The best Claude Code alternatives are OpenCode if you want an open-source terminal agent that works with many model providers, Codex CLI if you already pay for a ChatGPT plan, and Gemini CLI if you work through Google Cloud's Gemini Code Assist. Aider suits developers who want every AI edit committed to git, Cline covers editor, terminal and CI, and Goose is a general-purpose agent with a desktop app and a CLI.
Claude Code is Anthropic's closed-source coding agent that reads a codebase, edits files and runs commands while you review. This guide covers agents you drive from a terminal or that run commands on your own machine, with open-source tools first and commercial agents after. For AI editors such as Cursor and Zed, see the Cursor alternatives guide.
| Tool | Type | Category | Self-host | Pricing | GitHub |
|---|---|---|---|---|---|
Claude Code | SaaS | AI Tools | No | From $20/mo per seat | Closed source |
OpenCode | Open source | AI Tools | No | Free (open source) | ★ 226k |
Codex CLI | Open source | AI Tools | No | Free (open source) | ★ 135k |
Gemini CLI | Open source | AI Tools | No | Free (open source) | ★ 109k |
Aider | Open source | AI Tools | No | Free (open source) | ★ 50k |
Cline | Open source | AI Tools | No | Free (open source) | ★ 72k |
Goose | Open source | AI Tools | No | Free (open source) | ★ 56k |
OpenHands | Open source | AI Tools | No | Free (open source) | ★ 93k |
Open Interpreter | Open source | AI Tools | No | Free (open source) | ★ 69k |
Warp | SaaS | Developer Tools | No | Free plan · from $20/mo per seat | Closed source |
Factory | SaaS | AI Tools | Vendor edition | From $20/mo | Closed source |
Augment Code | SaaS | AI Tools | No | From $20/mo | Closed source |
Live data from Enlisted: GitHub stats sync daily; pricing comes from each vendor's pricing page. “Vendor edition” means closed source, with a version the vendor lets you run on your own servers.
A note on the table: its Self-host column is mostly No because terminal agents run on your own machine rather than as server software. What matters is which model provider you connect, which the picks below explain.
How much do Claude plans cost compared with free open-source agents?
Claude Code is included in Claude subscriptions, so its entry cost is the price of a Claude plan, while the open-source agents below are free to install and cost whatever model you connect. The table lists the plan prices Anthropic publishes.
| Claude plan | Monthly billing | Annual billing |
|---|---|---|
| Free | $0 (checked Nov 2026) | Not applicable |
| Pro, per user | $20 (checked Nov 2026) | $17 per month, billed as $200 up front (checked Nov 2026) |
| Max, per user | $100 (checked Nov 2026) | Not listed separately (checked Nov 2026) |
| Ultra, per user | $200 (checked Nov 2026) | Not listed separately (checked Nov 2026) |
| Team Standard, per seat | $25 (checked Nov 2026) | $20 per month (checked Nov 2026) |
| Team Premium, per seat | $125 (checked Nov 2026) | $100 per month (checked Nov 2026) |
Source: Claude pricing. The page does not name a currency code and says prices exclude tax and may change. It lists Claude Code on Pro, Max and Ultra and not on Free, says Claude Code is included in all paid plans, and describes the Team plan as for teams of 2 to 150 people (checked Nov 2026).
The commercial agents in this guide that publish a price on a readable page are Warp, Augment Code and Factory. Their entry points are in the table below, and each pick explains what the plan covers.
| Agent | Plan and price | What the page says it includes |
|---|---|---|
| Warp | Free $0; Build $20 per month on the monthly plan or $18 on the annual plan; Max $200 monthly or $180 annual; Business $50 per user monthly or $45 annual (checked Nov 2026) | Build and Max include $20 and $200 of agent usage each month; Business is for up to 25 seats |
| Augment Code | Standard $20 per month flat; Business $100 per month flat (checked Nov 2026) | No per-seat charge, up to 50 seats, with $20 and $100 of usage included each month |
| Factory | Pro $20 per month; Plus $100; Max $200; Teams $60 per month per team plus $40 per seat (checked Nov 2026) | Plus is about 5x and Max about 10x the usage of Pro; Teams covers up to 10 seats |
Sources: Warp pricing, Augment Code pricing and Factory pricing. Prices are in USD as shown on each page.
