[ Learn ] # Is Jev open source? What is open and what is not Is Jev open source? No. Its weights are closed and used through TypeSafe's API, but its SDKs, agent skills and adapters are open source (MIT). Checked 28 October 2026. Published 28 October 2026By Jev Hub [Back to Learn](https://jevhub.io/learn) [ TLDR ] - No. - Jev's model is closed: TypeSafe has not published its weights, its size or its architecture, so you cannot download it, run it yourself, audit it or fine-tune it. - You use it through TypeSafe's API, or through gateways that resell that access. - The tools around it are different: TypeSafe's Python and JavaScript SDKs, its agent skills, its n8n node and its public examples are open source under the MIT licence. - If you need a model you can run on your own hardware, open decision models from AWS, Cloudflare and others exist. ## Jev, open and closed, at a glance | | Part of Jev | Open or closed | | --- | --- | --- | | The model (weights) | Closed | Not published. The Hugging Face accounts named TypeSafe AI list no models, and the GitHub organisation has no model repository | | Size and architecture | Not published | TypeSafe's launch post says only "a new model architecture" and a training method it calls RLCD, with no details | | How you use it | Through an API | TypeSafe's own API, or gateways such as OpenRouter and Vercel AI Gateway; the launch post calls access "early access" with a waitlist at launch | | Python and JavaScript SDKs | Open source, MIT | The GitHub repositories typesafe-sdk-python and typesafe-sdk-js; npm lists @typesafe-ai/sdk 0.7.0 under MIT | | Agent skills | Open source, MIT | The typesafe-ai/skills repository | | Other tools | Open source, MIT or Apache 2.0 | An n8n node, a Python adapter, workflow evaluation code and public examples, each in its own repository | | Self-hosting, auditing, fine-tuning | Not possible | There are no weights to run, inspect or train further | Checked on 28 October 2026 from TypeSafe's blog and documentation, the typesafe-ai organisation on GitHub (licences read from GitHub), npm and Hugging Face. We found no TypeSafe statement either way about releasing weights later. The Hugging Face accounts named TypeSafe AI are unverified, so we cannot confirm they are official. ## Is Jev open source? No, not the model. Jev is closed: TypeSafe, the company that makes it, has not published its weights (the learned numbers that make up the model), its size or its architecture. You cannot download Jev, run it on your own computer, look inside it or train it further. You use it through TypeSafe's API, and a few gateways resell that same access. What is open is the tooling around it. TypeSafe publishes its Python and JavaScript SDKs, its agent skills, an n8n node and some examples as open source, under the MIT licence. They help you call Jev; none of them contains Jev. What is closed and what is open. From TypeSafe's blog and documentation and the typesafe-ai organisation on GitHub, checked 28 October 2026. - [What is Jev?](https://jevhub.io/what-is-jev) - [Jev API access: five ways to call it](https://jevhub.io/jev-api-access) ## How do we know the weights are not public? TypeSafe's own pages say nothing about weights or a licence. Its launch post describes "a new model architecture" and a training method it calls RLCD without detail, and its documentation says only that Jev is not trained to generate text. We then checked where weights would be published, on 28 October 2026: - **GitHub.** TypeSafe's organisation has repositories for SDKs, skills, an adapter, an n8n node, evaluation code and examples, but no repository for the model. - **Hugging Face.** Two accounts are named TypeSafe AI (typesafeAI and typesafe). Neither is marked verified, so we cannot confirm they are official, and both list no models. A search for "jev" returns models made by other people in Jev's style. - **What this does not prove.** It is a check for something missing, not a statement from TypeSafe. The company has not said whether it will ever open the model; its launch post says only "we have a lot more in the pipeline". ## What is open, and what does it let you do? Several things TypeSafe publishes are open source, each under its own licence in its own repository: - **SDKs (MIT).