Alternatives to Codex

10 editor-selected alternatives · Codex overview →

source: tools.alternatives · stored order · active records only; review scores are annotations and never change membership or order

A directional evidence panel appears only when the substitute rationale, trade-offs, sources, and verification date have been recorded. Older selections without that panel remain visible but are unclassified under the new evidence contract.

Amp

85/100freemiumexplicit relation

Amp is a multi-model coding agent for terminal, web, macOS/iOS, and IDE-connected workflows. Vendor docs describe the same agent and threads across surfaces, with remote Orbs, local Runners, Dial modes (low / medium / high / ultra), shared threads, MCP, plugins, and BYOK / linked ChatGPT subscriptions. Pricing spans a free Hobby tier, optional Megawatt ($20/mo) and Gigawatt ($200/mo) Individual plans, no-extra-charge Teams workspaces, pay-as-you-go credits, and Enterprise.

Directional evidence

Amp competes with Codex as an AI coding agent from a different starting desk (multi-surface Sourcegraph agent vs OpenAI Codex stack).

aicoolies comparison; quillClass=comparison_backed; source=live aicoolies comparison checked September 25, 2026verified September 25, 2026

Amp pricing (vendor_documented, as-of 2026-09-17): free Hobby tier with all product features, pay-as-you-go orbs or free own Runners, and BYOK / linked ChatGPT (and other) subscriptions with no Amp token fees or limits on non-Enterprise tiers. Optional Individual plans: Megawatt $20/month and Gigawatt $200/month, each bundling included agent usage and orb minutes (vendor Individual cards describe ~45,000 minutes of orb time). Teams workspaces add sharing and pooled credits at no extra workspace fee; members can sit on Hobby, Megawatt, or Gigawatt. Enterprise is custom (SCIM, audit/network controls, pooled credits, priority support).Review →

OpenCode

83/100open sourceexplicit relation

Open-source terminal-based AI coding agent built in Go by the SST team, with a rich TUI (Bubble Tea) supporting 75+ model providers including OpenAI, Anthropic, Gemini, Bedrock, Groq, and OpenRouter. Features vim-like editing, persistent SQLite sessions, and LSP integration for 40+ languages. Fully free with no vendor lock-in, it has rapidly grown to 95k+ GitHub stars.

Directional evidence

OpenCode is a terminal-first OSS coding-agent alternative to Codex emphasizing openness and provider choice versus OpenAI’s integrated Codex stack.

aicoolies comparison; quillClass=comparison_backed; source=live aicoolies comparison checked September 25, 2026verified September 25, 2026

OpenCode is 100% free and open-source under the MIT license with $0 software licensing fees. Developers can run local models via Ollama at zero marginal cost, configure their own BYOK API keys across 75+ providers paying token costs directly to model providers, or optionally route requests through the OpenCode Zen pay-as-you-go gateway.Review →

Claude Code

92/100freemiumexplicit relation

Anthropic's agentic CLI coding tool that delegates complex tasks to Claude directly from the terminal. Understands entire codebases via automatic context gathering, edits multiple files, runs shell commands, and manages Git workflows autonomously. Supports CLAUDE.md for persistent project instructions, integrates with VS Code and JetBrains, and uses Claude Opus/Sonnet with extended thinking for complex architectural decisions. Built for terminal-first developers.

Directional evidence

Codex and Claude Code are catalogued as leading terminal AI coding agents with different model vendors and product packaging.

aicoolies comparison; quillClass=comparison_backed; source=live aicoolies comparison checked September 25, 2026verified September 25, 2026

Claude Code is included with Anthropic subscription tiers starting at $20/month for Claude Pro, $100/month for Claude Max (5x), $200/month for Claude Max (20x), and $30/user/month for Claude Team ($25/user/month billed annually). Alternatively, developers can use the CLI via pay-as-you-go Anthropic API keys billed strictly per token consumed.Review →

Aider

83/100open sourceexplicit relation

Terminal-based AI pair programmer with deep git integration. Auto-commits changes with meaningful messages and creates repository maps for navigating large codebases. Works with Claude, GPT, DeepSeek, and local models. One of the most popular open-source AI coding tools, known for its reliability, broad model support, and seamless command-line workflow.

