{"id":48642513,"url":"https://github.com/evolutionapi/evo-nexus","last_synced_at":"2026-04-24T03:02:53.594Z","repository":{"id":350194525,"uuid":"1205298114","full_name":"EvolutionAPI/evo-nexus","owner":"EvolutionAPI","description":"The open source operating system for AI-powered businesses","archived":false,"fork":false,"pushed_at":"2026-04-22T10:36:04.000Z","size":294751,"stargazers_count":363,"open_issues_count":7,"forks_count":111,"subscribers_count":2,"default_branch":"main","last_synced_at":"2026-04-22T12:29:19.813Z","etag":null,"topics":["ai-agents","ai-workspace","anthropic","automation","business-automation","claude","claude-code","dashboard","multi-agent","open-source","openclaw"],"latest_commit_sha":null,"homepage":"https://openclaude.evolutionfoundation.com.br","language":"TypeScript","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/EvolutionAPI.png","metadata":{"files":{"readme":"README.md","changelog":"CHANGELOG.md","contributing":"CONTRIBUTING.md","funding":null,"license":"LICENSE","code_of_conduct":"CODE_OF_CONDUCT.md","threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":"SECURITY.md","support":null,"governance":null,"roadmap":"ROADMAP.md","authors":null,"dei":null,"publiccode":null,"codemeta":null,"zenodo":null,"notice":"NOTICE.md","maintainers":null,"copyright":null,"agents":null,"dco":null,"cla":null}},"created_at":"2026-04-08T20:40:58.000Z","updated_at":"2026-04-22T12:02:55.000Z","dependencies_parsed_at":null,"dependency_job_id":null,"html_url":"https://github.com/EvolutionAPI/evo-nexus","commit_stats":null,"previous_names":["evolutionapi/open-claude","evolutionapi/evo-nexus"],"tags_count":65,"template":false,"template_full_name":null,"purl":"pkg:github/EvolutionAPI/evo-nexus","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/EvolutionAPI%2Fevo-nexus","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/EvolutionAPI%2Fevo-nexus/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/EvolutionAPI%2Fevo-nexus/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/EvolutionAPI%2Fevo-nexus/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/EvolutionAPI","download_url":"https://codeload.github.com/EvolutionAPI/evo-nexus/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/EvolutionAPI%2Fevo-nexus/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":32207191,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-04-24T01:12:49.758Z","status":"online","status_checked_at":"2026-04-24T02:00:07.115Z","response_time":64,"last_error":null,"robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":true,"can_crawl_api":true,"host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["ai-agents","ai-workspace","anthropic","automation","business-automation","claude","claude-code","dashboard","multi-agent","open-source","openclaw"],"created_at":"2026-04-09T22:24:30.525Z","updated_at":"2026-04-24T03:02:48.581Z","avatar_url":"https://github.com/EvolutionAPI.png","language":"TypeScript","funding_links":[],"categories":[],"sub_categories":[],"readme":"\u003cp align=\"center\"\u003e\n  \u003ca href=\"https://evolutionfoundation.com.br\"\u003e\n    \u003cimg src=\"public/cover.webp\" alt=\"Evolution Foundation\" height=\"60\"/\u003e\n  \u003c/a\u003e\n\u003c/p\u003e\n\n\u003cp align=\"center\"\u003e\n  \u003cimg src=\"public/cover.svg\" alt=\"EvoNexus\" width=\"100%\"/\u003e\n\u003c/p\u003e\n\n\u003cp align=\"center\"\u003e\n  \u003ca href=\"#quick-start\"\u003eQuick Start\u003c/a\u003e •\n  \u003ca href=\"#web-dashboard\"\u003eDashboard\u003c/a\u003e •\n  \u003ca href=\"docs/getting-started.md\"\u003eDocs\u003c/a\u003e •\n  \u003ca href=\"CHANGELOG.md\"\u003eChangelog\u003c/a\u003e •\n  \u003ca href=\"CONTRIBUTING.md\"\u003eContributing\u003c/a\u003e •\n  \u003ca href=\"LICENSE\"\u003eMIT License\u003c/a\u003e\n\u003c/p\u003e\n\n---\n\n\u003e **Disclaimer:** 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.