diff --git a/README.md b/README.md
index ef4efa032..a8dd3fe30 100644
--- a/README.md
+++ b/README.md
@@ -20,63 +20,62 @@
> ⚠️ **Jan is currently in Development**: Expect breaking changes and bugs!
-Jan lets you run AI on your own hardware, with helpful tools to manage models and monitor your hardware performance.
+Use offline LLMs with your own data. Run open source models like Llama2 or Falcon on your internal computers/servers.
-In the background, Jan runs [Nitro](https://nitro.jan.ai), a C++ inference engine. It runs various model formats (GGUF/TensorRT) on various hardware (Mac M1/M2/Intel, Windows, Linux, and datacenter-grade Nvidia GPUs) with optional GPU acceleration.
+Jan runs on any hardware, from PCs to multi-GPU clusters. Jan supports both CPU and GPU on the following architecture:
-> See the Nitro codebase at https://nitro.jan.ai.
+- [x] Nvidia GPUs (fast)
+- [x] Apple M-series (fast)
+- [x] Apple Intel
+- [x] Linux Debian
+- [x] Windows x64
-
-
+> Download Jan at https://jan.ai/
## Demo
-
+
+_Screenshot: Jan v0.1.3 on Mac M1 Pro, 16GB Sonoma_
+
## Quicklinks
-- Developer documentation: https://jan.ai/docs (Work in Progress)
-- Desktop app: Download at https://jan.ai/
-- Mobile app shell: Download via [App Store](https://apps.apple.com/us/app/jan-on-device-ai-cloud-ais/id6449664703) | [Android](https://play.google.com/store/apps/details?id=com.jan.ai)
-- Nitro (C++ AI Engine): https://nitro.jan.ai
+- [Developer docs](https://jan.ai/docs) (WIP)
+- Mobile App shell: [App Store](https://apps.apple.com/us/app/jan-on-device-ai-cloud-ais/id6449664703) | [Android](https://play.google.com/store/apps/details?id=com.jan.ai)
+- [Nitro Github](https://nitro.jan.ai): Jan's AI engine
## Plugins
Jan supports core & 3rd party extensions:
- [x] **LLM chat**: Self-hosted Llama2 and LLMs
-- [x] **Model Manager**: 1-click to install, swap, and delete models
-- [x] **Storage**: Optionally store your conversation history and other data in SQLite/your storage of choice
+- [x] **Model Manager**: 1-click to install, swap, and delete models with HuggingFace integration
+- [x] **Storage**: Optionally save conversation history and other data in SQLite
- [ ] **3rd-party AIs**: Connect to ChatGPT, Claude via API Key (in progress)
- [ ] **Cross device support**: Mobile & Web support for custom shared servers (in progress)
-- [ ] **File retrieval**: User can upload private and run a vectorDB (planned)
+- [ ] **File retrieval**: User can chat with docs
- [ ] **Multi-user support**: Share a single server across a team/friends (planned)
- [ ] **Compliance**: Auditing and flagging features (planned)
-## Hardware Support
+## Nitro (Jan's AI egine)
-Nitro provides both CPU and GPU support, via [llama.cpp](https://github.com/ggerganov/llama.cpp) and [TensorRT](https://github.com/NVIDIA/TensorRT), respectively.
+In the background, Jan runs [Nitro](https://nitro.jan.ai), an open source, C++ inference engine. It runs various model formats (GGUF/TensorRT) on various hardware (Mac M1/M2/Intel, Windows, Linux, and datacenter-grade Nvidia GPUs) with optional GPU acceleration.
-- [x] Nvidia GPUs (accelerated)
-- [x] Apple M-series (accelerated)
-- [x] Linux DEB
-- [x] Windows x64
-
-Not supported yet: Apple Intel, Linux RPM, Windows x86|ARM64, AMD ROCm
-
-> See [developer docs](https://docs.jan.ai/docs/) for detailed installation instructions.
+> See the open source Nitro codebase at https://nitro.jan.ai.
## Contributing
Contributions are welcome! Please read the [CONTRIBUTING.md](CONTRIBUTING.md) file
### Pre-requisites
+
- node >= 20.0.0
- yarn >= 1.22.0
### Use as complete suite (in progress)
+
### For interactive development
Note: This instruction is tested on MacOS only.
@@ -98,28 +97,29 @@ Note: This instruction is tested on MacOS only.
yarn build:plugins
```
-4. **Run development and Using Jan Desktop**
+3. **Run development and Using Jan Desktop**
```
yarn dev
```
+
This will start the development server and open the desktop app.
In this step, there are a few notification about installing base plugin, just click `OK` and `Next` to continue.
### For production build
- ```bash
- # Do step 1 and 2 in previous section
- git clone https://github.com/janhq/jan
- cd jan
- yarn install
- yarn build:plugins
+```bash
+# Do step 1 and 2 in previous section
+git clone https://github.com/janhq/jan
+cd jan
+yarn install
+yarn build:plugins
- # Build the app
- yarn build
- ```
+# Build the app
+yarn build
+```
- This will build the app MacOS m1/m2 for production (with code signing already done) and put the result in `dist` folder.
+This will build the app MacOS m1/m2 for production (with code signing already done) and put the result in `dist` folder.
## License