Directional evidence

Aider is a git-centric terminal coding-agent peer often compared with Codex for repo-local pair-programming workflows.

aicoolies comparison; quillClass=comparison_backed; source=live aicoolies comparison checked September 25, 2026verified September 25, 2026

Aider is free, open-source CLI software (Apache 2.0) with zero subscription fees ($0). Users bring their own API keys from providers like Anthropic, OpenAI, or DeepSeek and pay standard token rates directly to those providers, or connect free local models via Ollama.Review →

Factory Droid

82/100freemiumexplicit relation

System of specialized AI Droids — Code, Knowledge, Reliability, and Product — each optimized for specific development tasks. Ranked #1 on Terminal-Bench with 58.75% score. BYOK model with support for Anthropic and OpenAI models. Enterprise-focused approach that treats AI coding as a team of specialized agents rather than a single general-purpose assistant.

Factory Droid offers individual plans starting at $20/month for Pro, $100/month for Plus (5x usage), and $200/month for Max (10x usage), alongside a Teams plan at $60/month base plus $40/seat/month and custom Enterprise agreements.Review →

Grok Build

82/100explicit relation

Grok Build is xAI’s terminal-first coding agent for planning, editing, testing, and reviewing code from a local CLI. It exposes subagent controls, worktree mode, headless JSON output, best-of-N parallel attempts, sandbox profiles, and cross-session Memory (/memory, /dream) for durable project conventions and facts. It fits developers comparing Claude Code, Codex, and Gemini CLI for local agentic workflows with deeper parallel execution.

Commercial AI coding agent by xAI. Interactive terminal CLI access is included with SuperGrok ($30/mo) or X Premium+ ($40/mo) subscriptions. Headless and programmatic access is available via metered pay-as-you-go xAI API token billing.Review →

Crush

84/100explicit relation

LSP-enhanced terminal coding agent from Charmbracelet with the broadest cross-platform support including Android. Features mid-session model switching and MCP extensibility for custom tool integration. Combines the elegance of Charmbracelet's TUI toolkit with practical coding assistance, offering a polished terminal experience for developers on any platform.

Free source-available CLI under FSL-1.1-MIT (automatically converts to MIT after 2 years); requires commercial licensing for competing use or proprietary SaaS distribution.Review →

Pi

84/100open sourceexplicit relation

Pi Coding Agent is an MIT-licensed Node.js CLI from earendil-works for building and running coding agents in a local terminal. The current package describes a read/bash/edit/write toolset and session management, while the repo positions Pi as a unified LLM API, agent loop, TUI, and coding-agent CLI. It is best framed as a lean, self-extensible BYO-model toolkit rather than a managed IDE.

Free and 100% open source under the MIT license. Pi charges no subscription or license fees; developers bring their own API keys (BYOK) for cloud LLM providers or run local open-source models via Ollama and vLLM at zero compute license cost.Review →

Kimi Code

78/100freemiumexplicit relation

Terminal-based AI coding agent from Moonshot AI, powered by Kimi K2.5 with a 256K context window that achieves 76.8% on SWE-Bench Verified. Reads and edits code, executes shell commands, fetches web pages, and autonomously plans multi-step development workflows through natural language. Moonshot's entry into the AI coding agent market, leveraging their strength in large-context language models.

Freemium AI coding intelligence platform and API powered by Moonshot AI. Free web and mobile app tier ($0/mo) provides basic web search, code generation, and interactive assistant capabilities. Moonshot AI Developer API offers pay-as-you-go token billing across moonshot-v1 tiers (8k, 32k, 128k, up to 2M context) ranging from ¥12 to ¥60 per 1M tokens (~$0.001–$0.008/1k tokens), with a ¥15 free trial credit for new developer accounts.Review →

ZCode

freemiumexplicit relation

ZCode is Z.ai’s Agentic Development Environment for GLM-5.2 coding workflows. The desktop app combines a first-party coding agent, goal mode, model/provider setup, MCP server management, Git and terminal context, remote phone control, usage stats and safety confirmation modes so developers can plan, implement, review and iterate on long-running software tasks from one workspace.

The ZCode desktop application is free to download and use. Access to the underlying GLM-5.2 and GLM-5.3 models is billed via Z.ai's GLM Coding Plan subscriptions, starting at $18 per month for the Lite tier, $80 per month for Pro, and $168 per month for Max (with up to 30% discounts on annual billing).

