- Claude Code CLI — Install Claude Code
- Python 3.11+ with uv
- Node.js 18+ (for the dashboard)
- API keys for integrations you want to use
npx @evoapi/evo-nexusThis downloads and runs the interactive setup wizard automatically.
git clone --depth 1 https://github.com/EvolutionAPI/evo-nexus.git
cd evo-nexus
# Interactive setup wizard
make setup
# Or: python setup.pyThe wizard asks for:
- Your name and company
- Timezone and language
- Which AI provider to use (Anthropic by default; alternatives via OpenClaude)
- Which agents to enable
- Which integrations to configure
It generates:
config/workspace.yaml— central configconfig/routines.yaml— routine schedulesconfig/providers.json— active AI provider + backend CLI config.env— API keys (fill in after setup)CLAUDE.md— context file for Claude
The wizard asks which backend should power EvoNexus. Anthropic is the default — if you already have Claude Code authenticated, you don't need to do anything else.
For any other provider (OpenRouter, OpenAI, Gemini, AWS Bedrock, Vertex AI, Codex Auth), EvoNexus uses OpenClaude, a drop-in binary compatible with the Claude CLI protocol. Install it once:
npm install -g @gitlawb/openclaudeThen select the provider in the wizard (or later from the Providers page in the dashboard) and fill in the keys. The active provider is stored in config/providers.json and both the terminal-server and the ADW runner re-read it on every session spawn — no restart required when switching.
See docs/dashboard/providers.md for the full provider reference and docs/reference/env-variables.md for all provider-related env vars.
Edit .env with your keys:
nano .envAt minimum, you need:
- No keys required for basic operation (agents, skills work without integrations)
DISCORD_BOT_TOKEN— for community monitoringSTRIPE_SECRET_KEY— for financial routines- Social OAuth keys — via the dashboard Integrations page
On a VPS (remote): The setup wizard automatically creates a dedicated evonexus system user (Claude Code refuses --dangerously-skip-permissions as root) and installs a systemd service that starts on boot:
systemctl status evo-nexus # check status
systemctl restart evo-nexus # restart
journalctl -u evo-nexus -f # follow logs
su - evonexus # switch to service userYou can also install the systemd service manually on an existing installation:
sudo bash install-service.shLocal (macOS/Linux):
make dashboard-appOpen http://localhost:8080 — the first run shows a setup wizard where you create your admin account and configure the workspace.
On a VPS, the scheduler runs automatically inside the dashboard service. Locally:
make schedulerThis starts the scheduler that runs routines at their configured times (see config/routines.yaml).
Open Claude Code in this directory. It reads CLAUDE.md automatically and has access to all agents and skills.
First thing to run: /oracle. Oracle is the official entry point — it interviews you about your business, maps workspace capabilities to your pain points, and delivers a phased activation plan through the prod-activation-plan skill (index file + folder-per-phase + file-per-item, each with suggested agent team and pending decisions). You never have to guess the next step.
/oracle # Start here — business discovery + activation planAfter the plan is ready, you can invoke individual agents:
/clawdia # Operations hub
/flux # Financial analysis
/atlas # Project management
/pulse # Community pulse
/pixel # Social media
# Or let Claude route automatically based on your request- Read Architecture to understand how agents, skills, and routines work together
- Browse
.claude/skills/CLAUDE.mdfor the full skill index (175+ skills) - Check
ROUTINES.mdfor routine documentation - Customize
config/routines.yamlto adjust schedules
