The open source operating system for AI-powered businesses
# Add to your Claude Code skills
git clone https://github.com/evolution-foundation/evo-nexusDisclaimer: EvoNexus is an independent, unofficial open-source project. It is not affiliated with, endorsed by, or sponsored by Anthropic. "Claude" and "Claude Code" are trademarks of Anthropic, PBC. This project integrates with Claude Code as a third-party tool and requires users to provide their own installation and credentials.
EvoNexus is an open source, unofficial multi-agent operating layer built around the Claude Code CLI protocol — but not locked to any single LLM provider. It runs natively on Anthropic's claude CLI by default, and can transparently switch to OpenAI, Google Gemini, OpenRouter (200+ models), AWS Bedrock, Google Vertex AI, or Codex Auth via OpenClaude. Same agents, same skills, same workflows — your choice of backend.
It turns a single CLI installation into a team of 38 specialized agents organized in two ortogonal layers — 17 business agents (operations, finance, community, marketing, HR, legal, product, data, learning retention) and 21 engineering agents (architecture, planning, code review, testing, debugging, security, design, cycle orchestration, retrospective — 19 derived from oh-my-claudecode, MIT, by Yeachan Heo + 2 native: Helm and Mirror). The engineering layer follows a canonical 6-phase workflow documented in .claude/rules/dev-phases.md.
This is not a chatbot. It is a real operating layer that runs routines, generates HTML reports, syncs meetings, triages emails, monitors community health, tracks financial metrics, and consolidates everything into a unified dashboard — all automated.
No comments yet. Be the first to share your thoughts!
EvoNexus is one of the projects maintained by Evolution Foundation. It is the operating layer that orchestrates the Foundation's own work — including the development of Evo CRM Community, Evolution API and Evolution Go.
.md files with system prompts, not code. No SDK, no compile step. Add an agent by dropping a file in .claude/agents/, or package reusable bundles via the plugin system (see docs/introduction.md)claude CLI, but can switch to OpenRouter, OpenAI, Gemini, AWS Bedrock, Google Vertex, or Codex Auth via OpenClaude without touching a line of code. Your keys, your model choice, no vendor lock-in/clawdia, /flux, /pulse, /apex invoke agents directly from the terminalCLAUDE.md + per-agent memory survives across sessionsclaude) or any of 6 alternate backends via OpenClaude: OpenRouter (200+ models), OpenAI, Google Gemini, Codex Auth, AWS Bedrock, Google Vertex AI. Switch providers from the dashboard, no code changescustom-* agents (gitignored)social-, fin-, int-, prod-, mkt-, gog-, obs-, discord-, pulse-, sage-, hr-, legal-, ops-, cs-, data-, pm-, dev-)Starting out? After installing, open Claude Code and call
/oracle. It's the official entry point of EvoNexus: runs the initial setup, interviews you about your business, shows what the toolkit can automate for you, and delivers a phased activation plan.
curl -O https://raw.githubusercontent.com/evolution-foundation/evo-nexus/main/docker-compose.hub.yml
docker compose -f docker-compose.hub.yml up -d
open http://localhost:8080
The setup wizard loads on first boot. Paste your Anthropic / OpenAI / Codex key and you're done. Full guide: docs/guides/docker-install.md.
npx @evoapi/evo-nexus
git clone --depth 1 https://github.com/evolution-foundation/evo-nexus.git
cd evo-nexus
# Interactive setup wizard
make setup
| Tool | Required | Install |
|---|---|---|
| Claude Code | Yes (CLI install) | npm install -g @anthropic-ai/claude-code |
| Python 3.11+ | Yes (CLI install) | via uv |
| Node.js 18+ | Yes (CLI install) | nodejs.org |
| uv | Yes (CLI install) | curl -LsSf https://astral.sh/uv/install.sh \| sh |
| Docker Engine 24+ | Yes (Docker install) | docs.docker.com/engine/install |
EvoNexus runs on Anthropic's Claude by default. For OpenAI, Gemini, Bedrock, OpenRouter, Vertex AI, or Codex Auth, it switches to OpenClaude.
| Provider | Binary | Key env vars |
|---|---|---|
| Anthropic (default) | claude | native auth |
| OpenRouter (200+ models) | openclaude | CLAUDE_CODE_USE_OPENAI, OPENAI_BASE_URL, OPENAI_API_KEY, OPENAI_MODEL |
| OpenAI | openclaude | CLAUDE_CODE_USE_OPENAI, OPENAI_API_KEY, OPENAI_MODEL |
| Google Gemini | openclaude | CLAUDE_CODE_USE_GEMINI, GEMINI_API_KEY, GEMINI_MODEL |
| Codex Auth | openclaude | CLAUDE_CODE_USE_OPENAI, OPENAI_MODEL=codexplan |
| AWS Bedrock | openclaude | CLAUDE_CODE_USE_BEDROCK, AWS_REGION, AWS_BEARER_TOKEN_BEDROCK |
| Google Vertex AI | openclaude | CLAUDE_CODE_USE_VERTEX, ANTHROPIC_VERTEX_PROJECT_ID, CLOUD_ML_REGION |
npm install -g @gitlawb/openclaude
The setup wizard asks which provider you want during make setup, and you can switch at any time from the Providers page in the dashboard.
A full web UI at http://localhost:8080:
| Page | What it does | |--