Open-source Codex alternatives

OpenCode, Aider, Pi — see all open-source developer tools.

Free Codex alternatives

Amp, Claude Code, Factory Droid, Kimi Code, ZCode offer a free plan or free tier.

More Terminal & CLI Tools tools

same category, not editor-selected alternatives — see how Codex compares →

CursorAI-first code editor built as a VS Code fork that deeply integrates LLMs into every part of the development workflow. Features Tab autocomplete with multi-line predictions, Cmd+K inline editing, AI chat with full codebase awareness, and Agent mode for autonomous multi-file edits with terminal execution. Supports GPT-4, Claude, and more with automatic context from project files and docs. Includes privacy mode for SOC 2 compliance. The leading AI-native IDE with 100K+ paying users.DevinDevin is Cognition's managed AI software engineer for delegating engineering tasks to cloud and desktop agents. It can plan work, navigate codebases, write and run code, test changes, open PRs, review/autofix issues, and collaborate through GitHub, GitLab, Bitbucket, Linear, Jira, Slack, and Teams. Current Devin surfaces include Devin Cloud, Devin Desktop, Devin CLI, Devin Review, Windows VM support, DeepWiki, Ask Devin, and team/enterprise controls.ClaudeAnthropic's AI assistant known for strong reasoning, nuanced writing, and extended context up to 200K tokens. Available in Opus (most capable), Sonnet (balanced), and Haiku (fast) tiers. Features web search, deep research, file analysis, code execution, artifacts, and Projects for organized workflows. Claude Code provides terminal-based agentic coding. API supports tool use, batch processing, and prompt caching. Available via claude.ai, mobile apps, and developer API.ChatGPTChatGPT is OpenAI’s consumer and business assistant for everyday Q&A, writing, coding help, image tools, deep research, and workspace collaboration across web and apps. Plans span Free, Go, Plus, Pro, Business, and Enterprise on chatgpt.com.ripgrepUltra-fast recursive text search tool written in Rust that respects .gitignore rules automatically. Searches directories significantly faster than grep with smart defaults like line numbers, syntax highlighting, and compressed file support. The de facto replacement for grep among developers, combining the speed of Rust with sensible defaults that eliminate the need for complex command-line flags.GitDiagramVisual architecture generator that transforms any GitHub repository into an interactive system design map within seconds. Analyzes repository structures and README documentation to produce validated component flowcharts, dependency graphs, and Mermaid diagrams. Supports direct URL routing by replacing hub with diagram, provides instant export to SVG and PNG formats, and handles private repositories through user-supplied personal access tokens.CodeRabbitAI-powered code review tool that automatically analyzes pull requests and provides line-by-line feedback on code quality, bugs, security vulnerabilities, and best practices. Integrates with GitHub and GitLab as a bot that comments on PRs. Uses LLMs to understand code context and suggest improvements. Learns from your codebase patterns and team preferences. Supports all major programming languages. Reduces review cycle time while catching issues human reviewers might miss.GitHub CopilotAI-powered code assistant from GitHub and OpenAI that provides real-time code suggestions, completions, and chat-based help directly in your editor. Offers inline completions, a chat interface, an autonomous coding agent that can implement features from GitHub Issues, and AI code review with 60M+ reviews processed. Supports GPT-4o, Claude Sonnet, and Gemini Pro. Works with VS Code, Visual Studio, JetBrains IDEs, Neovim, Xcode, and Eclipse. The benchmark AI pair programmer.Mistral AIMistral AI is the French frontier-AI lab behind open-weight and commercial models, Mistral Vibe (formerly Le Chat), Studio, agentic coding, and the European-hosted Mistral Compute cloud. It gives developers an EU-centered alternative across API, assistant, agent-platform, and sovereign-infrastructure workflows, with model-specific licensing and pricing that should be checked per workload.

Codex head-to-head

FAQ

Which Codex alternative is listed first?

Amp is first in the editor-selected list of 10 Codex alternatives and carries an editorial review score of 85/100. The stored order is editorial; review scores do not determine membership or position.

Are there open-source Codex alternatives?

Yes — OpenCode, Aider, Pi are open source.

Are there free Codex alternatives?

Yes — Amp, Claude Code, Factory Droid, and more offer a free plan or free tier.