\n\n---\n\n## What It Is\n\nEvoNexus is an open source, **unofficial** multi-agent operating layer built around the [Claude Code](https://docs.anthropic.com/en/docs/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](https://www.npmjs.com/package/@gitlawb/openclaude). Same agents, same skills, same workflows — your choice of backend.\n\nIt 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](https://github.com/yeachan-heo/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`. Each agent has its own domain, skills, persistent memory, and automated routines. The result is a production system that runs daily operations for a founder/CEO **and** supports software development workflows: from morning briefings to financial reports, community monitoring, social analytics, end-of-day consolidation, plus architectural reviews, code audits, and verified implementation pipelines.\n\n**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.\n\n### Why EvoNexus?\n\n- **Markdown-first agents** — agents are `.md` files with system prompts, not code. No SDK, no plugin runtime, no compile step. Add an agent by dropping a file in `.claude/agents/`\n- **Skills as instructions** — reusable capabilities are markdown too. 175+ skills covering finance, community, social, engineering, data, legal, HR, ops, product, CS\n- **Multi-provider by design** — default runs on Anthropic's native `claude` CLI, but can switch to OpenRouter, OpenAI, Gemini, AWS Bedrock, Google Vertex, or Codex Auth via [OpenClaude](https://www.npmjs.com/package/@gitlawb/openclaude) without touching a line of code. Your keys, your model choice, no vendor lock-in\n- **MCP integrations** — first-class support for Google Calendar, Gmail, GitHub, Linear, Telegram, Canva, Notion, and more via the Model Context Protocol\n- **Slash commands** — `/clawdia`, `/flux`, `/pulse`, `/apex` invoke agents directly from the terminal\n- **Persistent memory** — `CLAUDE.md` + per-agent memory survives across sessions\n- **CLI-first, local-only** — runs anywhere the Claude CLI (or OpenClaude) runs. Your data never leaves your infrastructure\n\n---\n\n## Key Features\n\n- **Multi-Provider** — runs on Anthropic (native `claude`) or any of 6 alternate backends via [OpenClaude](https://www.npmjs.com/package/@gitlawb/openclaude): OpenRouter (200+ models), OpenAI, Google Gemini, Codex Auth, AWS Bedrock, Google Vertex AI. Switch providers from the dashboard, no code changes\n- **17 Core Agents + Custom** — Ops, Finance, Projects, Community, Social, Strategy, Sales, Courses, Learning Retention, Personal, Knowledge, Marketing, HR, Customer Success, Legal, Product, Data — plus user-created `custom-*` agents (gitignored)\n- **150+ Skills + Custom** — organized by domain prefix (`social-`, `fin-`, `int-`, `prod-`, `mkt-`, `gog-`, `obs-`, `discord-`, `pulse-`, `sage-`, `hr-`, `legal-`, `ops-`, `cs-`, `data-`, `pm-`). Includes `prod-activation-plan` — the canonical skill for producing phased activation plans (index + folder-per-phase + file-per-item) used by Oracle\n- **7 Core + 20 Custom Routines** — daily, weekly, and monthly ADWs managed by a scheduler (core routines ship with the repo; custom routines are user-created and gitignored)\n- **Web Dashboard** — React + Flask app with auth, roles, web terminal, service management\n- **19 Integrations** — Google Calendar, Gmail, Linear, GitHub, Discord, Telegram, Stripe, Omie, Bling, Asaas, Fathom, Todoist, YouTube, Instagram, LinkedIn, Evolution API, Evolution Go, Evo CRM, and more\n- **2 core + custom HTML report templates** — dark-themed dashboards for every domain\n- **Persistent Memory** — two-tier system (CLAUDE.md + memory/) with LLM Wiki pattern: ingest propagation, weekly lint, centralized index, and operation log\n- **Knowledge Base** — optional semantic search via [MemPalace](https://github.com/milla-jovovich/mempalace) (local ChromaDB vectors, one-click install)\n- **Full Observability** — JSONL logs, execution metrics, cost tracking per routine\n- **Heartbeats (Phase 1)** — proactive agents that wake on a schedule, run a 9-step protocol, and decide whether to act\n- **Goal Cascade (Phase 1)** — Mission → Project → Goal → Task