Why people look for Claude Code alternatives
Claude Code is available in the terminal, VS Code and JetBrains, on the web and mobile, and through GitHub and Slack. Enlisted lists it as closed source and hosted, and the reasons to compare it with other agents are specific.
- No free plan. Enlisted lists Claude Code with paid plans only. It is included in Claude subscriptions, with per-seat Team and Enterprise plans, so trying it means paying.
- The agent and the model come from one vendor. Claude Code is Anthropic's own agent, built around its models. Open-source agents let you choose the model provider, use a local model, or sign in with a subscription you already have.
- Closed source. You cannot read or modify the agent itself. Open-source agents publish their code and licences, so you can audit what runs on your machine.
- Different approval and sandbox defaults. Teams compare how each agent asks before it runs commands or edits files, covered in a section below.
- Headless and CI use. Some agents are built to run in scripts and pipelines. Cline's CLI, for example, has a headless mode for CI/CD.
How we picked
Each tool reads a codebase, edits files and can run commands, which is Claude Code's core job. Open-source entries needed recent GitHub activity, and licences are quoted as Enlisted lists them. One popular project whose repository is read-only, Continue, is left out for that reason. Commercial agents are included where Enlisted lists a terminal or command-line product. Descriptions come from the catalogue and vendor docs. Read about how Enlisted ranks tools.
1. OpenCode: best open-source terminal agent with many providers
OpenCode is an open-source coding agent for the terminal, released under MIT, with a beta desktop app for macOS, Windows and Linux. It ships two built-in agents you switch between with the Tab key: a build agent with full development access, and a read-only plan agent that denies file edits by default and asks before running shell commands.
Its docs say it connects to model providers through the AI SDK and Models.dev, supports local models through Ollama, LM Studio and llama.cpp, and can sign in with existing ChatGPT, GitHub Copilot or GitLab Duo subscriptions. That makes it the most direct open-source answer to a Claude Code habit without Anthropic's models.
- Best for: terminal users who want to choose their provider or run a local model.
- Watch out for: its permission rules mostly default to allow, so tighten them (covered below), and the desktop app is in beta.
2. Codex CLI: best for ChatGPT plan users
OpenAI's open-source coding agent, Codex CLI, runs locally in your terminal. Its code is in Rust, and the licence is Apache-2.0. You start it with the codex command and ask it to read, explain and change code. It installs through scripts, package managers or binaries for Mac, Linux and Windows.
You can sign in with a ChatGPT plan or use an API key. OpenAI's docs describe a default "Auto" preset that combines a workspace-write sandbox with approvals on request, with network access off. A closed-source OpenAI Codex product adds cloud tasks and IDE use.
- Best for: developers who already have a ChatGPT plan and want a local agent from the same vendor.
- Watch out for: Codex CLI is designed around OpenAI's models and account system, which matters if you want a different vendor.
3. Gemini CLI: best open-source terminal agent for Google Cloud and Gemini users
Gemini CLI is Google's open-source terminal agent for working with Gemini models, written in TypeScript and licensed under Apache-2.0. Out of the box it can ground answers with Google Search, work with files, run shell commands and fetch web pages, and integrations can be added through MCP.
The project's README says Gemini CLI has no free tier or Google AI plan access as of November 2026, and that free individual access moved to Antigravity CLI on 18 June 2026. It is now aimed at organizations with Gemini Code Assist Standard or Enterprise, Code Assist for GitHub on Google Cloud, and legacy paid API or Vertex keys, per the Gemini CLI repository (checked Nov 2026). Its docs describe optional sandboxing, using macOS Seatbelt or containers such as Docker and Podman, which you turn on with a flag, environment variable or setting. It is not enabled by default.
- Best for: teams already on Google Cloud who want a Gemini terminal agent under an Apache-2.0 licence.
- Watch out for: there is no free individual tier any more, and sandboxing is opt-in.
4. Aider: best git-first terminal pair programmer
Aider pairs you with large language models for programming from the command line. It is open source under Apache-2.0. It builds a map of your codebase, commits each change to git with a descriptive message so you can diff or undo it, and can run linters and tests after edits and try to fix what they report.
