A coding agent from Anthropic, run in a terminal or an editor, that holds the conversation, chooses which tools to call, runs commands and manages its own context until the work is done or it stops to ask.
Our description, from the vendor's documentation, as of 2026-09-03; reasoned from those pages, not observed running.
Runs onThe places the vendor's own pages say the product runs: your machine, a container environment you run, or a cloud service the vendor runs. It is not a limit.
Several providers in one sessionOne session can use models from different providers, for example one agent on one maker's model and another on a second maker's. Switching the single model for the whole session does not count on its own. A tool that is itself a gateway or library routing to the providers its page names counts.
Local and cloud togetherA local model (on your machine or in a container environment you run) and a cloud model (in its model company's cloud or a cloud provider's model service) can both be used in the same session or setup.
oMLX: oMLX lists POST /v1/messages, the Anthropic Messages API (github.com)
llama.cpp server: llama.cpp server has a /v1/messages endpoint; the README does not strongly claim Anthropic compatibility and does not name Claude Code in the sentence (github.com)
LiteLLM: runs Claude Code on any model through its Python SDK (github.com)
Compared with similar tools
Same role (harness / agent client) at the same layer (Coding agents and assistants). Up to 4 others, in alphabetical order; nothing is ranked.
Product
Several providersOne session can use models from different providers, for example one agent on one maker's model and another on a second maker's. Switching the single model for the whole session does not count on its own. A tool that is itself a gateway or library routing to the providers its page names counts.
Several endpointsThe tool itself can hold more than one provider or address, so nothing has to sit in front of it to reach different providers.
Model on your machineThe tool can use a model running on your own computer, for example through Ollama, LM Studio, oMLX or llama.cpp.
Local and cloudA local model (on your machine or in a container environment you run) and a cloud model (in its model company's cloud or a cloud provider's model service) can both be used in the same session or setup.
Words in the cells: YesA page we read says so., PartlyA page says part of it, for example separate models per agent without saying the providers can differ., Via a proxyOnly with a proxy, or a local server that imitates a cloud provider's interface, in front of the tool., NoA page we read says the product does not support it., ClaimedA vendor page says so on a marketing or overview page, and we found no guide showing how to set it up., Not foundWe read pages for it and found nothing there. It says nothing about whether the product has the feature., n/aThe question does not apply to the product, for example because it is a model server and not a tool that connects to models., BlankNothing is published for it yet.
Data and compliance
Compliance: SOC 2 Type II (company-wideThe mark rests on a sentence that names no product, so check on the page whether it covers this one.); ISO/IEC 27001:2022 (company-wideThe mark rests on a sentence that names no product, so check on the page whether it covers this one.); ISO/IEC 42001:2023 (company-wideThe mark rests on a sentence that names no product, so check on the page whether it covers this one.); HIPAA BAA (Enterprise; under a conditionThe mark holds only under a setting or an agreement the line names.); DPA (company-wideThe mark rests on a sentence that names no product, so check on the page whether it covers this one.).
Data: Training use and default retention only on some plans or optionsNothing found covers the product as a whole; what was found holds only for the plans, options or regions named. (Commercial, Enterprise, Consumer); zero-retention option only on some plans or optionsNothing found covers the product as a whole; what was found holds only for the plans, options or regions named. (Commercial, Enterprise); data residency only on some plans or optionsNothing found covers the product as a whole; what was found holds only for the plans, options or regions named. (Hosted on Anthropic, Hosted on Azure).
Model and where it runs: Installed: a terminal harness; model provider and where it can run stated on the maker's pageA sentence on the maker's page answers it for this product..
Details: What the maker's own pages state, not a compliance determination, unverified after 2026-12-23: trust page, trust.anthropic.com.
What the maker's own pages said on the dates shown, not a compliance determination.
Also covers
The vendor's own pages present these as parts or modes of this product, so each is described here and has no page of its own.
Claude Code plugin marketplaces
A feature of Claude Code: a marketplace is a marketplace.json catalog, kept in a git repository or a local path, that lists plugins (skills, agents, hooks, MCP servers, LSP servers) for a team or a community to install from.