hierarchy. Link any routine/heartbeat/ticket to a goal; agents receive the chain as prompt context\n- **Tickets (Phase 1)** — persistent conversation/work threads with atomic checkout (`UPDATE WHERE locked_at IS NULL`), 6-state workflow, mention-based wake triggers, global `/issues` page\n\n---\n\n## Screenshots\n\n\u003cp align=\"center\"\u003e\n  \u003cimg src=\"public/print-overview.webp\" alt=\"Overview\" width=\"49%\" /\u003e\n  \u003cimg src=\"public/print-chat.webp\" alt=\"Agent Chat\" width=\"49%\" /\u003e\n\u003c/p\u003e\n\u003cp align=\"center\"\u003e\n  \u003cimg src=\"public/print-agents.webp\" alt=\"Agents\" width=\"49%\" /\u003e\n  \u003cimg src=\"public/print-integrations.webp\" alt=\"Integrations\" width=\"49%\" /\u003e\n\u003c/p\u003e\n\u003cp align=\"center\"\u003e\n  \u003cimg src=\"public/print-costs.webp\" alt=\"Costs\" width=\"49%\" /\u003e\n\u003c/p\u003e\n\n---\n\n## Integrations\n\nConnect your existing tools via MCP servers, API clients, or OAuth:\n\n| Integration | Type | What it does |\n|---|---|---|\n| **Google Calendar** | MCP | Read/create/update events, find free time |\n| **Gmail** | MCP | Read, draft, send emails, triage inbox |\n| **GitHub** | MCP + CLI | PRs, issues, releases, code search |\n| **Linear** | MCP | Issues, sprints, project tracking |\n| **Discord** | API | Community messages, channels, moderation |\n| **Telegram** | MCP + Bot | Notifications, messages, commands |\n| **Stripe** | API | Charges, subscriptions, MRR, customers |\n| **Omie** | API | ERP — clients, invoices, financials, stock |\n| **Bling** | API (OAuth2) | Brazilian ERP — products, orders, NF-e, contacts, stock (auto-refresh via `make bling-auth`) |\n| **Asaas** | API | Brazilian payments — Pix, boleto, credit card, subscriptions, marketplace split |\n| **Fathom** | API | Meeting recordings, transcripts, summaries |\n| **Todoist** | CLI | Task management, priorities, projects |\n| **YouTube** | OAuth | Channel stats, videos, engagement |\n| **Instagram** | OAuth | Profile, posts, engagement, insights |\n| **LinkedIn** | OAuth | Profile, org stats |\n| **Canva** | MCP | Design and presentations |\n| **Notion** | MCP | Knowledge base, pages, databases |\n| **Obsidian** | CLI | Vault management, notes, search |\n| **Evolution API** | API | WhatsApp messaging — instances, messages, chats, groups |\n| **Evolution Go** | API | WhatsApp messaging (Go implementation) |\n| **Evo CRM** | API | AI-powered CRM — contacts, conversations, pipelines |\n\nSocial media accounts (YouTube, Instagram, LinkedIn) are connected via OAuth through the dashboard.\n\n---\n\n## Prerequisites\n\n| Tool | Required | Install |\n|------|----------|---------|\n| **Claude Code** | Yes | `npm install -g @anthropic-ai/claude-code` ([docs](https://claude.ai/download)) |\n| **Python 3.11+** | Yes | via [uv](https://docs.astral.sh/uv/): `curl -LsSf https://astral.sh/uv/install.sh \\| sh` |\n| **Node.js 18+** | Yes | [nodejs.org](https://nodejs.org) |\n| **uv** | Yes | `curl -LsSf https://astral.sh/uv/install.sh \\| sh` |\n\nThe setup wizard (`make setup`) checks for all prerequisites before proceeding.\n\n---\n\n## AI Providers\n\nEvoNexus runs on **Anthropic's Claude** by default — no extra config needed. For everything else (OpenAI, Gemini, Bedrock, OpenRouter, Vertex AI, Codex Auth), it switches to [OpenClaude](https://www.npmjs.com/package/@gitlawb/openclaude), a drop-in binary that speaks the Claude CLI protocol but dispatches to the provider of your choice via environment variables.