** The Python and JavaScript libraries that send requests to Jev. You can read and change them, but they still need a TypeSafe or gateway key to get an answer. - **Agent skills (MIT).** The files that teach coding agents such as Claude Code and Codex to write programs that call Jev. - **An n8n node, an adapter and examples (MIT).** Ready-made pieces for automations and small projects. - **Workflow evaluation code (Apache 2.0).** A repository named WorkflowEvals. - [Jev in Claude Code, Codex, OpenCode and Cursor](https://jevhub.io/jev-claude-code) ## What does closed mean for you? Because Jev is closed, four things follow: - **Your text goes to someone else's servers.** Every request is sent to TypeSafe's API or to the gateway you use. You cannot keep the data inside your own network. - **You cannot inspect or change the model.** If Jev gets something wrong, you can change your questions and thresholds, but not the model. - **You depend on one company's prices and rules.** TypeSafe's models page lists $0.042 per million input tokens with free output today, and prices can change. - **You can pin a version.** Sending a version ID such as jev-1.14.0 instead of the alias jev-latest keeps answers from changing when a new release ships. - [Jev pricing](https://jevhub.io/economics) - [Can you use Jev for free?](https://jevhub.io/is-jev-free) ## What are the open alternatives? If you need a model you can run yourself, several open decision models do a similar job. The three below are compared with Jev in full on this site. They differ in size, speed and accuracy, and the numbers in those comparisons are each company's own unless an article says otherwise. Open models that do a similar job. From this site's comparison articles. Each is compared with Jev in full there. - [Jev vs open models: can you skip Jev?](https://jevhub.io/jev-vs-open-decision-models) - [Jev vs Laya: pay per call or run it yourself?](https://jevhub.io/jev-vs-laya) ## Which should you choose? Based on what is published today: - **Use Jev** if you want a hosted service with public pricing, no hardware to run and the tooling above. - **Use an open model** if the data must stay on your own machines, you need to inspect or fine-tune the model, or you want a fixed cost on hardware you own. - **Test both on your own data** before you decide: run the same labelled sample through each and compare accuracy, speed and total cost. ## Common questions No. Jev's weights, size and architecture are not published, and it is used through TypeSafe's API. The SDKs, agent skills and other tools around it are open source under the MIT licence. No. There are no weights to download, so you cannot run Jev on your own hardware. You call it through TypeSafe's API or a gateway. Yes. TypeSafe's Python and JavaScript SDKs are MIT-licensed on GitHub, and npm lists @typesafe-ai/sdk 0.7.0 under MIT. They need an API key to get answers from Jev. No. On 28 October 2026 the Hugging Face accounts named TypeSafe AI listed no models. Models there with Jev in the name were made by other people in Jev's style. Yes. AWS's Strands Decider, Cloudflare's Clef models and Laya are open and can be run on your own hardware. They are compared with Jev on this site. TypeSafe has not said. Its launch post says only that it has "a lot more in the pipeline". ## Sources Written by Jev Hub from the sources below and checked against them on 28 October 2026. Where a figure is a company's own claim, the article says so. - [TypeSafe blog: Introducing System One Models & Jev (read 28 October 2026)](https://typesafe.ai/blog/introducing-system-one-models-and-jev) - [GitHub: the typesafe-ai organisation, its repositories and licences (checked 28 October 2026)](https://github.com/typesafe-ai) - [GitHub: typesafe-ai/skills (MIT licence, checked 28 October 2026)](https://github.com/typesafe-ai/skills) - [npm: @typesafe-ai/sdk (MIT licence, version 0.7.0, checked 28 October 2026)](https://www.npmjs.com/package/@typesafe-ai/sdk) - [TypeSafe docs: models and limits (read 28 October 2026)](https://docs.typesafe.ai/models) - [Hugging Face: models matching "jev" (searched 28 October 2026)](https://huggingface.co/models?search=jev) ## Related content - [What is Jev?](https://jevhub.io/what-is-jev) - [How to use Jev](https://jevhub.io/how-to-use-jev) - [Jev pricing](https://jevhub.io/economics)