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.
Models runWhere the vendor's own pages say the product's models run, not a limit: your machine, a container environment you run, the model company's cloud (servers of the company that makes or serves the model), or a cloud provider's model service. For a cloud, read the data and compliance lines of the company running it, linked by its name.
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.
Several endpoints built inThe tool itself can hold more than one provider or address, so nothing has to sit in front of it to reach different providers.
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.
Use a local model: How to set it up(goose-docs.ai page, read 2026-10-19) Settings the guide names: OLLAMA_HOST.
Use a local and a cloud model together: How to set it up(goose-docs.ai page, read 2026-10-21) Settings the guide names: /model.
Hold several endpoints in the product: How to set it up(goose-docs.ai page, read 2026-10-19) Settings the guide names: OPENAI_HOST, OPENAI_BASE_PATH, OPENAI_API_KEY.
Requirements the pages state
ChatGPT Plus or Pro for its Codex provider (goose-docs.ai page, read 2026-10-19)
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.
Our reading, beyond the maker's pages
Each item below is our own view of how the product compares or groups with other products in the catalog, or of a limit worth knowing about. It goes beyond what the maker's pages cited here say; no maker has said it or reviewed it, and it cannot be confirmed on a vendor's page. A second AI model read each item on 2026-10-25. Terms
It is comparable to Cline: the catalog lists both as harness or agent clients in the coding agents and assistants layer. (as of 2026-09-26)
Data and compliance
Compliance: Set by whoever runs itThe answer belongs to whoever runs the software, because open-source software has no maker running it for you., for their own deployment.
Data: Set by whoever runs itThe answer belongs to whoever runs the software, because open-source software has no maker running it for you., with telemetry not checked yetWe have not read a page of the right kind for this question yet..
Model and where it runs: Run by its operator.
Details: What the project's own pages state, not a compliance determination.
What the maker's own pages said on the dates shown, not a compliance determination.
GitHub page: goose(the product's own site, from our list of products; not read for these lines)
The readings behind this page
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 models
goose's provider table lists Ollama as a local runner for open-source models; a model must be downloaded and running first. (goose-docs.ai page, read 2026-10-19)
In goose Desktop, models already installed locally for Ollama appear in the model dropdown. (goose-docs.ai page, read 2026-10-19)
Local and cloud models in one session
goose's multi-model page says the /model command changes models without ending the session, either staying with the current provider or moving to another. (goose-docs.ai page, read 2026-10-19)
What you set up
goose Desktop lists providers with a Configure button each, and a provider that is not listed can be added as a custom provider. (goose-docs.ai page, read 2026-10-19)
Models from different providers in one session
Focused tasks are delegated to isolated goose instances, and each can run a provider and model of its own. (goose-docs.ai page, read 2026-10-21)
What a local model must meet
goose's Qwen 3 blog post says the model, even in a compact form of 8B parameters at 4-bit quantization, was able to call tools with goose. (goose-docs.ai page, read 2026-10-23)
goose's blog post on running it with Ollama calls RAM the key requirement, with 32GB a sound starting point for bigger models and outputs. (goose-docs.ai page, read 2026-10-23)
goose's blog post on running it with Ollama says that on Windows and Linux, GPU memory matters more for acceleration. (goose-docs.ai page, read 2026-10-23)
Plan, policy and billing
goose's providers page says its ChatGPT Codex provider requires a ChatGPT Plus or Pro subscription. (goose-docs.ai page, read 2026-10-19)
OpenAI's Sign in with ChatGPT page on ChatGPT Learn lists partner apps that use a ChatGPT plan, among them Amp Code, Devin, Kilo Code, Notion, Vercel and Warp, apps that offer sign-in only, and four open-source integrations, namely OpenClaw, OpenCode, Pi and T3; none of its lists names goose. (learn.chatgpt.com page, read 2026-10-23)
OpenAI's help article on using a ChatGPT plan in other apps says OpenAI has begun with a limited number of partners, sends open-source developers to its developer documentation and asks commercial partners to use an interest form. (help.openai.com page, read 2026-10-23)
OpenAI's Sign in with ChatGPT developer overview says an open-source app can ask a person for permission to draw on their ChatGPT plan for eligible API requests, that its docs cover apps that are open source or hosted locally, and that an app that is paid or hosted remotely should apply through an interest form. (developers.openai.com page, read 2026-10-23)
OpenAI's Sign in with ChatGPT Terms say an app may use a person's ChatGPT plan only for the app that person connected, may not hand out general API access to other tools, and must let people use their plan through it without paying the app. (openai.com page, read 2026-10-23)
goose's providers page says its GCP Vertex AI entry limits the models that can be chosen according to an organization policy, where one has been set. (goose-docs.ai page, read 2026-10-19)
A separate model for planning and for doing
goose's page on using multiple models describes subagents as isolated goose instances to which focused tasks are delegated, each able to use a provider and model of its own. (goose-docs.ai page, read 2026-10-21)
GOOSE_SUBAGENT_MODEL and GOOSE_SUBAGENT_PROVIDER define the subagent model and provider defaults, with recipe settings taking precedence over both. (goose-docs.ai page, read 2026-10-21)
Works with other products
LM Studio allows local execution of open-source models via an OpenAI-compatible API server. (goose-docs.ai page, read 2026-10-19)
About the product
goose's README describes goose as an all-purpose AI agent running on the user's own machine. (github.com page, read 2026-10-24)
goose's providers page says the OpenAI provider also takes OpenAI-compatible endpoints, with self-hosted LLaMA, vLLM and KServe given as examples. (goose-docs.ai page, read 2026-10-24)
goose's providers page lists an OpenAI provider offering gpt-4o and o1, among other advanced language models. (goose-docs.ai 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