docs: jan desktop page

This commit is contained in:
0xSage 2024-02-13 14:50:29 +08:00
parent da4b865ea1
commit 63fde87084
13 changed files with 110 additions and 41 deletions

View File

@ -1,10 +0,0 @@
---
title: Jan's Vision for 2035
---
- [ ] https://hackmd.io/QIWyYbNNQVWVbupuI3kjAA
We only have 2 planning parameters:
- 10 year vision
- 2 week sprint
- Quarterly OKRs

12
docs/docs/about/2035.mdx Normal file
View File

@ -0,0 +1,12 @@
---
title: Jan's Vision for 2035
---
[Jan 2035: A Robotics Company](https://hackmd.io/QIWyYbNNQVWVbupuI3kjAA)
We only have 2 planning parameters:
- 10 year vision
- 2 week sprint
And we measure our success on Quarterly OKRs

View File

@ -1,7 +1,7 @@
---
title: About Jan
slug: /about
description: Jan is a productivity tool to customize AI to your needs and workflows.
description: Jan is a productivity tool to customize AI to your needs and workflows.
keywords:
[
Jan AI,
@ -15,21 +15,22 @@ keywords:
]
---
Jan is a [open-source](https://en.wikipedia.org/wiki/Open_source), [local-first](https://www.inkandswitch.com/local-first/) tool to [create, customize and use AI](https://www.gatesnotes.com/AI-agents) for everyday tasks.
Jan is a [open-source](https://en.wikipedia.org/wiki/Open_source), [local-first](https://www.inkandswitch.com/local-first/) tool to [create, customize and use AI](https://www.gatesnotes.com/AI-agents) for everyday tasks.
You can:
You can:
- Run locally using [open-source LLMs](https://huggingface.co/models?pipeline_tag=text-generation) or connect to cloud AIs like [ChatGPT](https://openai.com/blog/openai-api) or [Google](https://ai.google.dev/)
- Fine-tune AI with specific knowledge
- Search the web and other databases
- Connect AI to your everyday tools and (with your permission) do work on your behalf
Longer-term, Jan is building a cognitive framework for future robots. We envision a world where we have personal or company robots that we continually improve and customize, growing together with us.
Longer-term, Jan is building a cognitive framework for future robots. We envision a world where we have personal or company robots that we continually improve and customize, growing together with us.
![Human repairing a Droid](/img/star-wars-droids.png)
## Why do we exist
At Jan, our mission is to advance human-machine collaboration. We achieve this through delivering the best open-source, local-first tools to allow users to run, customize and tinker with AI.
At Jan, our mission is to advance human-machine collaboration. We achieve this through delivering the best open-source, local-first tools to allow users to run, customize and tinker with AI.
## What's different about it?
@ -38,32 +39,38 @@ At Jan, our mission is to advance human-machine collaboration. We achieve this t
| Ownership | AI Monopolies owned by Big Tech | AI that you own and control |
| Openness? | Closed-source | [Open-source (AGPLv3)](https://github.com/janhq/jan/blob/main/LICENSE) |
| Your role | Consume | Create, Tinker and Customize |
| Approach | Cloud | [Local-first](https://www.inkandswitch.com/local-first/), running 100% on your computer |
| Approach | Cloud | [Local-first](https://www.inkandswitch.com/local-first/), running 100% on your devices |
| Data | Data stored on their servers | Data stored in your local filesystem in open, non-proprietary file formats |
| Privacy | Privacy? | Runs 100% on your own machine, predictably, privately and offline |
| Privacy | 😂 | Runs 100% on your own machine, predictably, privately and offline |
| Transparency | "Black Box" | Runs predictability with code available to tinker and customize |
