Skip to content

README.md

Latest commit

 

History

History
348 lines (230 loc) · 15 KB

README.md

File metadata and controls

348 lines (230 loc) · 15 KB
Raw

ibl.ai

ibl.ai/os

The open-source AI agent platform.

Build, deploy, and manage intelligent conversational agents — from prototype to production, in minutes. One codebase. Every platform. Your code, your data, any LLM.

Join About Docs License: MIT SOC 2 Type II


⬇️ Get ibl.ai/os

Use it on the Web   Download for macOS   Download for Windows

Download for iOS   Download for Android

Windows ARM64 · older builds · Linux → all downloads


Watch the demo

▶︎ Watch the demo  ·  by Miguel Amigot, CTO at ibl.ai


Why ibl.ai/os · Every platform · Features · Case studies · Screenshots · Quick Start · Deployment

SOC 2 Type II  ·  Universities, enterprises, and governments run on ibl.ai — read the case studies →

Why ibl.ai/os
🔓 Your code, your data MIT-licensed and self-hostable. No vendor lock-in — full ownership of the stack and everything that flows through it.
🧠 Any LLM, your choice Bring OpenAI, Anthropic, Google, Microsoft, Meta, or your own models. Switch providers without rewrites.
📱 Truly everywhere One codebase ships as web, macOS, Windows, Linux, iOS, and Android — with near-native performance.
🏢 Enterprise-ready Multi-tenancy, SSO, RBAC, Stripe billing, and whitelabeling built in — not bolted on later.

Every platform, one codebase

Most AI apps make you choose a device. ibl.ai/os meets your users wherever they are — the same product, native everywhere.

Platform Status
Web 🌐 Live at os.ibl.ai — any modern browser
macOS 🍎 Native app — download universal .dmg (Intel + Apple Silicon, signed & notarized)
Windows 🪟 Native app — download installer (x64 + ARM64)
iOS 📱 Native app — App Store
Android 🤖 Native app — Google Play
Linux 🐧 Native app — build from source

Features

🤖 Build & customize

  • AI Agents — configurable LLMs, system prompts, tools, and safety filters
  • Projects — collaborative workspaces with shared context and goals
  • Canvas / Artifacts — generate, edit, and version rich documents alongside chat
  • MCP Servers — extend agents with Model Context Protocol tool servers

📚 Ground in your data

  • RAG Training — upload docs, connect Google Drive / OneDrive / Dropbox, or crawl sites
  • Web Search — ground responses with live web results
  • Deep Research — extended multi-step reasoning for complex queries

🎙️ Rich conversations

  • Voice Calls — real-time WebRTC voice chat powered by LiveKit
  • Screen Sharing — share your screen directly inside a session

🏢 Operate & scale

  • Analytics — usage dashboards, topic analysis, transcripts, financial reporting
  • Multi-tenancy — full tenant isolation, per-org branding & user management
  • SSO & RBAC — OAuth / OIDC / SAML with granular role-based access
  • Stripe Billing — subscriptions, free trials, usage-based pricing
  • Embed & API — iframe embed mode, custom domains, and API keys
  • Whitelabeling — custom branding, logos, and disclaimers

Case studies

Universities, enterprises, and government agencies build on ibl.ai — deploying agents on their own infrastructure, with their own models, at a fraction of the cost of closed platforms.

Read the case studies →

Screenshots

Agent Configuration

Agent configuration — dial in LLMs, prompts, safety filters, and conversation starters



Agent Settings
Agent settings — identity, description, and appearance		 MCP Connectors
MCP connectors — GitHub, Notion, Slack, and more
Memory Settings
Memory — knowledge gaps, learning goals, preferences		 Agent Discovery
Discovery — visibility, access permissions, and LTI

Quick Start

git clone https://github.com/iblai/os.git
cd os
pnpm install

Using Claude Code? Run /setup — it walks you through connecting your ibl.ai tenant and configuring .env.local automatically.

Manual setup: Copy .env.example to .env.local, then set NEXT_PUBLIC_MAIN_TENANT_KEY to your org key from login.iblai.app/me.

cp .env.example .env.local   # then edit NEXT_PUBLIC_MAIN_TENANT_KEY
pnpm dev

Open http://localhost:3000. See the full Development Guide for environment variables, scripts, and architecture details.

