An open-source coding agent that plans and executes multi-step changes using terminal, browser, and code-editing tools, available for local or self-hosted deployment.
Our description, from the project's GitHub description and the maintainer's own site, as of 2026-09-24.
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(docs.openhands.dev page, read 2026-10-22) Settings the guide names: LLM_BASE_URL, LLM_MODEL, LLM_API_KEY, --served-model-name.
Use a local and a cloud model together: How to set it up(docs.openhands.dev page, read 2026-10-22) Settings the guide names: /model, SwitchLLMTool, switch_llm.
Hold several endpoints in the product: How to set it up(docs.openhands.dev page, read 2026-10-22) Settings the guide names: /model, litellm_proxy/, local-llm.
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: For OpenHands Cloud, none marked from the pages read; the software itself, 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: For OpenHands Cloud, training use and default retention stated for the whole companyThe only sentence found is about the maker as a whole and names no product, so check on the page whether it covers this one.; zero-retention option not checked yetWe have not read a page of the right kind for this question yet.; data residency not stated on the pages readWe read a page that could answer and found no sentence that does. It says nothing about what the maker does.; the software itself, 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, or hosted by the maker as OpenHands Cloud; for OpenHands Cloud, model provider stated for the whole companyThe only sentence found is about the maker as a whole and names no product, so check on the page whether it covers this one.; 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 2026-12-29.
What the maker's own pages said on the dates shown, not a compliance determination.
GitHub page: OpenHands(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
OpenHands's LLM page names SGLang, vLLM, LM Studio and Ollama as examples of local model servers. (docs.openhands.dev page, read 2026-10-20)
Cloud models
OpenHands's LLM overview page has, after a short introduction, a table of access options under the heading Choose a Model Configuration Path; its first row, under the column I have, lists a key issued by a model provider or by OpenHands. (docs.openhands.dev page, read 2026-10-20)
One sentence naming both a local and a cloud path
OpenHands executes both proprietary and open-weight models, including Kimi, DeepSeek, and Qwen, across local, cloud, or VPC environments. (www.openhands.dev page, read 2026-10-20)
Models from different providers in one session
OpenHands' LLM settings page says LLM profiles suit using different models for different tasks, such as a faster model for simple work and a more powerful one for complex reasoning. (docs.openhands.dev page, read 2026-10-23)
OpenHands' SDK model routing page describes a built-in MultimodalRouter that sends requests that hold only text to a secondary LLM, and image-bearing requests to the primary LLM. (docs.openhands.dev page, read 2026-10-23)
Several endpoints, built in (no proxy)
OpenHands allows saved LLM profiles to simplify model switching, so provider settings need not be re-entered each time. (docs.openhands.dev page, read 2026-10-21)
OpenHands' LLM profiles page says Provider Connections let several profiles share one stored provider, key and optional base URL, each profile keeping its own model; the page limits them to local agent-server backends and hides the panel on OpenHands Cloud. (docs.openhands.dev page, read 2026-10-21)
Local and cloud in one session
OpenHands' LLM settings page says its LLM profiles let a user hold several LLM configurations and swap between them, even while a conversation is active. (docs.openhands.dev page, read 2026-10-21)
What a local model must meet
OpenHands' local model guide says running Qwen3.6-35B-A3B takes a recent GPU with 24GB or more of VRAM when running quantized variants, or several GPUs when you want full precision or bigger context windows. (docs.openhands.dev page, read 2026-10-23)
OpenHands' local model guide names a Mac with Apple Silicon and 64GB or more of unified memory as another way to meet its stated hardware need for quantized variants of Qwen3.6-35B-A3B. (docs.openhands.dev page, read 2026-10-23)
Tool-use reliability varies widely for open-weight models and local models. (docs.openhands.dev page, read 2026-10-19)
Plan, policy and billing
OpenHands' organization settings page says all members use the organization's LLM configuration unless they have set personal overrides. (docs.openhands.dev page, read 2026-10-23)
OpenHands' LLM page has an 'I have / Start here' table whose first row sends a reader who holds a key issued by a model provider, or by OpenHands itself, to the page on configuring a model in Agent Canvas. (docs.openhands.dev page, read 2026-10-19)
A separate model for planning and for doing
OpenHands' model recommendations advise using cheaper profiles for routine edits and then returning to a stronger model when planning, debugging or reviewing. (docs.openhands.dev page, read 2026-10-19)
About the product
OpenHands' README says OpenHands runs on the user's machine by default and can connect to agent backends such as Docker containers, virtual machines or a company's own infrastructure, and that agents can optionally run on OpenHands Cloud, or on the infrastructure of OpenHands Enterprise. (github.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