Enterprise DNA Enterprise DNA
Directories / Alternatives / OpenAI Codex

Open Source Alternatives

Open source alternatives to OpenAI Codex

Open source alternatives to OpenAI Codex, ranked by GitHub stars and freshness.

6 open-source alternatives in the index, ranked by GitHub stars and freshness.

A Agents Coding one click

Aider

Paul Gauthier

Terminal-first AI pair programmer. Edits files in your repo, commits with sensible messages, runs your tests.

Alternative to Claude Code, Cursor, Github Copilot +2 more

open-source

Best for: Engineers who live in the terminal and want a tight, scriptable AI loop

A Agents Coding one click

Claude Code

Anthropic

Anthropic's terminal-native coding agent. Reads your repo, edits files, runs tests, ships PRs.

Alternative to Openai Codex, Aider, Cline +4 more

paid

Best for: Senior engineers who want a real terminal agent, not just autocomplete

A Agents Coding low

Cursor Background Agent

Anysphere

Cloud-based async coding agent that clones your repo, works on a branch, and ships a PR while you keep coding.

Alternative to Openhands, Openai Codex, Claude Code

freemium

Best for: Teams who want to parallelize coding work across isolated cloud environments

A Agents Coding one click

GitHub Copilot

GitHub / Microsoft

The original AI pair programmer, now with Agent Mode, Workspaces, and multi-model selection.

Alternative to Cursor, Codeium, Windsurf +2 more

freemium

Best for: Large orgs already on GitHub Enterprise

A Agents Coding high

OpenHands

All Hands AI

Open-source autonomous coding agent platform. Spins up a sandboxed dev environment, ships PRs end to end.

Alternative to Aider, Claude Code, Cursor +3 more

open-source

Best for: Teams who want a real autonomous coding agent and can run their own infra

A Agents Coding one click

Windsurf

Codeium

Codeium's IDE-with-an-agent. Cascade flow combines deep context with autonomous multi-file work.

Alternative to Cursor, Github Copilot, Claude Code +2 more

freemium

Best for: Engineers who want continuous agent context, not chat-and-snippet