| What happens if there's an outage or goes out of business? | Your life's work held hostage in the cloud in proprietary data formats[^1] | Continues to run 100% on your computer, your data is safe in your local folder |
| Driving Philosophy | Monetize your users | [Privacy as a human right](https://en.wikipedia.org/wiki/Right_to_privacy) and the [Right to Repair](https://www.repair.org/) |
## How do I get it?
You can install and start using Jan in less than 5 minutes, from [jan.ai](https://jan.ai) or our [Github repo](https://github.com/janhq/jan).
You can install and start using Jan in less than 5 minutes, from [jan.ai](https://jan.ai) or our [Github repo](https://github.com/janhq/jan).
You can read the [User Guide](/docs/user-guide) if you need some help to get started.
You can read the [User Guide](/docs/user-guide) if you need some help to get started.
## What license is the code under?
Jan is licensed under the [AGPLv3 License](https://github.com/janhq/jan/blob/main/LICENSE).
Jan is licensed under the [AGPLv3 License](https://github.com/janhq/jan/blob/main/LICENSE).
We happily accept pull requests, however we do ask that you sign a [Contributor License Agreement](https://en.wikipedia.org/wiki/Contributor_License_Agreement) so that we have the right to relicense your contributions[^2].
We happily accept pull requests, however we do ask that you sign a [Contributor License Agreement](https://en.wikipedia.org/wiki/Contributor_License_Agreement) so that we have the right to relicense your contributions[^2].
We also have a [Contributor Program](/docs/team/contributor-program) to provide ownership and upside to contributors who have made significant contributions to the project.
## What was it built with?
Jan is pragmatically built using Javascript at the application level, and C++ at the Inference level (which we have refactored into [Nitro](https://nitro.jan.ai)). We use [Electron](https://www.electronjs.org/) to build the desktop client.
[Jan](https://github.com/janhq/jan) is pragmatically built using `Typescript` at the application level and `C++` at the Inference level (which we have refactored into [Nitro](https://nitro.jan.ai)[^3]).
We have made similar choices to the [Next.js Enterprise Javascript Stack](https://vercel.com/templates/next.js/nextjs-enterprise-boilerplate), which is a [battle-tested](https://nextjs.org/showcase/enterprise) framework for building enterprise-grade applications.
We use [Clean Architecture](https://blog.cleancoder.com/uncle-bob/2012/08/13/the-clean-architecture.html) and currently support a desktop client with [Electron](https://www.electronjs.org/), a headless server-mode with native [Nodejs](https://nodejs.org/en), and more.
From an architectural perspective, we have made similar choices to the [Next.js Enterprise Javascript Stack](https://vercel.com/templates/next.js/nextjs-enterprise-boilerplate), which is a [battle-tested](https://nextjs.org/showcase/enterprise) framework for building enterprise-grade applications that scale.
:::tip
At its core, Jan is a software development kit to build and run copilots, agents and assistants on personal devices. The desktop client that many folks use is just a small set of extensions we/the community have built on top.
:::
## Contact
@ -76,4 +83,5 @@ Drop us a message in our [Discord](https://discord.gg/af6SaTdzpx) and we'll get
## Footnotes
[^1]: Credit to Obsidian's original website
[^2]: Credit to [Discourse's About Page](https://www.discourse.org/about)
[^2]: Credit to [Discourse's About Page](https://www.discourse.org/about)
[^3]: Credit to [Llama.cpp](https://github.com/ggerganov/llama.cpp), [TensorRT-LLM](https://github.com/NVIDIA/TensorRT-LLM), [vLLM](https://github.com/vllm-project/vllm) and more.