It works with cloud and local models, accepts images and web pages as context, supports voice requests and covers more than 100 programming languages. Its history of small commits doubles as the review trail.
- Best for: developers who want every AI change in their git history.
- Watch out for: Aider's last GitHub commit is older than most others here, so check how active the repository is before you depend on it.
5. Cline: best open-source agent across IDE, terminal and CI
Cline is an open-source coding agent for your IDE, terminal and desktop, with a VS Code extension, a JetBrains plugin, a CLI, a desktop app for macOS and Windows, and an SDK. It can edit across a project, create files, run commands and browse the web, with human-in-the-loop approval for tools in the editor. It is Apache-2.0 licensed.
The CLI has an interactive mode and a headless mode for CI/CD and scripting, and the desktop app schedules recurring routines. Enlisted lists the open-source extension as free for individuals, who pay only for model inference or use their own API keys.
- Best for: developers who want one agent in the editor, the terminal and CI.
- Watch out for: you manage keys and inference costs, and agents that run commands need careful approval settings.
6. Goose: best general-purpose agent with many model providers
Goose is an open-source, general-purpose AI agent written in Rust, available as a desktop app, a CLI and an API. It is not limited to coding: the project suggests research, writing, automation and data analysis too. It runs locally and is released under Apache-2.0.
It works with more than a dozen model providers, including Anthropic, OpenAI, Google, Ollama, OpenRouter, Azure and Bedrock, and can use existing Claude, ChatGPT or Gemini subscriptions through ACP instead of API keys. Extensions connect through the Model Context Protocol, and teams can ship a custom build with preset providers and branding.
- Best for: people who want a local agent that is not tied to one model vendor, for coding and other tasks.
- Watch out for: its scope is wider than coding, so check how it handles your project size and language.
7. OpenHands: best for running several coding agents from one place
OpenHands is an open-source project whose current README centres on Agent Canvas, a self-hosted control center for starting conversations with coding agents and automating engineering tasks. By default it uses the OpenHands agent, and it can also drive third-party agents such as Claude Code, Codex and Gemini.
It runs locally by default and can use backends including Docker containers, virtual machines and company infrastructure. Automations can run on a schedule or on webhooks, with integrations for Slack, GitHub, Linear and Notion. The code is MIT-licensed, and Enlisted lists a free local use and a free hosted individual tier with model usage passed through at cost.
- Best for: teams that want to run agents, including Claude Code itself, in isolated Docker or cloud environments.
- Watch out for: it is a control center around agents rather than a single terminal assistant, so it adds a layer to learn.
8. Open Interpreter: best for low-cost open models
Open Interpreter is an open-source coding agent in Rust, forked from OpenAI's Codex CLI and tuned to get good results from low-cost open models such as Kimi, GLM and Qwen. After installing on macOS, Linux or Windows you start a session by typing interpreter or i.
Its main idea is harness emulation: it reproduces the agent setup that suits a given model and lets you switch harness with a slash command. It reuses AGENTS.md files, skills directories and MCP, and is Apache-2.0 licensed. Model costs depend on the provider you choose.
- Best for: developers who want to run a terminal agent on cheaper open models.
- Watch out for: its latest release is numbered 0.0.x, so expect the interface to keep changing, and results depend on the model you pair it with.
9. Warp: best terminal with agents built in
Warp began as a modern terminal and now positions itself as a platform for automating software development with agents. Its products include Warp Terminal, designed for working with coding agents, Warp Agent CLI, a coding agent that runs in any terminal, and Warp Factories for running fleets of agents.
The vendor lists use cases such as first-pass code review on pull requests, bug investigation, refactors and migrations. Enlisted lists a free plan alongside paid individual and business tiers with usage-based top-ups, and Warp's pricing page shows a $0 Free plan and a $20 per month Build plan on monthly billing (checked Nov 2026). Warp is closed source.
- Best for: developers who want their terminal and their agent from the same product.
- Watch out for: it is proprietary, and heavy agent use means usage-based costs.
10. Factory: best for governed agents in enterprises
Factory is a commercial platform of autonomous agents, called Droids, that plan, build, review and ship code across desktop, terminal, web and CLI. The vendor describes model-independent intelligence, analytics on adoption and consumption per developer and team, Mission Control for monitoring active work, and Automations for repetitive tasks.
