8 Best Codex CLI Alternatives (2026)

• Most people searching for Codex CLI alternatives are not shopping, they already run it and something has stopped fitting.
• That something is usually a specific number rather than a feeling.
• This page starts from the fields where Codex CLI genuinely trails the rosters it appears in, and only then covers the reasons that never show up in a table.

The measured reasons.

• Subagents, No. Claude Code records Yes.

• Any one of those is enough on its own if you sized your architecture around it.
• None of them is enough if you didn't, which is why the list is short and specific rather than a general case against Codex CLI.

The reasons that never make it into a table.

• A price rise after a funding round.
• A licence change that turns a self-host into a subscription.
• A region you now need and they do not have.
• An acquisition.
• A support experience that quietly degrades.
• None of those are fields, and all of them move teams, which is why every entry below links back to Coding agents, where the full field set and its sources live.
• The ones we catch get logged on the Codex CLI timeline.

How the shortlist is ordered.

• Every tool below shares at least one comparison category with Codex CLI, sorted by how many categories the two overlap in.
• There is no editorial ranking, no sponsorship and no affiliate link, the order is the overlap count.
• The rationale under each is generated from the two tools' own cells, so it names real values rather than adjectives.

• Aider, Minimal terminal pair-programmer with a tree-sitter repo map and automatic git commits.
• It meets Codex CLI in Coding agents.
• It is ahead on Model breadth (any provider / router against one vendor + custom endpoint), Checkpoint & undo (Yes against Partial) and Pricing model (BYOK tokens only against subscription + token overage).
• What you give up: Opens PRs (No, where Codex CLI records Yes) and MCP (No, where Codex CLI records Yes).
• Best for scripted, repeatable edits where you want a git commit per change.
• The most auditable harness here, but visibly slowed while the category sprinted past.

Opens PRs

○NoCodex CLI: Yes

Inferredverified 2026-01-15

MCP

○NoCodex CLI: Yes

Community-reported

Background agents

○NoCodex CLI: Yes

Inferred

Permissions

prompts every actionCodex CLI: allowlist + OS sandbox

Inferredverified 2026-01-15

Hooks

○NoCodex CLI: Partial

Community-reported

Model breadth

any provider / routerCodex CLI: one vendor + custom endpoint

Vendor-claimedverified 2026-01-15source

• Amp, Sourcegraph's opinionated agent with no model picker and an ad-supported free tier.
• It meets Codex CLI in Coding agents.
• It is ahead on Subagents (Yes against No), Token markup (Yes against No) and Entry price ($0 /seat/mo against $20 /seat/mo).
• What you give up: Opens PRs (No, where Codex CLI records Yes) and BYOK (No, where Codex CLI records Yes).
• Best for teams who would rather not run a model-selection debate every quarter.
• Removing the model picker is defensible, but you control neither cost nor provider.

Opens PRs

○NoCodex CLI: Yes

Inferred

BYOK

○NoCodex CLI: Yes

Inferredverified 2026-01-15

Subagents

●YesCodex CLI: No

Inferredverified 2026-01-15

Licence

proprietaryCodex CLI: Apache-2.0

Inferredverified 2026-01-15

Token markup

●YesCodex CLI: No

Inferred

Local models

○NoCodex CLI: Yes

Inferredverified 2026-01-15

• Claude Code, Anthropic's terminal-first agent, with IDE, web and GitHub Action surfaces.
• It meets Codex CLI in Coding agents.
• It is ahead on Subagents (Yes against No), Plan mode (Yes against Partial) and Checkpoint & undo (Yes against Partial).
• What you give up: Licence (proprietary, where Codex CLI records Apache-2.0) and Local models (No, where Codex CLI records Yes).
• Best for terminal-native teams who want subagents and hooks without building them.
• The most complete extensibility surface here, at the cost of lock-in to one model vendor.

Subagents

●YesCodex CLI: No

Vendor-claimedverified 2026-01-15source

Licence

proprietaryCodex CLI: Apache-2.0

Inferredverified 2026-01-15

Local models

○NoCodex CLI: Yes

Community-reported

Plan mode

●YesCodex CLI: Partial

Inferredverified 2026-01-15

Checkpoint & undo

●YesCodex CLI: Partial

Community-reported

Skills / commands

●YesCodex CLI: Partial

Vendor-claimedverified 2026-01-15source

• Cline, Open-source VS Code and JetBrains agent built around an explicit plan/act split.
• It meets Codex CLI in Coding agents.
• It is ahead on Model breadth (any provider / router against one vendor + custom endpoint), Plan mode (Yes against Partial) and Checkpoint & undo (Yes against Partial).
• What you give up: Opens PRs (No, where Codex CLI records Yes) and Background agents (No, where Codex CLI records Yes).
• Best for VS Code and JetBrains teams who want BYOK without leaving the IDE.
• The clearest plan/act interaction and safest BYOK default, but it stays inside the editor.

