AI Agnostic (Multi-user and Multi-bot) Chat with Fictional Characters. Designed with scale in mind.
782
stars
1,389
commits
TypeScript
primary language
Jun 15, 2026
updated
AI Roleplay Chat with Personalized Characters using your favorite AI services.
Visit the live version at Agnai.chat.
Based on the early work of Galatea-UI by PygmalionAI.
Important! MongoDB and Redis are optional! Agnaistic will run in "Guest Only" mode if MongoDB is not available.
Agnaistic is published as an NPM package and can be installed globally:
# Install or update:
npm install agnai -g
agnai
# View launch options:
agnai help
# Run with the Pipeline features
agnai --pipeline
When using the NPM package, your images and JSON files will be stored in: HOME_FOLDER/.agnai.
Examples:
Linux: /home/sceuick/.agnai/
Mac: /Users/sceuick/.agnai
Windows: C:\Users\sceuick\.agnai.
anonymous-only mode if there is no database available.Anonymous users have their data saved to the browser's local storage. Your data will "persist", but not be shareable between devices or other browsers. Clearing your browser's application data/cookies will delete this data.git clone https://github.com/agnaistic/agnai or download itnpm run deps
pnpm v8npm run build:allnpm run startnpm run start:winnpm run start:publicnpm run start:public:windocker compose -p agnai -f self-host.docker-compose.yml up -ddocker run -dt --restart=always -p 3001:3001 ghcr.io/agnaistic/agnaistic:latest
-dt Run the container detached--restart=always Restart at start up or if the server crashes-p 3001:3001 Expose port 3001. Access the app at http://localhost:3001To try and cater for the small tweaks and tuning that people need for their specific needs at an application level we have settings.json.
You can create a file called settings.json at the root level to apply some changes across the entire application.
If you have a specific need for your application, this is the place to ask to have it catered for.
I will try and find a balance between catering to these requests and not having them get out of control in the codebase.
Examples of requests that are suited for this:
You can copy or look at template.settings.json for an example of all of the available settings. You will need to restart Agnai for changes to take effect.
Currently supported custom settings:
baseEndTokens: Add extra response end tokens to the base set.I'd highly recommend using VSCode with the following extensions:
Prettier - Code formatter: For auto-formattingTailwind CSS Intellisense: For auto-completion and intellisense with Tailwind CSS classes"editor.formatOnSave": true to your VSCode settings.json to auto-format with PrettierWhen using pnpm start, the Node.JS server is run using --inspect. This means you can use various Inspector Clients for debugging.
The important parts of the stack are:
# Install dependencies - Always run this after pulling changes
> npm run deps
# Run MongoDB using Docker
> npm run up
# Start the frontend, backend, and python service
# Mac/Linux
> npm start
# Windows
> npm run start:win
# Install and run Pipeline API
# If required, this will update the dependencies before running the API
> npm run model # Install poetry into a virtual environment
# Run everything with a single command:
> npm run start:all # Linux and OSX
> npm run start:all:win # Windows
At this point, you should be able to access http://localhost:3001 in your browser to see the UI.
You can also try to access the frontend with hot reloading at http://localhost:1234
pnpm start script launches the NodeJS API using the --inspect flagF5)chrome://inspect to use the debuggerPoetry - https://python-poetry.org/docs/cli
.model/bin/poetry [...args]The project uses ESLint for linting, Prettier for enforcing code style and TypeScript to check for type errors. When opening a PR, please make sure you're not introducing any new errors in any of these checks by running:
# auto-fixes any style problems
$ pnpm run format:fix
# runs the TypeScript compiler so any type errors will be shown
$ pnpm run typecheck
This project is tested with BrowserStack.
(top 30 of 39)
TypeScript
96.4%
CSS
1.8%
JavaScript
1.4%
AI Agnostic (Multi-user and Multi-bot) Chat with Fictional Characters. Designed with scale in mind.
782
stars
1,389
commits
TypeScript
primary language
Jun 15, 2026
updated
AI Roleplay Chat with Personalized Characters using your favorite AI services.
Visit the live version at Agnai.chat.
Based on the early work of Galatea-UI by PygmalionAI.
Important! MongoDB and Redis are optional! Agnaistic will run in "Guest Only" mode if MongoDB is not available.
Agnaistic is published as an NPM package and can be installed globally:
# Install or update:
npm install agnai -g
agnai
# View launch options:
agnai help
# Run with the Pipeline features
agnai --pipeline
When using the NPM package, your images and JSON files will be stored in: HOME_FOLDER/.agnai.
Examples:
Linux: /home/sceuick/.agnai/
Mac: /Users/sceuick/.agnai
Windows: C:\Users\sceuick\.agnai.
anonymous-only mode if there is no database available.Anonymous users have their data saved to the browser's local storage. Your data will "persist", but not be shareable between devices or other browsers. Clearing your browser's application data/cookies will delete this data.git clone https://github.com/agnaistic/agnai or download itnpm run deps
pnpm v8npm run build:allnpm run startnpm run start:winnpm run start:publicnpm run start:public:windocker compose -p agnai -f self-host.docker-compose.yml up -ddocker run -dt --restart=always -p 3001:3001 ghcr.io/agnaistic/agnaistic:latest
-dt Run the container detached--restart=always Restart at start up or if the server crashes-p 3001:3001 Expose port 3001. Access the app at http://localhost:3001To try and cater for the small tweaks and tuning that people need for their specific needs at an application level we have settings.json.
You can create a file called settings.json at the root level to apply some changes across the entire application.
If you have a specific need for your application, this is the place to ask to have it catered for.
I will try and find a balance between catering to these requests and not having them get out of control in the codebase.
Examples of requests that are suited for this:
You can copy or look at template.settings.json for an example of all of the available settings. You will need to restart Agnai for changes to take effect.
Currently supported custom settings:
baseEndTokens: Add extra response end tokens to the base set.I'd highly recommend using VSCode with the following extensions:
Prettier - Code formatter: For auto-formattingTailwind CSS Intellisense: For auto-completion and intellisense with Tailwind CSS classes"editor.formatOnSave": true to your VSCode settings.json to auto-format with PrettierWhen using pnpm start, the Node.JS server is run using --inspect. This means you can use various Inspector Clients for debugging.
The important parts of the stack are:
# Install dependencies - Always run this after pulling changes
> npm run deps
# Run MongoDB using Docker
> npm run up
# Start the frontend, backend, and python service
# Mac/Linux
> npm start
# Windows
> npm run start:win
# Install and run Pipeline API
# If required, this will update the dependencies before running the API
> npm run model # Install poetry into a virtual environment
# Run everything with a single command:
> npm run start:all # Linux and OSX
> npm run start:all:win # Windows
At this point, you should be able to access http://localhost:3001 in your browser to see the UI.
You can also try to access the frontend with hot reloading at http://localhost:1234
pnpm start script launches the NodeJS API using the --inspect flagF5)chrome://inspect to use the debuggerPoetry - https://python-poetry.org/docs/cli
.model/bin/poetry [...args]The project uses ESLint for linting, Prettier for enforcing code style and TypeScript to check for type errors. When opening a PR, please make sure you're not introducing any new errors in any of these checks by running:
# auto-fixes any style problems
$ pnpm run format:fix
# runs the TypeScript compiler so any type errors will be shown
$ pnpm run typecheck
This project is tested with BrowserStack.
(top 30 of 39)
TypeScript
96.4%
CSS
1.8%
JavaScript
1.4%