"Vibe-Trading: Your Personal Trading Agent"
Project management app with MCP access
Kaneo is a self-hosted project management app with kanban, issue tracking, and a built-in MCP endpoint for agent tools. The repo also includes Docker Compose, a Coolify setup, and a Helm chart for deployment.

Builders who want a self-hosted project tracker their agent can use alongside them.
You can manage tasks and labels in one project system while letting an agent connect through MCP.
What it does
Kanban and issue tracking
Tracks work in a project management app focused on boards and issues.
Built-in MCP endpoint
Exposes `/api/mcp` for MCP clients, and provides the `@kaneo/mcp` package for stdio use.
Self-hosted deployment options
Includes Docker Compose, Coolify, and Helm chart deployment files.
Multi-package TypeScript repo
Uses `apps/` and `packages/` for the web app, API, email, permissions, imports, and MCP code.
How to get it
- 1For straightforward deployments, use drim - a CLI tool that handles everything for you
curl -fsSL https://assets.kaneo.app/install.sh | sh drim setup
README
Quick Start | Website | Cloud | Discord
Why Kaneo?
After years of using bloated, overcomplicated project management platforms that distracted from actual work, we built Kaneo to be different.
The problem with most tools isn't that they lack features, it's that they have too many. Every notification, every unnecessary button, every complex workflow pulls your team away from what matters: building great products.
We believe the best tools are invisible. They should amplify your team's natural workflow, not force you to adapt to theirs. Kaneo is built on the principle that less is more: every feature exists because it solves a real problem, not because it looks impressive in a demo.
What makes it different:
- Clean interface that focuses on your work, not the tool
- Self-hosted so your data stays yours
- Actually fast because we care about performance
- Open source with a permissive MIT license
Learn more about Kaneo's features and capabilities in our documentation.
Sponsors
Kaneo is open source. If you find it useful, consider sponsoring the project to help support ongoing development.


