# Alternatives to Claude Code > Source: https://theagentsindex.com/claude-code/alternatives (current datasheets, evidence-ranked) Candidates share the baseline category or are previously researched peers. Requirements, preserved strengths, explicit trade-offs and research coverage decide the order; paid tier does not. ## Shortlist ### 1. Cursor Coding agent in a desktop editor, terminal CLI, cloud VMs and CI, priced per seat plus token usage. **Research coverage:** 35/35 criteria **Where it improves on Claude Code:** - [GPT: yes — OpenAI models are available in the picker and priced per million tokens from the Other Models pool.](https://cursor.com/docs/integrations/jetbrains) - [Open models: partial — All inference is hosted: the catalogue includes GLM 5.2 from Z.ai and Kimi K3 from Moonshot, but there is no path to point Cursor at open weights you run.](https://cursor.com/docs/models-and-pricing) - [Model choice: yes — You pick the model per request, or hand selection to Auto/Cursor Router; each choice bills at that model's own rate.](https://cursor.com/docs/models-and-pricing) **Trade-offs against Claude Code:** - [MCP server: partial — MCP is inbound only: Cursor is the client that connects to MCP servers. Another agent drives Cursor over ACP (agent acp) or the SDKs, not by querying an MCP endpoint Cursor exposes.](https://cursor.com/docs/mcp) - [Admin controls: partial — Teams admins enforce Privacy Mode, team rules and sandbox mode; repository blocklists, model/MCP access controls and auto-run, browser and network controls are Enterprise-only.](https://cursor.com/pricing) - [Getting out: partial — Account deletion is self-serve and permanent with all data removed within 30 days, and your code stays local; included usage is not portable, resetting each billing cycle.](https://cursor.com/help/account-and-billing/delete-account) [View Cursor](https://theagentsindex.com/cursor) ### 2. Warp Agentic development environment: a terminal, a standalone agent CLI, and unattended cloud coding agents. **Research coverage:** 35/35 criteria **Where it improves on Claude Code:** - [GPT: yes — OpenAI models are listed in the vendor's own model table alongside Anthropic and Google; Codex is also supported as an alternative harness.](https://docs.warp.dev/agents/inference/model-choice/) - [Open models: yes — Open-weight models are hosted for you through Fireworks AI, and an Auto (Open-weights) router picks between them; Llama is absent from that enumerated table.](https://docs.warp.dev/agents/inference/model-choice/) - [Model choice: yes — You pick from the model picker or write your own routing rules; an admin or your plan can grey out models, and Auto hands selection back to Warp if you want it.](https://docs.warp.dev/agents/inference/model-choice/) **Trade-offs against Claude Code:** - [In your editor: no — There is no first-party IDE or editor extension; Warp ships its own editor and diff review and positions itself as the thing that replaces the external IDE. It can only launch your editor.](https://docs.warp.dev/code/overview/) - [MCP server: partial — Warp is a mature MCP client for local and cloud agents. Being queried by another agent works only through the hosted Factory MCP server, which is inside Warp Factories Early Access.](https://docs.warp.dev/factories/factory-mcp/) - [Admin controls: partial — Admins set org-wide autonomy per action type plus regex command allowlists and denylists, and can lock users out of overriding them. On Free most settings are fixed; configurability starts at Business and is complete on Enterprise.](https://docs.warp.dev/enterprise/team-management/admin-panel/) [View Warp](https://theagentsindex.com/warp) ### 3. Augment Code Cosmos platform running fleets of coding agents across the SDLC, plus Auggie CLI and IDE extensions. **Research coverage:** 35/35 criteria **Where it improves on Claude Code:** - [GPT: yes — GPT-5.1 through GPT-5.6 variants are selectable, and a GPT Prism router is offered.](https://docs.augmentcode.com/models/available-models) - [Open models: partial — Open-weight GLM and Kimi models are offered, but only Augment-hosted; the model list is closed and has no self-supplied weights.](https://docs.augmentcode.com/models/available-models) - [Model choice: yes — You pick the model per expert, session or message; Prism routing is an opt-in alternative.](https://docs.augmentcode.com/models/available-models) **Trade-offs against Claude Code:** - [API access: partial — Auggie TypeScript/Python SDKs drive the agent from your own code; the Analytics API is Enterprise-only preview.](https://docs.augmentcode.com/cli/sdk) - [Bring your own key: partial — You can supply your own machines or cloud for execution, but all inference is billed through Augment; no bring-your-own model key is documented.](https://docs.augmentcode.com/cosmos/environments/daemons) - [Opt out of training: partial — Paid plans exclude AI training on your data, but the Community terms grant Augment the right to train on Customer Code.](https://www.augmentcode.com/pricing) [View Augment Code](https://theagentsindex.com/augment-code) ### 4. Devin Cloud AI software engineer that takes a ticket, works in its own VM, and opens a pull request. **Research coverage:** 35/35 criteria **Where it improves on Claude Code:** - [GPT: yes — OpenAI models are selectable in Devin CLI, with gpt among the three the vendor recommends trying first.](https://docs.devin.ai/cli/models) - [Open models: yes — Open-weight models including DeepSeek, Kimi and GLM are selectable in Devin CLI.](https://docs.devin.ai/cli/models) - [Open source: partial — Only the Outposts Kubernetes orchestration operator is published as open source; no source distribution is documented for Devin itself.](https://docs.devin.ai/cloud/outposts/overview) **Trade-offs against Claude Code:** - [Bring your own key: partial — Your own AWS KMS key encrypts data at rest, but only on the Enterprise Assured deployment; no bring-your-own-inference is documented.](https://docs.devin.ai/enterprise/security-access/security/customer-managed-keys) - [Opt out of training: partial — Training is on by default and the opt-out is paid-plans-only; opting out also enables Zero Data Retention with the model providers.](https://docs.devin.ai/admin/security) - [Getting out: partial — Purchased on-demand credits roll over and never expire; no account-wide data export is documented beyond invoices and per-resource API reads.](https://docs.devin.ai/admin/billing/self-serve) [View Devin](https://theagentsindex.com/devin) ### 5. Junie JetBrains coding agent for the terminal, JetBrains IDEs and CI, running on hosted or your own model keys. **Research coverage:** 35/35 criteria **Where it improves on Claude Code:** - [GPT: yes — OpenAI models are reachable both through the JetBrains subscription's curated cloud set and by connecting your own OpenAI key directly, with built-in CLI aliases routing to them.](https://junie.jetbrains.com/docs/byok.html) - [Open models: yes — Open-weight models run two ways: through Ollama or LM Studio on any plan, or via the vendor's own Apple Silicon inference engine that ships a quantised Qwen model to your machine.](https://www.jetbrains.com/ai-ides/buy/) - [Model choice: yes — You choose, not the vendor: four provider classes are supported and a flag forces a specific one, though leaving the default lets JetBrains pick on price-quality grounds.](https://junie.jetbrains.com/docs/junie-cli-model-selection.html) **Trade-offs against Claude Code:** - [In a browser: partial — The web app is a companion view onto a CLI session still running on your own machine, not a standalone hosted agent, and the vendor lists a dozen features it cannot do.](https://junie.jetbrains.com/docs/junie-cli-remote-mode.html) - [MCP server: partial — MCP runs one way only: Junie consumes external MCP servers as a client. Another program reaches it through ACP instead, and no MCP server exposing Junie is documented.](https://junie.jetbrains.com/docs/junie-cli-acp.html) - [Admin controls: partial — A developer can constrain the agent locally through the allowlist file on any tier, but organisation-wide policy such as company MCP rules is an enterprise capability.](https://www.jetbrains.com/ide-services/ai-enterprise/) [View Junie](https://theagentsindex.com/junie) ### 6. Codex CLI OpenAI's terminal coding agent for inspecting, editing and running repository code from the shell. **Research coverage:** 35/35 criteria **Where it improves on Claude Code:** - [GPT: yes — GPT-5.6 Sol, Terra and Luna are all marked available in Codex CLI, selected with --model.](https://learn.chatgpt.com/docs/models) - [Open models: yes — --oss runs Codex against a local Ollama or LM Studio provider.](https://learn.chatgpt.com/docs/config-file/config-advanced) - [Open source: yes — CLI, SDK and app server are in openai/codex; the IDE extension and Codex cloud are not open source.](https://learn.chatgpt.com/docs/open-source) **Trade-offs against Claude Code:** - [Whole-codebase work: partial — Documented for repository-wide exploration and multi-step plans; the vendor states no repo-wide migration guarantee.](https://learn.chatgpt.com/docs/agent-configuration/subagents) - [Claude: no — Sign-in and model support are OpenAI models only; no Anthropic model appears in any documented model list.](https://learn.chatgpt.com/docs/auth) - [MCP server: partial — Codex is an MCP client for local and remote servers, but exposing Codex itself as an MCP server is deprecated in favour of the app server.](https://learn.chatgpt.com/docs/codex-sdk) [View Codex CLI](https://theagentsindex.com/codex-cli) ## Method Unknown data is never treated as a benefit or a trade-off. Featured placement is labelled but cannot alter recommendation order.