Deployment

ibl.ai/os is the frontend for the ibl.ai platform. Choose your path based on your backend setup:

Option A: Existing ibl.ai Tenant

If you already have an ibl.ai tenant (organization key):

  1. Configure your tenant

    cp .env.example .env.local

    Update these values with your tenant details:

    NEXT_PUBLIC_TENANT=your-tenant

  2. Deploy with Docker (recommended)

    docker build -t os .
docker run -p 5000:5000 --env-file .env.local os

    Or deploy standalone:

    pnpm build
PORT=3000 node server-wrapper.js

    The build emits a self-contained server under .next/standalone/ (Next.js standalone output). next.config.ts pins outputFileTracingRoot to the project directory so the output always lands at .next/standalone/server.js with its static assets alongside it. See Troubleshooting if the app loads to a blank screen.

Option B: Enterprise Deployment

If you need full backend infrastructure:

  1. Get an enterprise license

    Reach out at ibl.ai/contact to get a license of the enterprise platform (full backend codebase).

  2. Deploy with our infra CLI

    If you already have access to our Docker images, deploy them easily via iblai/iblai-infra-cli.

Note: ibl.ai/os requires the ibl.ai backend platform for authentication, AI agent APIs, and data services. The backend is not included in this repository — visit ibl.ai to get started.

Desktop & Mobile

See docs/development.md for native app build instructions.

Full deployment docs: Docker & Standalone

Build-Time Configuration

The native (Tauri) app reads two optional build-time flags. Because they're baked in at compile time (Rust's option_env!), you set them as environment variables in the build shell before pnpm exec tauri build — so the same codebase can produce differently-configured builds from the same app URL (e.g. one build locked to tenant A, another to tenant B).

Env var Tauri command Default Effect
IBL_TENANT get_locked_tenant → string "" (unlocked) Tenant lock. When set, the app forces every user onto this tenant — logging out of any other tenant it finds — and hides the tenant switcher. Empty = multi-tenant.
IBL_ALLOW_IN_APP_PURCHASE allow_in_app_purchase → bool false Enables in-app purchase UI. Truthy values: 1, true, yes, on (case-insensitive). 
# a build locked to the "acme" tenant with in-app purchase enabled
IBL_TENANT=acme IBL_ALLOW_IN_APP_PURCHASE=true pnpm exec tauri build

In CI, set them as env on the build step. src-tauri/build.rs declares cargo:rerun-if-env-changed for both, so cargo recompiles whenever a value changes between builds. Leaving them unset yields a standard, unlocked build.

Troubleshooting

The app loads to a blank page or stays stuck on the loading spinner (no redirect to login).

Open your browser's DevTools → Network tab and reload. If every request under /_next/static/... and /env.js returns 404/503, the server isn't finding its static assets. Two common causes:

  • A duplicate or stale server is bound to the port. An older node/next process from a previous run can keep listening on :3000 and shadow the new one (a process bound to a specific address such as 127.0.0.1 wins over a wildcard bind). Find and stop strays before starting fresh:

    lsof -nP -iTCP:3000 -sTCP:LISTEN   # list listeners on the port
kill <PID>                         # stop the stale one

  • The standalone output was nested under an unexpected path. Next.js infers the file-tracing root from the nearest lockfile. A stray lockfile in a parent directory (e.g. ~/package-lock.json) makes it treat your home directory as the workspace root and emit the server at .next/standalone/<path-to-project>/server.js instead of .next/standalone/server.js — post-build.sh then copies static assets next to the wrong path and server-wrapper.js can't find the server. This repo pins outputFileTracingRoot in next.config.ts to prevent it; if you still hit nesting, remove the stray parent lockfile and rebuild.

Testing

This project is covered by Playwright end-to-end tests in e2e/. Run the E2E suite for any change so nothing regresses:

make e2e-ui

make e2e-ui launches Playwright in interactive UI mode — watch the journeys run, step through them, and re-run individual tests. The first time, install the browsers once:

make e2e-install

Other useful targets:

Command What it does
make e2e Run the full suite headless (all browsers)
make e2e-headed Run with a visible browser
make e2e-chrome Run on Chrome only
make e2e-journey J=01 Run a single journey spec
make e2e-report Open the last HTML report

See e2e/COVERAGE.md for current coverage. Coverage must not regress — add or update a journey whenever you change user-facing behavior.

Contributing

We welcome contributions! Please see CONTRIBUTING.md for guidelines. If you'll be working with AI-assisted tooling, read AGENTS.md first — it documents the formatting, lint, and push protocol rules that the husky hooks enforce.

Resources

License

MIT License. See LICENSE for details.


ibl.ai · Your organization's AI, under your control.