Skip to content
Agent Search Engine.

Alternatives · Coding Agents

OpenAI Codex alternatives

These records overlap with OpenAI Codex's recorded tasks and have the same product type. The selection uses task text, then information completeness; stars and sponsorship do not set the order. Check the specific capability you need before switching.

8 task-related records from 61 category candidates · all coding agents · how we rank

The product you're replacing

OpenAI CodexAgentCoding Agents

OpenAI’s coding agent for local repository work and cloud tasks.

Paid product · License not checked

OpenAI Codex's record says to avoid it if: You need a no-code business workflow builder rather than a repository coding agent.

Building one yourself? How to build a coding agent →

Task-related research candidates

OpenCodeAgentOpen-source coding agent with a terminal interface and model-provider choice.Provider usage; optional model plansOpen sourcerecorded license: MITRecord checked · Recent push 227kGitHub stars

Recorded task overlap: repositories and code review; coding workflow. Compare the documented setup and limits before treating it as a substitute. The recorded use cases differ: OpenAI Codex — Developers who want assisted coding, local tests and reviewable changes, with optional cloud task delegation; OpenCode — Developers who want to choose a model provider for an interactive repository coding workflow.

AiderAgentPair-program with language models from your terminal and Git repository.Provider usage or local runtime costsOpen sourcerecorded license: Apache-2.0Record checked 50kGitHub stars

Recorded task overlap: repositories and code review; coding workflow. Compare the documented setup and limits before treating it as a substitute. The recorded use cases differ: OpenAI Codex — Developers who want assisted coding, local tests and reviewable changes, with optional cloud task delegation; Aider — Developers who want an interactive terminal workflow with Git-based review and a choice of model provider.

OpenWikiAgentMaintain Markdown context and source-linked claims for coding agents.Costs need recheckingOpen sourcerecorded license: MITRecord checked · Recent push 18kGitHub stars

Recorded task overlap: repositories and code review; coding workflow. Compare the documented setup and limits before treating it as a substitute. The recorded use cases differ: OpenAI Codex — Developers who want assisted coding, local tests and reviewable changes, with optional cloud task delegation; OpenWiki — Developers who want inspectable, updatable repository context rather than opaque memory alone.

Claude CodeAgentAnthropic's agentic coding tool that works in your terminal, IDE, and CI.Subscription or API billing; limits varyLicense not checkedRecord checked

Recorded task overlap: repositories and code review; coding workflow. Compare the documented setup and limits before treating it as a substitute. The recorded use cases differ: OpenAI Codex — Developers who want assisted coding, local tests and reviewable changes, with optional cloud task delegation; Claude Code — Developers who want an agentic coding tool in the terminal, IDE, and CI that works against existing repositories.

Devin CloudAgentCloud coding agents for delegated software tasks and pull requests.Costs need recheckingLicense not checkedRecord checked

Recorded task overlap: repositories and code review; coding workflow. Compare the documented setup and limits before treating it as a substitute. The recorded use cases differ: OpenAI Codex — Developers who want assisted coding, local tests and reviewable changes, with optional cloud task delegation; Devin Cloud — Delegating software tasks to cloud agents and reviewing their proposed changes.

Roo CodeAgentEditor coding assistant with an archived upstream repository.Costs not checkedOpen sourceUpstream archivedrecorded license: Apache-2.0Record checked 24kGitHub stars

Recorded task overlap: repositories and code review; coding workflow. Compare the documented setup and limits before treating it as a substitute. The recorded use cases differ: OpenAI Codex — Developers who want assisted coding, local tests and reviewable changes, with optional cloud task delegation; Roo Code — Developers reviewing an existing Roo Code installation or its open-source implementation.

OrbiAgentCoordinate GitHub issues, coding, review and repository releases.Costs not checkedOpen sourcerecorded license: AGPL-3.0Record checked · Recent push 255GitHub stars

Recorded task overlap: repositories and code review; coding workflow. Compare the documented setup and limits before treating it as a substitute. The recorded use cases differ: OpenAI Codex — Developers who want assisted coding, local tests and reviewable changes, with optional cloud task delegation; Orbi — Developers evaluating an issue-driven coding workflow with explicit repository release controls.

spec_driven_developAgentSpec-driven development workflow for AI coding agents: architecture-first planning, task decomposition, GitHub Issue/PR tracking, Deep Discuss, and adaptive control for Claude Code, Codex, Cursor,Costs not checkedOpen sourcePython · recorded license: MITRecord checked 992GitHub stars

Recorded task overlap: repositories and code review; coding workflow. Compare the documented setup and limits before treating it as a substitute. Recorded pricing categories differ: OpenAI Codex — Paid product; spec_driven_develop — Costs not checked. They do not establish total cost.

Browse all coding agents →

Frequently asked

How were alternatives to OpenAI Codex selected?
Recorded task topics and meaningful shared terms qualify same-type candidates in the same category. Results are ordered by that overlap, then information completeness and a stable identifier. Sponsorship and GitHub stars do not participate. The method can miss suitable tools whose records lack task information.
Does inclusion mean a tested replacement?
No. These are catalogue-based research candidates. Check current sources, costs, permissions and deployment requirements, then test your own task. ASE has not run a performance benchmark of this shortlist.