8 Best Codex CLI Alternatives (2026)

The closest alternatives to Codex CLI are Aider, Amp, Claude Code and Cline, with 4 more below. Each shares a comparison category with it, so every rationale here names both tools' real values. Codex CLI is marked No on Subagents, where Claude Code records Yes — usually where a switch starts.

Website Docs Source Codex CLIlogo & brand assets Coding agents

Why do people look for Codex CLI alternatives?

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, so 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, and the rationale under each is generated from the two tools' own cells, so it names real values rather than adjectives.

1.Aider

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. Still the most auditable harness here, and the repo map is a better idea than much of what replaced it — but the project has visibly slowed while the category sprinted past on MCP, subagents and sandboxing. Pick it for minimalism, not for keeping up.

Where Aider and Codex CLI actually differ

Opens PRs: NoCodex CLI: Yes
MCP: NoCodex CLI: Yes
Background agents: NoCodex CLI: Yes
Permissions: prompts every actionCodex CLI: allowlist + OS sandbox
Hooks: NoCodex CLI: Partial
Model breadth: any provider / routerCodex CLI: one vendor + custom endpoint

Aider profile Compare in Coding agents

2.Amp

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 a defensible product decision — most people choose badly and then blame the harness — but it means you control neither cost nor provider, and an ad-supported tier is an odd thing to sit next to a proprietary codebase. Subagent quality is genuinely good.

Where Amp and Codex CLI actually differ

Opens PRs: NoCodex CLI: Yes
BYOK: NoCodex CLI: Yes
Subagents: YesCodex CLI: No
Licence: proprietaryCodex CLI: Apache-2.0
Token markup: YesCodex CLI: No
Local models: NoCodex CLI: Yes

Amp profile Compare in Coding agents

3.Claude Code

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 of any harness here — subagents, hooks, skills and MCP all first-class — at the cost of being locked to one model vendor. If Anthropic's pricing or availability is a business risk for you, that lock is the whole argument against it.

Where Claude Code and Codex CLI actually differ

Subagents: YesCodex CLI: No
Licence: proprietaryCodex CLI: Apache-2.0
Local models: NoCodex CLI: Yes
Plan mode: YesCodex CLI: Partial
Checkpoint & undo: YesCodex CLI: Partial
Skills / commands: YesCodex CLI: Partial

Claude Code profile Compare in Coding agents

4.Cline

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 plan/act split remains the clearest interaction model in the category — you approve an approach, not a diff. It is the safest default for VS Code teams who want BYOK, but it stays inside the editor: no subagents, no hooks, no PR path.

Where Cline and Codex CLI actually differ

Opens PRs: NoCodex CLI: Yes
Background agents: NoCodex CLI: Yes
Permissions: granular allowlistCodex CLI: allowlist + OS sandbox
Hooks: NoCodex CLI: Partial
Model breadth: any provider / routerCodex CLI: one vendor + custom endpoint
Headless / CI: PartialCodex CLI: Yes

Cline profile Compare in Coding agents

5.Cursor

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, which is exactly what a million-line monorepo needs and what grep-based harnesses cannot fake. It is not the only index here — Windsurf and Kilo Code embed too, and Copilot and Devin read an index alongside live search — but it is the best-integrated one. You pay for it in lock-in: the index, the gateway and the agent identity are all Cursor's, and BYOK is a second-class path.

Where Cursor and Codex CLI actually differ

Licence: proprietaryCodex CLI: Apache-2.0
Local models: NoCodex CLI: Yes
Subagents: PartialCodex CLI: No
Token markup: PartialCodex CLI: No
Repo indexing: embeddings indexCodex CLI: agentic grep
BYOK: PartialCodex CLI: Yes

Cursor profile Compare in Coding agents

6.Devin

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 expression of full delegation: no local client, no model picker, a pull request or nothing. A real fit for well-specified tickets on a repo with good tests, and a poor one for anything exploratory. ACU pricing means you learn the cost afterwards.

Where Devin and Codex CLI actually differ

BYOK: NoCodex CLI: Yes
Licence: proprietaryCodex CLI: Apache-2.0
Token markup: YesCodex CLI: No
Local models: NoCodex CLI: Yes
Repo indexing: hybrid index + agenticCodex CLI: agentic grep
Checkpoint & undo: NoCodex CLI: Partial

Devin profile Compare in Coding agents

7.DIY harness

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 — a codemod runner, a test-backfill bot — where a general harness wastes most of its context rediscovering conventions you could have hardcoded. Wrong for open-ended engineering, where you will spend a quarter rebuilding permissions, checkpointing and context management worse than the incumbents. 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.

Where DIY harness and Codex CLI actually differ

Permissions: applies everythingCodex CLI: allowlist + OS sandbox
Subagents: PartialCodex CLI: No
Plan mode: NoCodex CLI: Partial
Checkpoint & undo: NoCodex CLI: Partial
Skills / commands: NoCodex CLI: Partial
Model breadth: any provider / routerCodex CLI: one vendor + custom endpoint

DIY harness profile Compare in Coding agents

8.Gemini CLI

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 way to run an agent every day — the free tier is not a trial. In exchange you get a harness a step behind Claude Code and Codex on orchestration, and a PR path that lives in a separate GitHub Action.

Where Gemini CLI and Codex CLI actually differ

Local models: NoCodex CLI: Yes
Subagents: PartialCodex CLI: No
Opens PRs: PartialCodex CLI: Yes
Background agents: PartialCodex CLI: Yes
Checkpoint & undo: YesCodex CLI: Partial
Skills / commands: YesCodex CLI: Partial

Gemini CLI profile Compare in Coding agents

How this list was built

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.