Built by the community, for the community. Private AI that respects your freedom.
Website · Documentation · Quick Start · Community · Contributing
ClaraVerse is a private AI workspace that combines chat, visual workflows, long-running tasks, and Telegram integration in one app. Assign Clara research, coding, or automation tasks and track everything on a board. Use OpenAI, Claude, Gemini, or local models like Ollama — with browser-local storage that keeps your conversations private.
If you have Ollama or LM Studio running on your machine, ClaraVerse detects them automatically and imports all your models — zero configuration.
curl -fsSL https://raw.githubusercontent.com/claraverse-space/ClaraVerse/main/cli/install.sh | bash && claraverse initgit clone https://github.com/claraverse-space/ClaraVerse.git
cd ClaraVerse
docker compose -f docker-compose.production.yml up -dOpen http://localhost:3000 — register your account (first user becomes admin) and start chatting.
Have Ollama running? ClaraVerse auto-detects it and imports all your models. No setup needed. Make sure Ollama is listening on
0.0.0.0(setOLLAMA_HOST=0.0.0.0in your Ollama config).
Docker run (single command)
docker run -d \
--name claraverse \
-p 3000:3000 \
-v claraverse-data:/app/data \
-v claraverse-uploads:/app/uploads \
--add-host=host.docker.internal:host-gateway \
ghcr.io/claraverse-space/claraverse:latestThis runs ClaraVerse with a single container. For the full stack with MySQL, MongoDB, Redis, and SearXNG, use the Docker Compose setup above.
Advanced configuration
- Docker & Docker Compose v2+
- 4 GB RAM minimum (8 GB recommended)
- Ollama, LM Studio, or any OpenAI-compatible API
Override defaults by creating a .env file next to docker-compose.production.yml:
# Port (default 3000)
CLARAVERSE_PORT=8080
# Point to a custom Ollama or LM Studio URL
OLLAMA_BASE_URL=http://host.docker.internal:11434
LMSTUDIO_BASE_URL=http://host.docker.internal:1234ClaraVerse automatically discovers local AI providers running on your host machine:
| Provider | Default URL | What happens |
|---|---|---|
| Ollama | http://host.docker.internal:11434 |
Models imported, provider created, visibility set |
| LM Studio | http://host.docker.internal:1234 |
Models imported via OpenAI-compatible API |
The discovery runs every 2 minutes. When a provider goes offline, it's automatically disabled. When it comes back, models are re-imported.
Ollama setup tip: Ollama defaults to 127.0.0.1 which Docker containers can't reach. Set OLLAMA_HOST=0.0.0.0:
# If using systemd:
sudo systemctl edit ollama
# Add under [Service]:
# Environment="OLLAMA_HOST=0.0.0.0"
sudo systemctl restart ollama# View logs
docker compose -f docker-compose.production.yml logs -f claraverse
# Restart
docker compose -f docker-compose.production.yml restart
# Fresh start (removes all data)
docker compose -f docker-compose.production.yml down -v && docker compose -f docker-compose.production.yml up -dAssign Clara long-running tasks like research, coding, or analysis. Track everything on a Kanban board — you always know what she's working on and why. No black box.
Clara uses skills mid-conversation — context-aware tools that activate when needed. Search the web, generate images, analyze data, all without leaving the chat.
Talk to Clara from Telegram when you're away from the app. Set up routines that run on a schedule and report back to your phone.
Slack, GitHub, Jira, Google Sheets, Notion, Discord, Telegram, HubSpot, and many more — built in, no MCP required. All integrations are shared across Chat, Workflows, Nexus, and Routines. Connect once, use everywhere.
Have all your creations in one place — images, charts, games, apps and more.
Built-in tools for PPT, PDF, CSV and much more.
The AI asks you visual questions when it needs your input.
Drag-and-drop workflow builder with parallel execution, scheduling, and 200+ integrations. Describe what you need and let the LLM build the automation for you.
