llocal

llocal

Aiming to provide a seamless and privacy driven chatting experience with open-sourced technologies(Ollama), particularly open sourced LLM's(eg. Llama3, Phi-3, Mistral). Focused on ease of use. Available on both Windows and Mac.

Stars: 58

Visit
 screenshot

LLocal is an Electron application focused on providing a seamless and privacy-driven chatting experience using open-sourced technologies, particularly open-sourced LLM's. It allows users to store chats locally, switch between models, pull new models, upload images, perform web searches, and render responses as markdown. The tool also offers multiple themes, seamless integration with Ollama, and upcoming features like chat with images, web search improvements, retrieval augmented generation, multiple PDF chat, text to speech models, community wallpapers, lofi music, speech to text, and more. LLocal's builds are currently unsigned, requiring manual builds or using the universal build for stability.

README:

llocal-banner

LLocal

Aiming to provide a seamless and privacy driven chatting experience with open-sourced technologies(Ollama), particularly open sourced LLM's(eg. Llama3, Phi-3, Mistral). Focused on ease of use.
LLocal can be installed on Windows, Mac and Linux.

Demo

llocal-demo

What can LLocal do?

  • Llocaly store chats.
  • Llocal utilizes Ollama which ensures that from processing to utilizing everything happens on your machine LLocally.
  • Seamlessly switch between models.
  • Easily pull new models.
  • Image upload for models that support vision.
  • Web search (i.e Website scraper aswell as duckduckgo search inbuilt) for all models.
  • Responses are rendered as markdown (Supporting Code Blocks with syntax highlighting, tabular formats and much more).
  • Multiple themes (5 themes all suporting both light and dark mode)
  • Seamless integration with Ollama, from download to install.

What's ahead?

  • Chat with images ✅
  • Web Search ☑️ (purple because, it still can be improved)
  • Retrieval Augmented Generation/RAG (with single PDF's)
  • Multiple PDF chat
  • Text to Speech Models (only if we can get to be similar to a human like response).
  • Community wallpapers
  • Community themes (something like what spicetify does)
  • Lofi Music (this would be optional)
  • Speech to text (Do we really need it?)
  • Conversations like those with ChatGPT (Speech to text input and text to speech output, but the aim would be low-latency).
  • Chat with chats ?! (Not sure)

At some point: would want to pivot LLocal in a different direction... (Although would need to discuss this with the users.)

Important Note

LLocal's builds are unsigned at the moment, meaning there will be an unknown publisher alert on Windows and Mac. But, on mac it does not open because the code is unsigned and to solve this issue you can do either of the following:

  1. Running a manual build by cloning the repo and then running the npm run build:mac:arm for m series or npm run build:mac:intel for intel based macs. When you build it on your own, that time apple does not throw the error. I know this is inconvenient but the build does take at max a few minutes.

  2. Incase, you don't want to build it by yourself then you can also try the Universal build that seems to be more stable than the separate builds, but then you'd get the developer is not verified error which can be by passed by following this video .

The link to the mac universal build is this.

Project Setup

LLocal is an Electron application with React and TypeScript.

Recommended IDE Setup (You do you, honestly)

Installation

Install dependencies

$ npm install

Development

$ npm run dev

Build

# For windows
$ npm run build:win

# For macOS (m-series)
$ npm run build:mac:arm

# For macOS (intel-chips)
$ npm run build:mac:intel

# For Linux (Supported now!)
$ npm run build:linux

How to contribute?

You can refer to the Contribute.md

For Tasks:

Click tags to check more tools for each tasks

For Jobs:

Alternative AI tools for llocal

Similar Open Source Tools

For similar tasks

For similar jobs