Factory's pricing page lists no free plan: Pro is $20 per month, Plus $100 and Max $200 for individuals, Teams is $60 per month per team plus $40 per seat for up to 10 seats, and Business and Enterprise are by contact (checked Nov 2026).
- Best for: engineering organizations that want governance and usage analytics around coding agents.
- Watch out for: it is closed source and aimed at organizations more than solo developers.
11. Augment Code: best for very large codebases
Augment Code is an AI coding platform for large codebases and engineering teams, with a Context Engine, a CLI and cloud agents. Its solutions cover code review, test coverage, ticket-to-PR automation, migrations and onboarding, with engineers holding the quality gates.
Augment Code's pricing page shows flat team pricing rather than per-seat charges: Standard at $20 per month and Business at $100 per month, each for up to 50 seats, with no free plan listed (checked Nov 2026). It is closed source.
- Best for: teams working in big repositories who want a context-aware agent with a CLI.
- Watch out for: it is proprietary, and Enlisted lists paid plans only.
More agents worth a look
- Kilo Code: an MIT-licensed agent for VS Code, JetBrains and the command line that works with hundreds of models. It is covered in the Cursor guide.
- Cursor and GitHub Copilot: both list a command-line product (Cursor CLI and Copilot CLI) alongside their editor features.
- Kiro and Google Antigravity: AWS's spec-driven agentic IDE and Google's agent-first platform, each with a CLI.
- Devin: an AI software engineer that takes tickets and opens pull requests in its own environment.
- OpenAI Codex: the closed-source cloud, terminal and IDE product behind Codex CLI.
How do approvals and sandboxing compare?
A terminal agent that edits files and runs commands needs boundaries. These are the defaults each vendor's docs describe today, and they change, so read the current docs before trusting any of them.
| Agent | What its docs describe | Where to tighten |
|---|---|---|
| Claude Code | Manual mode asks before shell commands, except a built-in set of read-only ones, and before file edits. Modes include acceptEdits and bypassPermissions | Deny, ask and allow rules, plus an OS-level sandbox documented separately |
| Codex CLI | An Auto preset with a workspace-write sandbox, approvals on request and network access off by default | Sandbox modes read-only, workspace-write and danger-full-access |
| Gemini CLI | Optional sandbox using Seatbelt or containers, not on by default | Turn on with a flag, environment variable or setting |
| OpenCode | Allow, ask or deny per action, with most actions defaulting to allow and .env files blocked by default | Rules with wildcards, per-agent overrides and the read-only plan agent |
| Cline | Human-in-the-loop approval for tools in the editor | The approval options in Cline's docs |
Claude Code's own docs say its bypass mode should only be used in isolated environments such as containers or virtual machines. The same advice applies to every agent here: for an unfamiliar repository, run it in a container or a throwaway checkout, and keep secrets out of reach.
Which Claude Code alternative should you choose?
| If you want | Pick |
|---|---|
| Open source with the widest model choice and local models | OpenCode |
| A local agent tied to your ChatGPT plan | Codex CLI |
| A Gemini agent through Google Cloud's Code Assist | Gemini CLI |
| A free agent to point at a local model | Aider or OpenCode |
| Every change committed to git | Aider |
| One agent for editor, terminal and CI | Cline |
| A general-purpose agent that is not tied to one vendor | Goose |
| To run several agents in Docker or the cloud | OpenHands |
| A terminal agent on cheap open models | Open Interpreter |
| Terminal and agents in one product | Warp |
| Governance and analytics for a team | Factory |
See every Claude Code alternative in the catalogue, the Cursor alternatives page, or the AI tools and developer tools categories.
Bring your own model: what it means for cost and privacy
Open-source agents are free to install, but the model behind them is not free by default. You either pay a provider for usage, sign in with a subscription where the tool supports it, or run a local model.
- Where the model runs decides where your code goes. A hosted provider receives the files the agent reads, whereas a local model keeps them on your machine.
- Subscriptions can replace keys. Codex CLI signs in with a ChatGPT plan, OpenCode supports ChatGPT, GitHub Copilot and GitLab Duo logins, and Goose can use existing Claude, ChatGPT or Gemini subscriptions through ACP.
