\n\n---\n\n## Why WOTANN\n\nMost agent frameworks lock you to a vendor, degrade quietly when a model can't tool-call, and hand you a single UI. WOTANN inverts that. It lives at the layer above inference so your configured lab subscription or API-key provider remains replaceable without moving agent execution off your machine.\n\n| | Most agents | **WOTANN** |\n|---|---|---|\n| **Provider** | Locked to one vendor | **25 providers** via openai-compat router; Anthropic + OpenAI subscriptions OR API keys |\n| **Capabilities** | Tool-calling, vision, thinking gated by model support | **Capability augmentation** normalizes provider capabilities |\n| **Inference economics** | Resold tokens or bundled inference | **BYO subscription or API key**: the user pays the lab |\n| **Memory** | Short-lived prompt context | **8-layer persistent**: SQLite + FTS5 + vector + graph-RAG + episodic + temporal + provenance |\n| **Surfaces** | One UI | **CLI + TUI + Desktop + iOS + Watch + CarPlay + 25 messaging channels** |\n| **Autonomy** | Vibes | **Proof bundles** (tests + typecheck + diff + screenshots) on every completion |\n| **Lock-in** | Total | Zero — swap models mid-session, export all state |\n\n---\n\n## Quick Start\n\n```bash\n# Try without installing (any platform — needs Node 22.13+)\nnpx wotann@latest\n\n# One-line install (macOS or Linux)\ncurl -fsSL https://raw.githubusercontent.com/gabrielvuksani/wotann/main/install.sh | bash\n\n# Windows (PowerShell — see install.ps1)\nirm https://wotann.com/install.ps1 | iex\n\n# Or from npm (any platform)\nnpm install -g wotann\n\n# Initialize a workspace\nwotann init\n\n# Start the always-on engine\nwotann engine start\n\n# Launch the TUI\nwotann\n```\n\n### Windows install\n\nWOTANN runs on Windows 10/11 with Node.js 22.13+. The bash installer above is POSIX-only — Windows users have three supported paths:\n\n```powershell\n# PowerShell one-liner (downloads and runs install.ps1)\nirm https://raw.githubusercontent.com/gabrielvuksani/wotann/main/install.ps1 | iex\n\n# Or from npm (when published) — works on every Node-supported OS\nnpm install -g wotann\n\n# Or run without installing (npx pulls the latest published version)\nnpx wotann@latest\n```\n\nNode.js prerequisite on Windows: `winget install OpenJS.NodeJS.LTS` (Node 22.13+ required). The PowerShell installer enforces this; the npm path surfaces a friendly preflight error on older Node.\n\nAgent execution and trust enforcement run on your machine. Inference uses a provider subscription or API key that you configure; WOTANN does not run local models or silently route prompts to anonymous public endpoints.\n\n```bash\n# Use frontier models when you want them\nexport ANTHROPIC_API_KEY=sk-ant-...\nexport OPENAI_API_KEY=sk-...\nexport GEMINI_API_KEY=AIza...\n\n# ChatGPT/Codex and Claude subscription paths are supported too\nwotann onboard\n```\n\nThere is no anonymous zero-config inference tier. If no authenticated remote processor is configured, WOTANN reports that honestly.\n\n---\n\n## A Minute of WOTANN\n\n```bash\n# Fix failing tests autonomously — with a proof bundle\n$ wotann autonomous \"fix the failing tests in src/memory\"\n [1/8] verification: 3 failing tests detected\n [2/8] strategy: minimal-change (preferred — tests are green-adjacent)\n [3/8] patch: memory/store.ts:441 null-check added, memory/hybrid.ts:88 guard\n [4/8] verification: tests + lint + typecheck all green · 46.01s\n [5/8] proof bundle: artifacts/proof-2026-04-20-133801.tar.gz\n [6/8] crystallize: skill saved as skills/fix-null-check-memory-store.md\n SUCCESS in 3 cycles · $0.42 · 47,000 tokens\n\n# Compare three models blind, side-by-side\n$ wotann arena \"refactor this function for readability\"\n ─── A ────────── ─── B ────────── ─── C ──────────\n [Opus output] [GPT-5.4 output] [Gemini 3 Pro output]\n Blind choice: B (revealed: GPT-5.4)\n\n# Same conversation, phone tap\n$ wotann link\n Scan QR on iPhone. Token transferred via ECDH. Session mirrored.\n```\n\n---\n\n## Headline Capabilities\n\n### Provider freedom (the moat)\n\nRemote providers share one router with authenticated fallback chaining: `preferred → other configured remote processors`. Local runtimes and anonymous endpoints are excluded from executable fallback. If configured processors exhaust, WOTANN reports that honestly.\n\nRuntime providers can be added without editing source: drop a strict `provider.json` under `.wotann/providers/![\"CI\"](\"https://github.com/gabrielvuksani/wotann/actions/workflows/ci.yml/badge.svg\"){kind=icon}
\n ![\"MIT](\"https://img.shields.io/badge/license-MIT-blue.svg\"){kind=icon}
\n ![\"Node](\"https://img.shields.io/badge/node-%E2%89%A522.13-43853d.svg?logo=node.js&logoColor=white\"){kind=icon}
\n ![\"Platforms\"](\"https://img.shields.io/badge/macOS%20%C2%B7%20Linux%20%C2%B7%20Windows%20%C2%B7%20iOS-supported-555.svg\"){kind=icon}
\n ![\"25](\"https://img.shields.io/badge/providers-25-0A84FF.svg\"){kind=icon}
\n ![\"25+](\"https://img.shields.io/badge/channels-25%2B-0A84FF.svg\"){kind=icon}
\n ![\"tests](\"https://img.shields.io/badge/tests-passing-green.svg\"){kind=icon}
\n ![\"wotann.com\"](\"https://img.shields.io/badge/wotann.com-Norse%20themed-8B5CF6.svg\"){kind=icon}
\n ![\"AAIF](\"https://img.shields.io/badge/AAIF-Agentic%20AI%20Foundation-0094FF.svg\"){kind=icon}
\n