# @yuuki-co/ai-portal > Multi-user AI sharing portal & CLI — Claude Code, Cursor, and IDE gateway Latest version **1.0.1** (published 2026-09-24) · MIT license · 0 weekly downloads ## Install ```sh npm install @yuuki-co/ai-portal pnpm add @yuuki-co/ai-portal yarn add @yuuki-co/ai-portal bun add @yuuki-co/ai-portal ``` Provides the command `ai-portal`. ## Health **Score 60/100 (C)** — status: active. Positive: esm support; no vulnerabilities; recently updated; high maintenance score. Warnings: low downloads; no types. ## Facts | | | |---|---| | Version | 1.0.1 | | Published | 2026-09-24 | | First published | 2026-09-24 | | Weekly downloads | 0 | | License | MIT | | TypeScript types | none | | Module format | ESM + CommonJS | | Node | >=20.0.0 | | Dependencies | 23 | | Unpacked size | 41.5 KB | | Known vulnerabilities | 0 | | Install scripts | no | | Maintainers | aditya253 | | Keywords | ai-portal, claude-code, cursor, gateway, anthropic, azure-foundry, openrouter | ## Links - npm: https://www.npmjs.com/package/@yuuki-co/ai-portal - Repository: https://github.com/Yuuki-Co/ai-portal - Homepage: https://github.com/Yuuki-Co/ai-portal#readme - Issues: https://github.com/Yuuki-Co/ai-portal/issues - npm.io page: https://npm.io/package/@yuuki-co/ai-portal ## Dependencies (23) - [pg](https://npm.io/package/pg.md) ^8.23.0 - [zod](https://npm.io/package/zod.md) ^3.24.4 - [uuid](https://npm.io/package/uuid.md) ^11.1.0 - [bullmq](https://npm.io/package/bullmq.md) ^5.51.0 - [helmet](https://npm.io/package/helmet.md) ^8.2.0 - [marked](https://npm.io/package/marked.md) ^15.0.12 - [openai](https://npm.io/package/openai.md) ^4.96.0 - [express](https://npm.io/package/express.md) ^4.21.2 - [ioredis](https://npm.io/package/ioredis.md) ^5.6.1 - [bcryptjs](https://npm.io/package/bcryptjs.md) ^2.4.3 - [playwright](https://npm.io/package/playwright.md) 1.61.1 - [highlight.js](https://npm.io/package/highlight.js.md) ^11.11.1 - [connect-redis](https://npm.io/package/connect-redis.md) ^8.0.2 - [better-sqlite3](https://npm.io/package/better-sqlite3.md) ^11.8.1 - [@bull-board/api](https://npm.io/package/@bull-board/api.md) ^6.7.0 - [express-session](https://npm.io/package/express-session.md) ^1.18.1 - [marked-highlight](https://npm.io/package/marked-highlight.md) ^2.2.4 - [playwright-extra](https://npm.io/package/playwright-extra.md) ^4.3.6 - [@anthropic-ai/sdk](https://npm.io/package/@anthropic-ai/sdk.md) ^0.39.0 - [@bull-board/express](https://npm.io/package/@bull-board/express.md) ^6.7.0 - [@google/generative-ai](https://npm.io/package/@google/generative-ai.md) ^0.21.0 - [@modelcontextprotocol/sdk](https://npm.io/package/@modelcontextprotocol/sdk.md) ^1.30.0 - [puppeteer-extra-plugin-stealth](https://npm.io/package/puppeteer-extra-plugin-stealth.md) ^2.11.2 ## Alternatives - [express-promise-router](https://npm.io/package/express-promise-router.md) — 736.1K weekly downloads - [next-usequerystate](https://npm.io/package/next-usequerystate.md) — 29.8K weekly downloads - [@bitkyc08/opencodex](https://npm.io/package/@bitkyc08/opencodex.md) — 4.6K weekly downloads - [lynkr](https://npm.io/package/lynkr.md) — 575 weekly downloads - [baremetal.js](https://npm.io/package/baremetal.js.md) — 42 weekly downloads ## Recent versions - 1.0.1 (latest) — 2026-09-24 - 1.0.0 — 2026-09-24 ## README # AI Portal A self-hosted, multi-user portal that gives a team shared access to AI subscriptions — Claude, Gemini, OpenAI, and others — through one chat UI and an admin console. Supports both direct API providers and browser-automated providers (for services without a usable API), per-user access control, multi-tenant orgs, usage tracking, and a job queue for concurrent requests. ## Architecture Two long-running processes, one shared SQLite DB, Redis as the connective tissue: ``` ┌────────────────────────┐ Browser ───────────▶│ server/index.js │◀── serves dist/ or pages/ (Vite dev/prod UI) │ Express API server │ │ │ │ requireLogin/Admin ──┐ │ │ routes/*.js ◀────────┘ │ └───────┬─────────┬───────┘ │ │ inline job │ │ enqueue (API providers) (browser provs) │ ▼ │ ┌─────────────┐ ┌──────────────┐ │ │ Redis │◀────▶│ queue/worker │ │ │ (sessions + │ │ .js │ │ │ BullMQ) │ └──────┬───────┘ │ └─────────────┘ │ ▼ ▼ ┌────────────────────────────────────────────┐ │ providers//*Provider.js │ │ API providers (Anthropic/OpenAI/Gemini/…) │ │ Browser providers (Playwright + Chromium) │ └───────────────────┬──────────────────────────┘ ▼ ┌───────────────────┐ │ data/portal.db │ (SQLite: conversations, │ (better-sqlite3) │ messages, jobs, usage_log, published_shares) └───────────────────┘ ``` - **API server** (`server/index.js`) — auth, UI serving (dev/production), job submission, SSE streaming; runs browser-provider jobs inline. - **Worker** (`server/queue/worker.js`) — separate process; pulls API-provider jobs off a per-user BullMQ queue in Redis. - **Vite Frontend** — built from `pages/` and `src/` into the `dist/` directory. Serve `dist/` in production; Vite dev server handles HMR on port 5110 (governed port assignment for Anand's local