\n\n| Provider | Binary | Key env vars |\n|---|---|---|\n| **Anthropic** (default) | `claude` | native auth |\n| **OpenRouter** (200+ models) | `openclaude` | `CLAUDE_CODE_USE_OPENAI`, `OPENAI_BASE_URL`, `OPENAI_API_KEY`, `OPENAI_MODEL` |\n| **OpenAI** | `openclaude` | `CLAUDE_CODE_USE_OPENAI`, `OPENAI_API_KEY`, `OPENAI_MODEL` |\n| **Google Gemini** | `openclaude` | `CLAUDE_CODE_USE_GEMINI`, `GEMINI_API_KEY`, `GEMINI_MODEL` |\n| **Codex Auth** (OpenAI via OAuth) | `openclaude` | `CLAUDE_CODE_USE_OPENAI`, `OPENAI_API_KEY` |\n| **AWS Bedrock** | `openclaude` | `CLAUDE_CODE_USE_BEDROCK`, `AWS_REGION`, `AWS_BEARER_TOKEN_BEDROCK` |\n| **Google Vertex AI** | `openclaude` | `CLAUDE_CODE_USE_VERTEX`, `ANTHROPIC_VERTEX_PROJECT_ID`, `CLOUD_ML_REGION` |\n\nInstall OpenClaude once globally if you plan to use any non-Anthropic provider:\n\n```bash\nnpm install -g @gitlawb/openclaude\n```\n\nThe setup wizard asks which provider you want during `make setup`, and you can switch at any time from the **Providers** page in the dashboard (no restart needed — the terminal-server and ADW runner re-read `config/providers.json` on every session spawn). See [docs/dashboard/providers.md](docs/dashboard/providers.md) for the full reference.\n\n---\n\n## Quick Start\n\n\u003e **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** — an index file at the top + one folder per phase + one file per item, each with suggested agent team, dependencies, and pending decisions. The plan is materialized by the `prod-activation-plan` skill (workspace canonical pattern) so you never have to guess the next step.\n\n### Method 1 — One command (recommended)\n\n```bash\nnpx @evoapi/evo-nexus\n```\n\nThis downloads and runs the interactive setup wizard automatically.\n\n### Method 2 — Manual clone\n\n```bash\ngit clone --depth 1 https://github.com/EvolutionAPI/evo-nexus.git\ncd evo-nexus\n\n# Interactive setup wizard — checks prerequisites, creates config files\nmake setup\n```\n\n### What the wizard does\n\nThe wizard:\n- Checks that Claude Code, uv, Node.js are installed\n- Asks for your name, company, timezone, language\n- **Asks which AI provider to use** (Anthropic by default; offers OpenRouter, OpenAI, Gemini, Bedrock, Vertex, Codex Auth as alternatives via OpenClaude)\n- Lets you pick which agents and integrations to enable\n- Generates `config/workspace.yaml`, `config/providers.json`, `.env`, `CLAUDE.md`, and workspace folders\n- Builds the dashboard frontend\n\n### 2. Configure API keys\n\n```bash\nnano .env\n```\n\nAdd keys for the integrations you enabled. Common ones:\n\n```env\n# Discord (for community monitoring)\nDISCORD_BOT_TOKEN=your_token\nDISCORD_GUILD_ID=your_guild_id\n\n# Stripe (for financial routines)\nSTRIPE_SECRET_KEY=sk_live_...\n\n# Telegram (for notifications)\nTELEGRAM_BOT_TOKEN=your_token\nTELEGRAM_CHAT_ID=your_chat_id\n\n# Social media (connect via dashboard Integrations page)\nSOCIAL_YOUTUBE_1_API_KEY=...\nSOCIAL_INSTAGRAM_1_ACCESS_TOKEN=...\n```\n\nSee `.env.example` for all available variables.\n\n### 3. Start the dashboard\n\n```bash\nmake dashboard-app\n```\n\nOpen **http://localhost:8080** — the first run shows a setup wizard where you:\n- Configure your workspace (name, company, agents, integrations)\n- Create your admin account\n- License is activated automatically in the background\n\n### 4. Start automated routines\n\n```bash\nmake scheduler\n```\n\nRuns all enabled routines on schedule (morning briefing, email triage, community pulse, financial reports, etc). Configure schedules in `config/routines.yaml`.\n\n### 5. Use Claude Code — start with `/oracle`\n\nOpen Claude Code in the project directory — it reads `CLAUDE.md` automatically. The **first thing you should do** is call `/oracle`:\n\n```bash\n/oracle\n```\n\nOracle will:\n1. Detect workspace state (fresh install vs. configured)\n2. Interview you about your business, pain points and priorities\n3. Map workspace capabilities to your pains (via @scout-explorer)\n4. Present the \"wow\" report — what can be automated for you\n5. Delegate the plan structure to @compass-planner\n6. **Materialize the plan using the `prod-activation-plan` skill** — creates an index file + phase folders + item files, each with suggested agent team, dependencies and pending decisions\n7. Hand you the plan with **3 autonomy paths**: Guided / Autonomous / Delegated\n\nThe plan lives at `workspace/development/plans/[C]{plan-name}-{date}.md` (index) + `fase-*/` folders. You can discuss or implement any item in isolation by pointing to its file.