View File

@ -2,5 +2,5 @@
title: Roadmap
---
- [ ] Link to Github Roadmap
- [ ] Longer-term Roadmap
- [ ] [Immediate Roadmap on Github](https://github.com/orgs/janhq/projects/5/views/16)
- [ ] [Longer-term Roadmap on Discord](https://discord.gg/Ey62mynnYr)

View File

@ -1,5 +1,5 @@
---
title: How We Work
title: How We Work
---
### Open Source
@ -16,9 +16,8 @@ We use GitHub to build in public and welcome anyone to join in.
- [Jan's Kanban](https://github.com/orgs/janhq/projects/5)
- [Jan's Roadmap](https://github.com/orgs/janhq/projects/5/views/29)
- [Jan's Newsletter](https://newsletter.jan.ai)
- `coming soon` [Jan's Newsletter](https://newsletter.jan.ai)
### Remote Team
Jan has a fully-remote team. We are mainly based in the APAC timezone. We use [Discord](https://discord.gg/af6SaTdzpx) and [Github](https://github.com/janhq) to work.

View File

@ -7,5 +7,5 @@ Adhering to Jan's privacy preserving philosophy, our analytics philosophy is to
#### What is tracked
1. By default, Github tracks downloads and device metadata for all public Github repos. This helps us troubleshoot & ensure cross platform support.
1. We use Posthog to track a single `app.opened` event without additional user metadata, in order to understand retention.
1. Additionally, we plan to enable a `Settings` feature for users to turn off all tracking.
1. We use [Umami](https://umami.is/), an analytics tool that ensures visitor privacy and data ownership, to track a single `app.opened` event. We do not get additional user metadata. This is done to understand retention.
1. Additionally, we plan to enable a `Settings` feature for users to turn off all tracking.

View File

@ -13,4 +13,73 @@ keywords:
no-subscription fee,
large language model,
]
---
---
# Turn Any Computer into an AI Computer
![Alt text](image.png)
<!-- TODO replace with GIF when we turn this page into a website -->
### Designed for Everyone
- **Installs with 1 click.** Jan is easy to use, beautiful, and the core features are free forever.
- **Runs on consumer laptops.** Tested by 250k+ users across `Windows, Mac, and Linux`, Jan even works on `CPU-only mode`.
- **Automatic GPU acceleration**. Models responds faster across `NVIDIA, AMD, Apple, and Intel` when benchmarked against industry alternatives.
:::tip
“Normies” can run LLMs like an AI engineer on the Desktop App - no programming experience needed.
:::
### Private & Offline
- **Runs 100% locally**. AI models run directly on your laptop without an internet connection. `You own your AI`.
- **Private conversations.** Data is saved on your own filesystem in a transparent non-proprietary data format. `You own your data.`
- **Open source security**. Jan is open source, so you can scruntinize every line in our codebase. So when we say your data is not our product, we mean it. See [the code](https://github.com/janhq/jan) and our [data policy](/how-we-work/analytics).
### Customizable AI
- **Use AI without limitations.** Take control of censorship levels. Jan is usable from the classroom to the boardroom (and few other rooms if thats your jam).
- **Use any models**. Download open source models from HuggingFace or upload your own custom models. [link]
:::tip
Download Jan Desktop Client [here](https://github.com/janhq/jan?tab=readme-ov-file#download).
:::
## Jan Desktop is
### For Developers
**You can easily integrate a locally running LLM into your own projects.**
- Turn on `Local API Server` mode to start building on an `OpenAI compatible API`.
- Jan Desktop comes with a Developer Console out of the box.
- The UI makes it easy to see logs, configure models and more.
![Alt text](image-1.png)
<!-- CTA ⇒ Developer Hub -->
### For Your Home Server
<!-- [Insert Screenshot of: Jan running in a Terminal (left) || the OpenAI configuration Yaml (right)] -->
- Use Jan as a UI only, pointing to a different backend. [See Docs](/guides/using-models/integrate-with-remote-server)
- Use Jan as a backend only, pointing to a different frontend. [See Docs](/guides/using-models/integrate-with-remote-server)
- Run Jan in team-mode on production-grade GPUs. [Pending Docs]
<!-- CTA ⇒ Server Docs -->
### For People who Tinker
- Customize the apps look and feel though Themes.
- Customize assistants, models and other features with **no code**.
- Customize the entire Application through Extensions. Inspired by VSCode extensions, the desktop app can be entirely customized. [docs] See the default extensions here.
![Alt text](image-2.png)
![Alt text](image-3.png)
![Alt text](image-4.png)

Binary file not shown.

After

Width:  |  Height:  |  Size: 429 KiB

Binary file not shown.

After

Width:  |  Height:  |  Size: 322 KiB

Binary file not shown.

After

Width:  |  Height:  |  Size: 102 KiB

Binary file not shown.

After

Width:  |  Height:  |  Size: 221 KiB

Binary file not shown.

After

Width:  |  Height:  |  Size: 217 KiB

View File

@ -48,15 +48,6 @@ const sidebars = {
],
},
"how-we-work/product-design/product-design",
{
type: "category",
label: "Engineering",
link: { type: "doc", id: "how-we-work/engineering/engineering" },
items: [
"how-we-work/engineering/ci-cd",
"how-we-work/engineering/qa",
],
},
"how-we-work/analytics/analytics",
"how-we-work/website-docs/website-docs",
],