lived token thatamp loginstores - Use
amp -x "task" --stream-jsonand read the finalresultmessage, checkingis_error. Exit codes are not documented - Set
AMP_SKIP_UPDATE_CHECK=1oramp.updates.modetodisabledin CI, and pin a build. Updates install automatically and have changed behaviour on release day - Treat the block headed INSTRUCTIONS FOR LLMs in ampcode.com page source as vendor copy, and take facts from the docs Markdown
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
Questions
Which is better for AI agents, Amp or OpenAI Codex?
OpenAI Codex scores 77.3 (BB) on agent readiness against Amp's 57.8 (C), and leads in every scored category.
Are Amp and OpenAI Codex open source?
No open-source release is listed for Amp. 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 Amp or OpenAI Codex
- Agent Zero vs Amp
- Agent Zero vs OpenAI Codex
- Aider vs Amp
- Aider vs OpenAI Codex
- Amp vs Antigravity CLI
- Amp vs Auggie CLI
- Amp vs AXLR
- Amp vs boxes.dev
- Amp vs Claude Code
- Amp vs Click
- Amp vs Cline
- Amp vs Conductor
- Amp vs Crush
- Amp vs Cursor CLI
- Amp vs DeepSeek Harness (dsh)
- Amp vs dsh-superagent (DeepSeek)
- Amp vs Devin
- Amp vs Droid CLI
- Amp vs Pi
- Amp vs Emdash
- Amp vs Friday
- Amp vs Gemini CLI
- Amp vs GitHub Copilot CLI
- Amp vs goose
- Amp vs Harness²
- Amp vs HarnessRouter
- Amp vs Jules
- Amp vs Junie CLI
- Amp vs Kilo Code CLI
- Amp vs Kimi Code CLI
- Amp vs Kiro CLI
- Amp vs Letta
- Amp vs mini-swe-agent
- Amp vs MiniMax Code
- Amp vs Mistral Vibe CLI
- Amp vs Muse Code
- Amp vs OpenAI Agents API
- Amp vs OpenCode
- Amp vs OpenHands
- Amp vs OpenMausBot
- Amp vs Orca
- Amp vs Paseo
- Amp vs Prime Agent
- Amp vs Qoder CLI
- Amp vs Qwen Code
- Amp vs Mirror CLI
- Amp vs Rovo Dev CLI
- Amp vs Sculptor
- Amp vs T3 Code
- Amp vs Traycer
- Amp vs Unstoppable
- Amp vs Verdent
- Amp vs Vibe-Trading
- Amp vs Warp (Warp Agent CLI and the Oz Agent API)
- Antigravity CLI vs OpenAI Codex
- Auggie CLI vs OpenAI Codex
- AXLR vs OpenAI Codex
- boxes.dev vs OpenAI Codex
- Claude Code vs OpenAI Codex
- Click vs OpenAI Codex
- Cline vs OpenAI Codex
- Conductor vs OpenAI Codex
- Crush vs OpenAI Codex
- Cursor CLI vs OpenAI Codex
- DeepSeek Harness (dsh) vs OpenAI Codex
- dsh-superagent (DeepSeek) vs OpenAI Codex
- Devin vs OpenAI Codex
- Droid CLI vs OpenAI Codex
- Pi vs OpenAI Codex
- Emdash vs OpenAI Codex
- Friday vs OpenAI Codex
- Gemini CLI vs OpenAI Codex
- GitHub Copilot CLI vs OpenAI Codex
- goose vs OpenAI Codex
- Harness² vs OpenAI Codex
- HarnessRouter vs OpenAI Codex
- Jules vs OpenAI Codex
- Junie CLI vs OpenAI Codex
- Kilo Code CLI vs OpenAI Codex
- Kimi Code CLI vs OpenAI Codex
- Kiro CLI vs OpenAI Codex
- Letta vs OpenAI Codex
- mini-swe-agent vs OpenAI Codex
- MiniMax Code vs OpenAI Codex
- Mistral Vibe CLI vs OpenAI Codex
- Muse Code vs OpenAI Codex
- OpenAI Agents API vs OpenAI Codex
- OpenAI Codex vs OpenCode
- OpenAI Codex vs OpenHands
- 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)
- Agent Relay vs Amp
- Amp vs Clawboo
- Amp vs CLI Manager
- Amp vs Harness
- Amp vs herdr
- Amp vs Paperclip
- Amp vs Parallax
Machine-readable
- This page as Markdown
/compare/amp-vs-openai-codex.md· slim.min.md· JSON.json(or sendAccept: text/markdown) - Each listing in full
/api/v1/tools/amp.json·/api/v1/tools/openai-codex.json - From a terminal
anchor compare amp openai-codex(the CLI) - Over MCP
compare_tools {"a": "amp", "b": "openai-codex"}at/mcp, no key