An open-source coding agent with its own default provider that, per its provider docs, also takes a user's own keys, local models through Ollama, and gateways.
Our description, from the pages we read, as of 2026-10-20; 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.
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(kilo.ai page, read 2026-10-19) Settings the guide names: kilo.json, provider, models.
Use a local and a cloud model together: How to set it up(kilo.ai page, read 2026-10-19) Settings the guide names: kilo.json, provider/model, enabled_providers.
Hold several endpoints in the product: How to set it up(kilo.ai page, read 2026-10-19) Settings the guide names: kilo.json, enabled_providers, disabled_providers, provider/model.
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: 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: kilocode(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
Kilo Code allows local model execution via Ollama. (kilo.ai page, read 2026-10-20)
One sentence naming both a local and a cloud path
Based on their requirements, the customer may pick among cloud providers, local models, and AI gateways. (kilo.ai page, read 2026-10-20)
Models from different providers in one session
In Kilo Code, a custom agent's model setting can pin a specific model, written as provider/model, for example anthropic/claude-sonnet-4-20250514. (kilo.ai page, read 2026-10-21)
What a local model must meet
A context size of at least 32k is needed for decent results, though memory usage rises and performance may drop as context grows, depending on hardware. (kilo.ai page, read 2026-10-19)
Kilo Code's Ollama page says a reader needs a GPU with 24GB or more of VRAM, or a MacBook with 32GB or more of unified memory, to run its two named models, qwen3-coder:30b and devstral:24b, at decent speed. (kilo.ai page, read 2026-10-19)
Plan, policy and billing
Kilo Code's plans page names Teams and Enterprise as its paid plans for organizations. (kilo.ai page, read 2026-10-23)
Kilo Code's provider page says a new account can start straight away on free models, and credits can be topped up to get premium models. (kilo.ai page, read 2026-10-23)
Kilo Code's page on using it for free says free models are supported for coding work and background tasks. (kilo.ai page, read 2026-10-23)
Kilo Code's model access controls page says organization owners on the Enterprise plan can block chosen AI models or providers for every team member, and that other plans leave every model and provider open. (kilo.ai page, read 2026-10-23)
Kilo Code's model access controls page says a restriction set for the organization cannot be overridden by individual users. (kilo.ai page, read 2026-10-23)
Kilo Code's enterprise page says organization administrators can limit BYOK routes, data policies, models and providers across the organization while leaving approved developer workflows unblocked. (kilo.ai page, read 2026-10-23)
Kilo Code supports over 30 providers for users who need specific models or want their own API keys. (kilo.ai page, read 2026-10-19)
A separate model for planning and for doing
Kilo Code's model selection page says that for local usage the main model can be a direct provider key you bring yourself, or a local one served by Ollama or LM Studio. (kilo.ai page, read 2026-10-23)
Kilo Code's model selection page tells local users to set small_model explicitly, to a model from the same provider as their main model. (kilo.ai page, read 2026-10-23)
The task tool launches subagents using the Subagent model as the default. (kilo.ai page, read 2026-10-21)
About the product
Kilo Code's README describes Kilo Code as an open source coding agent that can be used inside VS Code or JetBrains, or from the command line. (github.com page, read 2026-10-24)
Kilo Code's README says Kilo can be run from the web at app.kilo.ai/cloud, with no local machine needed. (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