- Local models trade quality for control. Check the model's strength on your language and project size before committing a team to it.
If you want a general chat assistant next to your coding agent, see ChatGPT alternatives. Where you host the code the agent edits is a separate choice, covered in the GitHub alternatives guide.
Sources and method
Figures and claims in this guide were read from official pages in November 2026:
- Claude pricing (checked Nov 2026)
- Warp pricing, Augment Code pricing and Factory pricing (checked Nov 2026)
- Gemini CLI repository, licence and free-tier status (checked Nov 2026)
- Each agent's own documentation for feature and approval descriptions, linked from its Enlisted page
The data comes from vendor pages and the Enlisted catalogue. The post makes no claim of having tested the agents. OpenAI's pricing pages could not be read in November 2026, so Codex CLI plan prices are not quoted. Warp, Augment Code and Factory pages were read as served in November 2026, and the toggle shown on Warp's page was recorded for both monthly and annual billing.
Claude Code alternatives: pricing compared
Plans and list prices from each vendor's pricing page. Prices change, so confirm the current price on the vendor's page before you buy.
| Tool | Free option | Paid plans | Source |
|---|---|---|---|
Claude Code | No free plan |
Pro, Max 5x, Max 20xPrices on the vendor's page | Pricing pageChecked 2 Oct 2026 |
OpenCode | Free (open source) | None listed | Pricing page |
Codex CLI | Free (open source) | None listed | |
Gemini CLI | Free (open source) |
Google AI Pro, Google AI Ultra, Google Developer Program, AI Studio API keyPrices on the vendor's page | Pricing pageChecked 2 Oct 2026 |
Aider | Free (open source) | None listed | |
Cline | Free (open source) |
| Pricing pageChecked 2 Oct 2026 |
Goose | Free (open source) | None listed | |
OpenHands | Free (open source) |
| Pricing pageChecked 2 Oct 2026 |
Open Interpreter | Free (open source) | None listed | |
Warp | Free plan |
| Pricing pageChecked 3 Oct 2026 |
Factory | No free plan |
| Pricing pageChecked 3 Oct 2026 |
Augment Code | No free plan |
| Pricing pageChecked 2 Oct 2026 |
List prices from each vendor's public pricing page on the date shown. Annual billing is often cheaper, and taxes, usage and transaction fees aren't included. Open-source tools cost nothing to self-host beyond your own server.
Frequently asked questions
- What is the best open-source alternative to Claude Code?
- OpenCode is the broadest open-source choice, released under MIT and able to connect to many model providers and local models. Codex CLI and Gemini CLI are Apache-2.0 agents from OpenAI and Google, Aider is an Apache-2.0 tool that commits each change to git, and Goose is an Apache-2.0 general-purpose agent. All of them run in a terminal and need a model provider, which can cost money.
- Is there a free alternative to Claude Code?
- OpenCode, Aider and Goose are free open-source software you can point at a local model, and Cline is free for individuals with model inference billed by your provider. Gemini CLI no longer has a free tier: its README says individual free access moved to Google's Antigravity CLI on 18 June 2026. Provider allowances change, so check the current terms before depending on one.
- Can I use Claude Code alternatives with local models?
- Yes. OpenCode's docs describe local inference through Ollama, LM Studio and llama.cpp using OpenAI-compatible endpoints, and Aider and Goose can also connect to local models. Open Interpreter is tuned for low-cost open models. Results depend on the model and your hardware, so smaller local models handle less than the large hosted ones.
- How do terminal coding agents handle permissions and sandboxing?
- Each agent takes a different default. Claude Code asks before running most shell commands and editing files, Codex CLI defaults to a sandbox limited to the workspace with network access off, Gemini CLI offers an optional sandbox that is not on by default, and OpenCode uses allow, ask and deny rules that mostly default to allow. Read each agent's current docs and tighten the settings before pointing it at a real repository.
- Which is better, Codex CLI or Claude Code?
- They serve different vendors' ecosystems. Codex CLI is open source under Apache-2.0 and signs in with a ChatGPT plan or an API key, while Claude Code is closed source and comes with Claude subscriptions. Choose by the model and account you already pay for, how each handles approvals, and whether you want to read or modify the agent's code.