Use workflows with your web apps, schedule daily messages, automate repetitive tasks.
| Feature | Description |
|---|---|
| Nexus | Assign long-running tasks, track progress on a Kanban board |
| Skills | Context-aware tools that activate mid-conversation when needed |
| Channels | Telegram integration — talk to Clara from your phone |
| Routines | Scheduled task sequences that report back via Telegram |
| Workflows | Drag-and-drop builder with parallel execution, scheduling, 200+ integrations |
| 150+ Integrations | Slack, GitHub, Jira, Notion, and more — shared across Chat, Workflows, Nexus, and Routines |
| Devices | Connect all your machines — Clara reaches MCP on any of them remotely |
| Clara Companion | Bridge local MCP servers to ClaraVerse over WebSocket from any machine |
| Browser-Local Storage | Conversations stay in IndexedDB — zero-knowledge architecture |
| Local AI Auto-Detection | Ollama and LM Studio discovered and imported automatically |
| Multi-Provider | OpenAI, Anthropic, Google, Ollama, any OpenAI-compatible endpoint |
| MCP Bridge | Native Model Context Protocol support for seamless tool connections |
| Interactive Prompts | AI asks clarifying questions mid-conversation with typed forms |
| Memory System | Clara remembers context across conversations, auto-archives old memories |
| BYOK | Bring your own API keys or use free local models |
Connect your local tools and filesystem to ClaraVerse via the Clara Companion CLI. It bridges local MCP servers to your ClaraVerse instance over WebSocket.
# Install via the claraverse CLI
claraverse companion
# Login (choose default localhost:3000 or enter your server URL)
clara_companion login
# Start the bridge
clara_companionOr install manually from GitHub Releases.
| Option | Description |
|---|---|
| Cloud | Free hosted version — no setup required |
| Self-Hosted | Docker deployment (this repo) — full control on your infrastructure |
| Desktop | Standalone Electron app for Windows, macOS, Linux |
| Layer | Technology |
|---|---|
| Frontend | React 19, TypeScript, Vite 7, Tailwind CSS 4, Zustand |
| Backend | Go 1.24, Fiber, WebSocket streaming |
| Database | MySQL, MongoDB, Redis (all bundled in Docker Compose) |
| Search | SearXNG (private, self-hosted) |
| Auth | Local JWT with Argon2id password hashing |
For contributors working on the codebase:
# Prerequisites: Go 1.24+, Node.js 20+, Docker
# Clone the repo
git clone https://github.com/claraverse-space/ClaraVerse.git
cd ClaraVerse
# Start backing services (MySQL, MongoDB, Redis, SearXNG)
docker compose -f docker-compose.dev.yml up -d
# Backend
cd backend
cp .env.example .env
go run cmd/server/main.go
# Frontend (separate terminal)
cd frontend
cp .env.example .env
npm install
npm run devFrontend runs at http://localhost:5173, backend at http://localhost:3001.
See CONTRIBUTING.md for coding standards and PR guidelines.
| Resource | Description |
|---|---|
| Architecture | System architecture and design decisions |
| API Reference | REST and WebSocket API |
| Admin Guide | System administration and provider setup |
| Developer Guide | Contributing and local development |
| Quick Reference | Common commands and shortcuts |
- Fork the repository
- Create a feature branch:
git checkout -b feature/amazing-feature - Make changes and test
- Run
cd frontend && npm run lint && npm run type-check - Commit and open a Pull Request
Areas we need help:
- Bug fixes (open issues)
- New tool integrations and model providers
- Documentation improvements
- Translations
See CONTRIBUTING.md for the full guide.
- Discord — Chat and support
- Twitter/X — Updates
- GitHub Issues — Bug reports
- GitHub Discussions — Feature requests
AGPL-3.0 — Free to use, modify, and host commercially. Modifications must be open-sourced. See LICENSE for details.
![@google-labs-jules[bot]](https://avatars.githubusercontent.com/in/842251?s=64&v=4){kind=small}