Getting Started
One-Click Deployment with drim
For straightforward deployments, use drim - a CLI tool that handles everything for you:
curl -fsSL https://assets.kaneo.app/install.sh | sh
drim setup
That's it. Your Kaneo instance will be running with automatic HTTPS, database setup, and all services configured.
Perfect for quick deployments and production setups where you want things to just work.
Quick Start with Docker Compose
The fastest way to try Kaneo is with Docker Compose. This sets up Kaneo and PostgreSQL with a single Kaneo container:
services:
postgres:
image: postgres:16-alpine
env_file:
- .env
ports:
- "5432:5432"
volumes:
- postgres_data:/var/lib/postgresql/data
restart: unless-stopped
healthcheck:
test: ["CMD-SHELL", "pg_isready -U kaneo -d kaneo"]
interval: 10s
timeout: 5s
retries: 5
kaneo:
image: ghcr.io/usekaneo/kaneo:latest
ports:
- "5173:5173"
env_file:
- .env
depends_on:
postgres:
condition: service_healthy
restart: unless-stopped
volumes:
postgres_data:
Save this as compose.yml, copy .env.sample to .env, uncomment KANEO_CLIENT_URL=http://localhost:5173, and set POSTGRES_PASSWORD=<password> and AUTH_SECRET=<output of openssl rand -hex 32>, run docker compose up -d, and open http://localhost:5173.
In Docker Compose, the bundled Kaneo container reaches PostgreSQL at the service hostname postgres.
If you run the API on your host instead of inside Compose, use localhost or set DATABASE_URL explicitly.
Important: See our full documentation for detailed setup instructions, environment variable configuration, and troubleshooting guides.
Deploy on Coolify
Kaneo ships a Coolify-optimized compose.coolify.yml. In Coolify, create a Public Repository resource pointing to https://github.com/usekaneo/kaneo, pick the Docker Compose build pack (Base Directory /, Compose Location compose.coolify.yml), assign a domain to the kaneo service as https://your-domain.com:5173, set KANEO_CLIENT_URL, and deploy. AUTH_SECRET and the database password are auto-generated by Coolify. Leave KANEO_API_URL unset (it is derived from KANEO_CLIENT_URL; a localhost value breaks the browser API calls). See the Coolify deployment guide for details.
Development Setup
For development, see our Environment Setup Guide for detailed instructions on configuring environment variables and troubleshooting common issues like CORS problems.
Configuration
Kaneo requires several environment variables to be configured. The Docker Compose setup above handles the database automatically, but you'll need to configure environment variables for the API and web services.
For complete configuration instructions, including all required environment variables, database setup for non-Docker deployments, and advanced settings, see the documentation. Advanced deployments can still use the separate ghcr.io/usekaneo/api and ghcr.io/usekaneo/web images.
Kubernetes Deployment
If you're running Kubernetes, we provide a comprehensive Helm chart. Check out the Helm chart documentation for detailed installation instructions, production configuration examples, TLS setup, and more.
Development
Want to hack on Kaneo? See our Environment Setup Guide for detailed instructions on configuring environment variables and troubleshooting common issues like CORS problems.
Quick start:
# Clone and install dependencies
git clone https://github.com/usekaneo/kaneo.git
cd kaneo
pnpm install
# Create a .env file in the root with required environment variables
# See ENVIRONMENT_SETUP.md for detailed instructions
# Start development servers
pnpm dev
For contributing guidelines, code structure, and development best practices, check out our contributing guide and documentation.
MCP Server
Kaneo has an official MCP (Model Context Protocol) server, so AI tools like Claude, Cursor, and other MCP clients can manage your tasks, projects, and labels. Every instance ships a built-in HTTP MCP endpoint at /api/mcp, and for stdio clients there is the official @kaneo/mcp package on npm (npx -y @kaneo/mcp).
Community
- Discord - Chat with users and contributors
- GitHub Issues - Bug reports and feature requests
- Documentation - Detailed guides, API docs, and tutorials
Contributing
We're always looking for help, whether that's:
- Reporting bugs or suggesting features
- Improving documentation
- Contributing code
- Helping other users on Discord
Check out CONTRIBUTING.md for the details on how to get involved.
License
MIT License - see LICENSE for details.
Built with ❤️ by the Kaneo team and contributors
Files in the repo
- .agents
- .claude
- .cursor
- .devcontainer
- .github
- .husky
- .vscode
- apps
- charts
- deploy
- i18n
- packages
- plans
- scripts
- sentry
- skills
- tests
- .coderabbit.yaml
- .dockerignore
- .env.sample
- .gitattributes
- .gitignore
- .npmrc
- AGENTS.md
- biome.json
- CHANGELOG.md
- CLAUDE.md
- CODE_OF_CONDUCT.md
- commitlint.config.js
- compose.coolify.yml
- compose.local.yml
- compose.yml
- CONTRIBUTING.md
- CONTRIBUTORS.svg
- Dockerfile.kaneo
- ENVIRONMENT_SETUP.md
- LICENSE
- package.json
- pnpm-lock.yaml
- pnpm-workspace.yaml
- README.md
- release.config.js
- SECURITY.md
- skills-lock.json
- turbo.json
Discussion (0)
Ask about usage, or say what you built with itSign in to join the discussion.
No comments yet. Be the first to say what this is good for.
More other

Your Personal AI Assistant; easy to install, deploy on your own machine or on the cloud; supports multiple chat apps with easily extensible capabilities.
macOS video editor built for AI
Open-source Claude Design alternative. One-click import your Claude Code / Codex API key. Prompt → prototype / slides / PDF. Multi-model (Claude, GPT, Gemini, Kimi, GLM, Ollama). BYOK, local-first, MIT.
🤯 LobeHub is your Chief Agent Operator, organizing your agents into 7×24 operations by hiring, scheduling, and reporting on your entire AI team.
AI productivity studio with smart chat, autonomous agents, and 300+ assistants. Unified access to frontier LLMs