development). - **Graceful degradation** — if Redis is down, API jobs fall back to inline execution in the API process. No Redis required to run it locally, just to scale it. For the full module-by-module map (every file in `server/`, the job data-flow, the role hierarchy, browser-automation internals, tiered sharing) see **[CONTEXT.md](docs/CONTEXT.md)** — that document is the detailed architecture reference this README summarizes. ## Quick start (local dev) Requires Node ≥ 20 and, ideally, a local Redis (optional — see above). ```bash cp .env.example .env # see "Environment" below npm install node scripts/add-user.js admin password admin # Start API server, worker, and Vite dev server: npm run dev:full # → http://localhost:5110 (Vite frontend with API proxy to 3040) ``` Other useful scripts (from `package.json`): | Command | What it does | |---|---| | `npm run dev:full` | Launches server, worker, and Vite frontend watcher concurrently (port 5110) | | `npm run build` | Compiles TypeScript and runs Vite production build (`tsc && vite build`) | | `npm run dev` | API server only (port 3040), auto-restart on change | | `npm run dev:worker` | Worker only, auto-restart on change | | `npm run start:all` | Production start for server and worker processes (requires built frontend) | | `npm run add-user` | CLI: create a user (`node scripts/add-user.js [role]`) | | `npm run add-subscription` | CLI: register a provider subscription | | `npm run migrate` | Apply pending SQLite schema migrations | | `npm run validate:skills` | Validate web-module skill definitions | ## Environment setup Copy `.env.example` to `.env` and fill in what you need. Everything not listed below is optional and provider-specific. | Variable | Required? | Notes | |---|---|---| | `SESSION_SECRET` | **Yes** | `openssl rand -base64 32`. The app has an insecure random fallback for convenience in dev — **never rely on it in production** (see [REMEDIATION.md](docs/REMEDIATION.md) S7). | | `REDIS_URL` | Recommended | Default `redis://localhost:6380`. Without it: sessions and queues degrade to in-process/inline behavior — fine for a single-instance dev box, not for production. | | `PORT` | No | Default `3040`. | | `*_API_KEY` (`ANTHROPIC_API_KEY`, `OPENAI_API_KEY`, `GEMINI_API_KEY`, …) | Only for providers you use | See `.env.example` for the full list. Per-subscription keys (via the admin console) take priority over these env fallbacks. | | `METRICS_TOKEN` | No | Bearer token to expose `/metrics` to something other than localhost (Prometheus scraping). | | `NODE_ENV=production` | Production only | Also gates the session cookie's `secure` flag — see [REMEDIATION.md](docs/REMEDIATION.md) S7 before deploying. | For provider-specific browser-automation setup (Chromium sessions, Xvfb on a headless VPS) and the full production deployment walkthrough, see **[DEPLOY.md](docs/DEPLOY.md)**. ## Project layout ``` server/ index.js Express entry point — mounts every route in routes/ auth/ Session guards, role/permission checks, org scoping db/ SQLite connection + schema.sql providers/ One folder per AI provider (API-based and browser-based) queue/ BullMQ queue + worker + per-user queue logic router/ Query classification / smart model routing routes/ ~20 Express routers — one per API surface web-module/ Browser-automation engine, SSRF guard, site adapters pages/ Source HTML templates for the Vite pages src/ Frontend TypeScript source code (chat UI, admin panels, shared) dist/ Production bundled frontend (output of `npm run build`) public/ Static assets (robots.txt, images, global CSS fallback) scripts/ CLI utilities (add-user, add-subscription, migrate, …) data/ Runtime state — gitignored (SQLite DB, session data, JSON configs) docs/adr/ Architecture Decision Records — the "why" behind key choices ``` See [CONTEXT.md](docs/CONTEXT.md) for a file-by-file breakdown of every path above. ## Further reading | Doc | What's in it | |---|---| | [CONTEXT.md](docs/CONTEXT.md) | Full architecture reference — every module, the job data-flow, role hierarchy, browser-automation internals | | [DEPLOY.md](docs/DEPLOY.md) | Production VPS/Docker deployment walkthrough | | [USER_GUIDE.md](docs/USER_GUIDE.md) | End-user and administrator guide to the product itself | | [ROADMAP.md](docs/ROADMAP.md) | Planned work, phased | | [docs/adr/](docs/adr) | Why the system is built the way it is — dual persistence, SQLite, browser automation, org/role model | | [REMEDIATION.md](docs/REMEDIATION.md) | Tracked findings from a technical due-diligence review — known gaps and their fixes, ranked by priority | ## Status Under active development. Several subsystems (multi-tenant orgs, per-user queues, additional providers, smart routing, groups) are implemented but not yet fully hardened for production multi-tenant use — see [REMEDIATION.md](docs/REMEDIATION.md) before deploying this beyond a trusted, single-team setting. --- _Source: https://npm.io/package/@yuuki-co/ai-portal · Machine-readable twin of the npm.io package page. Health data is recomputed on every publish._