Your Private AI Workspace

Built by the community, for the community. Private AI that respects your freedom.

Website · Documentation · Quick Start · Community · Contributing

Install CLI:

curl -fsSL https://get.claraverse.app | bash

Start ClaraVerse:

claraverse init

What is ClaraVerse?

ClaraVerse is a private AI workspace that combines chat, image generation, and visual workflows in one app. Use OpenAI, Claude, Gemini, or local models — with browser-local storage that keeps your conversations private. Even server admins can't read your chats.

50,000+ downloads — the only AI platform where conversations never touch the server, even when self-hosted.

🚀 Core Capabilities

Interactive Artifacts

Have all your creations in one place - Images, Charts, Games, Apps and so on.

AI Docs

Inbuilt tools for PPT, PDF, CSV and much more.

Interactive Chat UI (Human in Loop)

Chat UI that shows up visual question if it need your input

Tool Integrations (No More MCP)

100+ tools to integrate by default and more to come

Prompt to Create Agents (Real no code experience)

Just explain what's your workflow or automation you need and let llm handle the rest

Schedule, API and Automate

Use your agents with you web apps, make them send message everyday, automate workflow that are redundant

Try It Out

Option	Description
Cloud Zero Setup	Free hosted version with TEE-secured inference — no setup required
Self-Hosted	Docker deployment (this repo) — full control on your infrastructure
Desktop	Older Version - Standalone Electron app for Windows, macOS, Linux

---

Key Features

Feature	Description
Browser-Local Storage	Conversations stay in IndexedDB — zero-knowledge architecture
Multi-Provider	OpenAI, Anthropic, Google, Ollama, any OpenAI-compatible endpoint
Visual Workflows	Drag-and-drop builder — chat to design, visual editor to refine
MCP Bridge	Native Model Context Protocol support for seamless tool connections
Interactive Prompts	AI asks clarifying questions mid-conversation with typed forms
Offline Mode	Works completely air-gapped after initial load
Code Execution	Run Python/JS in sandboxed E2B (local Docker, no API key needed)
Memory System	Clara remembers context, auto-archives what's not used
BYOK	Bring your own API keys or use free local models
Tool Router	Small models can be assigned to pick right tools for the task one the fly

---

Quick Start

Install CLI:

curl -fsSL https://get.claraverse.app | bash

Start ClaraVerse:

claraverse init

Open http://localhost → Register → Add AI provider → Start chatting!

Other options

Docker (no CLI):

docker run -d -p 80:80 -p 3001:3001 -v claraverse-data:/data claraverseoss/claraverse:latest

Clone & Run:

git clone https://github.com/claraverse-space/ClaraVerseAI.git && cd ClaraVerseAI && ./quickstart.sh

Advanced Setup & Troubleshooting

Prerequisites

• Docker & Docker Compose installed
• 4GB RAM minimum (8GB recommended)
• If you have old machine that can run linux you are fine with it
• Ollama, Llama.cpp or any openai compatible api with keys

Manual Installation

# 1. Clone
git clone https://github.com/claraverse-space/ClaraVerseAI.git
cd ClaraVerseAI

# 2. Configure
cp .env.default .env

# 3. Start
docker compose up -d

# 4. Verify
docker compose ps

Default Admin

Email: admin@localhost
Password: admin

Change the password on first login.

Troubleshooting

# Run diagnostics
./diagnose.sh     # Linux/Mac
diagnose.bat      # Windows

# View logs
docker compose logs -f backend

# Restart
docker compose restart

# Fresh start
docker compose down -v && docker compose up -d

---

Development Setup

For contributors and local development:

# Prerequisites: Go 1.24+, Node.js 20+, Python 3.11+, tmux

# Install dependencies
make install

# Launch all services in tmux
./dev.sh

Opens a 4-pane terminal with Backend, Frontend, E2B Service, and Info panel.

---

Tech Stack

• Frontend: React 19, TypeScript, Vite, Tailwind CSS 4, Zustand
• Backend: Go 1.24, Fiber, WebSocket streaming
• Database: MongoDB, MySQL, Redis
• Services: SearXNG (search), E2B Local Docker (code execution)
• Auth: Local JWT with Argon2id password hashing

---

Documentation

Resource	Description
Architecture Guide	System design and components
API Reference	REST and WebSocket API
Developer Guide	Local development setup
Security Guide	Security features
Admin Guide	System administration
Quick Reference	Common commands

---

Contributing

1. Fork the repository
2. Create a feature branch: git checkout -b feature/amazing-feature
3. Make changes and test
4. Commit: git commit -m 'Add amazing feature'
5. Push and open a Pull Request

Areas we need help:

• Bug fixes (open issues)
• Documentation improvements
• Translations
• New integrations and model providers

---

Community

• Discord — Chat and support
• Twitter/X — Updates
• GitHub Issues — Bug reports
• GitHub Discussions — Feature requests

---

License

AGPL-3.0 — Free to use, modify, and host commercially. Modifications must be open-sourced. See LICENSE for details.

---

Built with love by the ClaraVerse Community

Back to Top

Build your own private AI workspace with ClaraVerseAI 🌸

Star History