\n\n### Available slash commands\n\n```bash\n# Use slash commands to invoke agents\n/clawdia       # Ops — agenda, emails, tasks, decisions\n/flux          # Finance — Stripe, ERP, cash flow, reports\n/atlas         # Projects — Linear, GitHub, sprints, milestones\n/pulse         # Community — Discord, WhatsApp, sentiment, FAQ\n/pixel         # Social media — content, calendar, analytics\n/sage          # Strategy — OKRs, roadmap, competitive analysis\n/nex           # Sales — pipeline, proposals, qualification\n/mentor        # Courses — learning paths, modules\n/lumen-learning # Learning retention — spaced repetition, fact capture, quizzes\n/kai           # Personal — health, habits, routine\n/oracle        # Entry point — onboarding, business discovery, implementation plan\n/mako          # Marketing — campaigns, content, SEO, brand\n/aria          # HR — recruiting, onboarding, performance\n/zara          # Customer Success — triage, escalation, health\n/lex           # Legal — contracts, compliance, NDA, risk\n/nova          # Product — specs, roadmaps, metrics, research\n/dex           # Data / BI — analysis, SQL, dashboards\n\n# Or just describe what you need — Claude routes to the right agent\n```\n\n---\n\n## Web Dashboard\n\nA full web UI at `http://localhost:8080`:\n\n| Page | What it does |\n|------|-------------|\n| **Overview** | Unified dashboard with metrics from all agents |\n| **Systems** | Register and manage apps/services (Docker, external URLs) |\n| **Reports** | Browse HTML reports generated by routines |\n| **Agents** | View agent definitions and system prompts |\n| **Routines** | Metrics per routine (runs, success rate, cost) + manual run |\n| **Tasks** | Schedule one-off actions (skill, prompt, script) at a specific date/time |\n| **Skills** | Browse all 175+ skills by category (~125 business + 25 dev-*) |\n| **Templates** | Preview HTML report templates |\n| **Services** | Start/stop scheduler, channels (Telegram, Discord, iMessage) with live logs |\n| **Memory** | Browse agent and global memory files |\n| **Knowledge** | Semantic search via [MemPalace](https://github.com/milla-jovovich/mempalace) — index code, docs, and knowledge |\n| **Integrations** | Status of all connected services + OAuth setup |\n| **Chat** | Embedded Claude Code terminal (xterm.js + WebSocket) |\n| **Users** | User management with roles (admin, operator, viewer) |\n| **Roles** | Custom roles with granular permission matrix |\n| **Audit Log** | Full audit trail of all actions |\n| **Config** | View CLAUDE.md, routines config, and workspace settings |\n\n```bash\nmake dashboard-app   # Start Flask + React on :8080\n```\n\n---\n\n## Architecture\n\n```\nUser (human)\n    |\n    v\nClaude Code (orchestrator)\n    |\n    +-- Clawdia   — ops: agenda, emails, tasks, decisions, dashboard\n    +-- Flux      — finance: Stripe, ERP, MRR, cash flow, monthly close\n    +-- Atlas     — projects: Linear, GitHub, milestones, sprints\n    +-- Pulse     — community: Discord, WhatsApp, sentiment, FAQ\n    +-- Pixel     — social: content, calendar, cross-platform analytics\n    +-- Sage      — strategy: OKRs, roadmap, prioritization, scenarios\n    +-- Nex       — sales: pipeline, proposals, qualification\n    +-- Mentor    — courses: learning paths, modules\n    +-- Kai       — personal: health, habits, routine (isolated domain)\n    +-- Oracle    — entry point: onboarding, business discovery, implementation plan\n    +-- Mako      — marketing: campaigns, content, SEO, brand\n    +-- Aria      — HR: recruiting, onboarding, performance\n    +-- Zara      — customer success: triage, escalation, health\n    +-- Lex       — legal: contracts, compliance, NDA, risk\n    +-- Nova      — product: specs, roadmaps, metrics, research\n    +-- Dex       — data/BI: analysis, SQL, dashboards\n```\n\nEach agent has:\n- System prompt in `.claude/agents/`\n- Slash command in `.claude/commands/`\n- Persistent memory in `.claude/agent-memory/`\n- Related skills in `.claude/skills/`\n\n---\n\n## Workspace