Opens PRs

○NoCodex CLI: Yes

Inferred

Background agents

○NoCodex CLI: Yes

Inferred

Permissions

granular allowlistCodex CLI: allowlist + OS sandbox

Inferredverified 2026-01-15

Hooks

○NoCodex CLI: Partial

Community-reported

Model breadth

any provider / routerCodex CLI: one vendor + custom endpoint

Vendor-claimedverified 2026-01-15source

Headless / CI

◐PartialCodex CLI: Yes

Community-reported

• Cursor, VS Code fork with a real codebase index, background cloud agents and a CLI.
• It meets Codex CLI in Coding agents.
• It is ahead on Subagents (Partial against No), Token markup (Partial against No) and Repo indexing (embeddings index against agentic grep).
• What you give up: Licence (proprietary, where Codex CLI records Apache-2.0) and Local models (No, where Codex CLI records Yes).
• Best for large monorepos where agentic grep runs out of context before it finds anything.
• A real persistent codebase index inside the editor you review in, paid for in lock-in.

Licence

proprietaryCodex CLI: Apache-2.0

Inferredverified 2026-01-15

Local models

○NoCodex CLI: Yes

Inferred

Subagents

◐PartialCodex CLI: No

Community-reported

Token markup

◐PartialCodex CLI: No

Community-reported

Repo indexing

embeddings indexCodex CLI: agentic grep

Vendor-claimedverified 2026-01-15source

BYOK

◐PartialCodex CLI: Yes

Community-reported

• Devin, Fully delegated cloud engineer: file a task in Slack or the web app, get a PR back.
• It meets Codex CLI in Coding agents.
• It is ahead on Token markup (Yes against No), Repo indexing (hybrid index + agentic against agentic grep) and Plan mode (Yes against Partial).
• What you give up: BYOK (No, where Codex CLI records Yes) and Licence (proprietary, where Codex CLI records Apache-2.0).
• Best for backlogs of small, well-specified tickets nobody wants to pick up.
• The clearest full delegation, great for well-specified tickets, but ACU pricing bills you afterwards.

BYOK

○NoCodex CLI: Yes

Inferredverified 2026-01-15

Licence

proprietaryCodex CLI: Apache-2.0

Inferredverified 2026-01-15

Token markup

●YesCodex CLI: No

Inferred

Local models

○NoCodex CLI: Yes

Inferredverified 2026-01-15

Repo indexing

hybrid index + agenticCodex CLI: agentic grep

Community-reported

Checkpoint & undo

○NoCodex CLI: Partial

Inferred

• DIY harness, Your own loop over a model API with an agent SDK, the build-it-yourself reference point.
• It meets Codex CLI in Coding agents.
• It is ahead on Subagents (Partial against No), Model breadth (any provider / router against one vendor + custom endpoint) and Hooks (Yes against Partial).
• What you give up: Permissions (applies everything, where Codex CLI records allowlist + OS sandbox) and Plan mode (No, where Codex CLI records Partial).
• Best for one repeated task with a known shape and a tight tool surface.
• Right for narrow, repeated jobs, wrong for open-ended engineering.
• Note that we carry DIY harness as the do-it-yourself baseline in that roster, the "what if we just ran this ourselves" reference point.
• The honest answer is usually that it is cheaper and considerably more work.

Permissions

applies everythingCodex CLI: allowlist + OS sandbox

Inferred

Subagents

◐PartialCodex CLI: No

Inferred

Plan mode

○NoCodex CLI: Partial

Inferred

Checkpoint & undo

○NoCodex CLI: Partial

Inferred

Skills / commands

○NoCodex CLI: Partial

Inferred

Model breadth

any provider / routerCodex CLI: one vendor + custom endpoint

Inferred

• Gemini CLI, Apache-2.0 terminal agent from Google with an unusually generous free tier.
• It meets Codex CLI in Coding agents.
• It is ahead on Subagents (Partial against No), Checkpoint & undo (Yes against Partial) and Skills / commands (Yes against Partial).
• What you give up: Local models (No, where Codex CLI records Yes) and Opens PRs (Partial, where Codex CLI records Yes).
• Best for solo developers and students who want daily agent use at zero cost.
• The cheapest credible daily agent, a step behind on orchestration, with its PR path in a separate Action.

Local models

○NoCodex CLI: Yes

Inferred

Subagents

◐PartialCodex CLI: No

Community-reported

Opens PRs

◐PartialCodex CLI: Yes

Inferredsource

Background agents

◐PartialCodex CLI: Yes

Inferred

Checkpoint & undo

●YesCodex CLI: Partial

Vendor-claimedverified 2026-01-15source

Skills / commands

●YesCodex CLI: Partial

Inferredverified 2026-01-15

There is no editorial ranking on this page and no sponsorship behind it. The order is mechanical: every tool that shares a comparison category with Codex CLI, sorted by how many categories the two overlap in. A tool that meets Codex CLI in three rosters sits above one that meets it in a single roster, because more overlap means the comparison is more like-for-like.

The rationale under each entry is composed from the two tools' own cells. Where they differ on a field we score, the sentence names both values and the unit. Where they don't differ, it says so instead of manufacturing a distinction, which is why some entries are short.

Values, sources and verification dates all live on the category tables: Coding agents. If a figure here disagrees with a vendor's current pricing page, the vendor is right and we are stale.

Still deciding whether to move at all? The Codex CLI profile has the when-to-use and when-not-to-use blocks, and the Codex CLI timeline has the dated changes that usually trigger a migration.