Our description, from the vendor's documentation, as of 2026-09-29.
Compliance: For Claude Code, SOC 2 Type II (company-wideThe mark rests on a sentence that names no product, so check on the page whether it covers this one.); ISO/IEC 27001:2022 (company-wideThe mark rests on a sentence that names no product, so check on the page whether it covers this one.); ISO/IEC 42001:2023 (company-wideThe mark rests on a sentence that names no product, so check on the page whether it covers this one.); HIPAA BAA (Enterprise; under a conditionThe mark holds only under a setting or an agreement the line names.); DPA (company-wideThe mark rests on a sentence that names no product, so check on the page whether it covers this one.).
Data: For Claude Code, training use and default retention only on some plans or optionsNothing found covers the product as a whole; what was found holds only for the plans, options or regions named. (Commercial, Enterprise, Consumer); zero-retention option only on some plans or optionsNothing found covers the product as a whole; what was found holds only for the plans, options or regions named. (Commercial, Enterprise); data residency only on some plans or optionsNothing found covers the product as a whole; what was found holds only for the plans, options or regions named. (Hosted on Anthropic, Hosted on Azure).
Model and where it runs: Hosted by the maker; for Claude Code, model provider and where it can run stated on the maker's pageA sentence on the maker's page answers it for this product..
Details: What the maker's own pages state, not a compliance determination, unverified after 2026-12-23: trust page, trust.anthropic.com.
What the maker's own pages said on the dates shown, not a compliance determination.
Our summary of the vendor's pages as of the dates shown on each line (2026-10-19 to 2026-10-24); confirm on the vendor's page.
Local and cloud models in one session
When model discovery is active, Claude Code contacts the gateway to retrieve available model names at startup, then lists them in the /model picker next to the built-in options. (code.claude.com page, read 2026-10-19)
What you set up
On Claude Code's gateway connection page, the gateway address and the credential variable chosen in an earlier step are both supplied through environment variables. (code.claude.com page, read 2026-10-19)
Models from different providers in one session
Claude Code's subagents page says a subagent's model field can be set to an alias, one of sonnet, opus, haiku or fable. (code.claude.com page, read 2026-10-21)
Plan or account
Claude Code's legal and compliance page says OAuth authentication is intended only for people who bought a Claude plan, whether Free, Pro, Max, Team or Enterprise, and is designed to cover everyday use of Claude Code and Anthropic's other native applications. (code.claude.com page, read 2026-10-21)
Anthropic's support article says that when an ANTHROPIC_API_KEY environment variable is set on the machine, Claude Code authenticates with that key rather than with a Pro, Max, Team or Enterprise subscription, so usage is billed as API usage instead of drawing on what the subscription includes. (support.claude.com page, read 2026-10-21)
Claude Code with a local server
The gateway page names ANTHROPIC_BASE_URL as the setting that sends Claude Code's requests to a gateway. (code.claude.com page, read 2026-10-21)
The Claude Code gateway page says Anthropic provides no support when a gateway sends Claude Code's requests to models that are not Claude, whichever gateway it is, and that Anthropic neither endorses, maintains nor audits gateway products made by others. (code.claude.com page, read 2026-10-21)
Plan, policy and billing
Claude Code's page on connecting to a gateway says a user who relies on the built-in models does not need gateway model discovery, and that an administrator may already have enabled it through managed settings. (code.claude.com page, read 2026-10-19)
A separate model for planning and for doing
Claude Code's model configuration page says that with the opusplan alias, opus is used while in plan mode, for difficult reasoning and architectural decisions. (code.claude.com page, read 2026-10-19)
About the product
Claude Code's overview page names four surfaces it runs on: a terminal, IDE extensions, a desktop application and a web version. (code.claude.com page, read 2026-10-24)
Claude Code's overview page says its scheduled tasks created as cloud tasks run in the cloud and keep going when the user's computer is off. (code.claude.com page, read 2026-10-24)
Our reading of vendors' pages, as of the dates shown. Confirm on the vendor's page before relying on any line that cites it. To report an error write to report@crinaro.ai