Structure\n\n```\nevo-nexus/\n├── .claude/\n│   ├── agents/          — 16 agent system prompts\n│   ├── commands/        — 16 slash commands\n│   ├── skills/          — 175+ skills by prefix (~125 business + 25 dev-*) (+ custom)\n│   └── templates/html/  — 2 core + custom HTML templates\n├── ADWs/\n│   ├── runner.py        — execution engine (logs + metrics + notifications)\n│   ├── routines/         — 7 core routine scripts (shipped with repo)\n│   └── routines/custom/  — 20 custom routines (user-created, gitignored)\n├── dashboard/\n│   ├── backend/         — Flask + SQLAlchemy + WebSocket\n│   └── frontend/        — React + TypeScript + Tailwind\n├── social-auth/         — OAuth multi-account app\n├── config/              — workspace.yaml, routines.yaml\n├── workspace/           — user data folders (gitignored content)\n├── setup.py             — CLI setup wizard\n├── scheduler.py         — automated routine scheduler\n├── Makefile             — 44+ make targets\n└── CLAUDE.template.md   — template for generated CLAUDE.md\n```\n\nWorkspace folders (`workspace/daily-logs/`, `workspace/projects/`, etc.) are created by setup — content is gitignored, only structure is tracked.\n\n---\n\n## Commands\n\n```bash\n# Setup \u0026 Dashboard\nmake setup           # Interactive setup wizard\nmake dashboard-app   # Start web dashboard on :8080\n\n\n# Routines\nmake scheduler       # Start automated routine scheduler\nmake morning         # Run morning briefing\nmake triage          # Run email triage\nmake community       # Run community pulse\nmake fin-pulse       # Run financial pulse\nmake eod             # Run end-of-day consolidation\nmake memory-lint     # Run memory health check (contradictions, stale data, gaps)\nmake weekly          # Run weekly review\n\n# Backup \u0026 Restore\nmake backup          # Export workspace data to local ZIP\nmake backup-s3       # Export + upload to S3\nmake restore FILE=\u003cpath\u003e  # Restore from backup ZIP\n\n# Observability\nmake logs            # Show latest JSONL log entries\nmake metrics         # Show per-routine metrics (runs, cost, tokens)\nmake help            # List all available commands\n```\n\n---\n\n## Documentation\n\n| Doc | Description |\n|-----|-------------|\n| [Getting Started](docs/getting-started.md) | Full setup guide |\n| [Architecture](docs/architecture.md) | How agents, skills, and routines work |\n| [ROUTINES.md](ROUTINES.md) | Complete routine documentation |\n| [ROADMAP.md](ROADMAP.md) | Improvement plan and backlog |\n| [CONTRIBUTING.md](CONTRIBUTING.md) | How to contribute |\n| [CHANGELOG.md](CHANGELOG.md) | Release history |\n| `.claude/skills/CLAUDE.md` | Full skill index |\n\n---\n\n## Credits \u0026 Acknowledgments\n\nEvoNexus stands on the shoulders of great open source projects:\n\n- **[oh-my-claudecode](https://github.com/yeachan-heo/oh-my-claudecode)** by **Yeachan Heo** (MIT) — 19 of the 21 engineering agents (including `apex-architect`, `bolt-executor`, `lens-reviewer`) and all `dev-*` skills are derived from OMC v4.11.4. The 2 native agents (`helm-conductor`, `mirror-retro`) and the 6-phase workflow (`.claude/rules/dev-phases.md`) are EvoNexus-native additions. See [NOTICE.md](NOTICE.md) for the full list of derived components and modifications.\n\n---\n\n## License\n\nMIT License. See [LICENSE](LICENSE) for details.\nThird-party attributions are documented in [NOTICE.md](NOTICE.md).\n\n---\n\n\u003cp align=\"center\"\u003e\n  An unofficial community toolkit for \u003ca href=\"https://docs.anthropic.com/en/docs/claude-code\"\u003eClaude Code\u003c/a\u003e\n  \u003cbr/\u003e\n  \u003csub\u003eBuilt by \u003ca href=\"https://evolutionfoundation.com.br\"\u003eEvolution Foundation\u003c/a\u003e — not affiliated with Anthropic\u003c/sub\u003e\n\u003c/p\u003e\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fevolutionapi%2Fevo-nexus","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fevolutionapi%2Fevo-nexus","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fevolutionapi%2Fevo-nexus/lists"}