# Build on an AI platform you own *Source: https://ibl.ai/developer* For Developers ibl.ai is open source from the application layer to the infrastructure. Read the code, scaffold an app, drive the whole system through skills and an MCP server, deploy agents, and run it on your own cloud. Not an API you rent — a full platform you keep. What you build is yours. - Explore the source on GitHub: https://github.com/iblai - Read the API reference: /docs/api-reference - Deploy in your own cloud: https://github.com/iblai/infra-cli Quickstart: ``` $ npx skills add iblai/vibe $ npx skills add iblai/api ``` ## Five repositories, one platform you own Most AI vendors give you an endpoint. ibl.ai gives you the entire stack as source you can read, fork, run, and extend — from the app your users touch down to the infrastructure it runs on. ### iblai/os — Application layer The open-source platform itself. Create and deploy customizable AI agents with multi-LLM support, real-time chat and voice, document training, analytics, user management, SSO, and embeddable widgets. Built on React 19. TypeScript · React 19 · the app layer you fork and own. Powers Agentic OS (/product/agentic-os). Repository: https://github.com/iblai/os ### iblai/vibe — Build Vibe-code AI apps on ibl.ai. Scaffold a production-ready Next.js app with the iblai-app-cli and the @iblai/iblai-js SDK — SSO auth, AI chat, profiles, notifications, and analytics wired up against a hosted backend. Ships pre-built components and Claude Code skills. JavaScript · SDK + CLI + Claude Code skills. Powers Agentic Vibe (/product/agentic-vibe). Command: `npx skills add iblai/vibe` Repository: https://github.com/iblai/vibe ### iblai/api — Operate Agent skills plus a chat MCP server to operate the entire platform through its REST API. Point Claude Code — or any MCP client — at it and your agent can create agents, manage users, and run workflows directly. Agent skills + Model Context Protocol server. Command: `npx skills add iblai/api` Repository: https://github.com/iblai/api ### iblai/claws — Agents Ready-to-deploy agent templates (NVIDIA NemoClaw + OpenClaw) across regulated sectors — healthcare, government, legal, financial services, education, and more. Run them on your ibl.ai instance or anywhere else. 160+ templates organized by vertical. Repository: https://github.com/iblai/claws ### iblai/infra-cli — Infrastructure An interactive CLI that provisions the whole platform on your own AWS account with Terraform and configures servers with Ansible — and it can bootstrap any existing server. You own the infrastructure. Python · Terraform + Ansible · your cloud. Repository: https://github.com/iblai/infra-cli ## A REST API for everything — and an MCP server to drive it Every capability of the platform is a documented REST endpoint: agents, chat, users, analytics, documents, and credentials. Build integrations against it directly, or let an AI agent operate it for you through the Model Context Protocol. ### Interactive API reference Browse the full endpoint catalog with per-endpoint curl examples — generated from the live OpenAPI schema. - API reference: /docs/api-reference - OpenAPI schema (JSON): https://ibl.ai/api/docs-schema - Base: platform.iblai.app ### Skills & MCP server Install the platform skills and your coding agent can run the whole system — create agents, manage users, trigger workflows — from Claude Code or any MCP client. Command: `npx skills add iblai/api` ## Start from 160+ agent templates The claws library ships ready-to-deploy agents — built on NVIDIA NemoClaw and OpenClaw — organized by sector. Clone one, point it at your data and models, and run it on your ibl.ai instance or anywhere else. Sectors: Healthcare, Government, Legal, Financial Services, Higher Education, K-12, Enterprise, Small Business. - github.com/iblai/claws: https://github.com/iblai/claws - See agents by solution: /solutions/enterprise ## Own what you build A store of value, not a subscription. Rented AI is a cost that recurs forever and leaves nothing behind. An owned platform is an asset: the code, the data, and the infrastructure are yours, and they keep their value after the contract ends. Rented AI: - Per-seat or per-token billing that scales with headcount - Locked to one vendor's models and roadmap - Your data lives in someone else's cloud - Credits evaporate when the subscription lapses ibl.ai — owned: - Full source under a perpetual license - Model-agnostic — run any LLM, switch anytime - Code, data, and infra stay in your environment - Usage-based, never per-seat — yours to keep ibl.ai serves 1.6M+ users from 400+ organizations and is family-owned and operated from New York, NY. Explore the self-hosted platform (/self-hosted-ai) or the full-code license (/full-code-license). ## Clone a repo and run it today Everything on this page is public. Start with the source, scaffold an app, or talk to us about deploying the whole platform on infrastructure you own. - github.com/iblai: https://github.com/iblai - Book a technical demo: https://cal.com/iblai/30min ## Developer FAQ ### Is ibl.ai actually open source? Yes — and we like to be precise about it. The application layer (iblai/os), the developer toolkit and SDK (iblai/vibe), the platform skills and MCP server (iblai/api), the infrastructure CLI (iblai/infra-cli), and the agent templates (iblai/claws) are all public on GitHub. Read them, fork them, and run them yourself — this page links each repository directly. There is one core platform component that isn't public open source. You can use it as a fully managed, hosted service, or take it under a perpetual source-code license and self-host the entire stack. Either way the principle is the same: you keep full ownership of your code, your data, and your deployment — nothing is locked away from you. Want to see exactly where every line is drawn? Talk to us and we'll walk you through the whole architecture. ### How do I start building on ibl.ai? Scaffold a production-ready Next.js app with the vibe toolkit — SSO auth, AI chat, profiles, notifications, and analytics are wired up against a hosted backend out of the box. Then add the platform skills with `npx skills add iblai/api` to drive the whole system from Claude Code or any MCP client, and deploy agents from the claws template library. ### What is the ibl.ai API, and where is the reference? ibl.ai exposes a full REST API for the platform — agents, chat, users, analytics, documents, credentials, and more. The interactive API reference lives at /docs/api-reference, the OpenAPI schema is served at /api/docs-schema, and the production API base is platform.iblai.app. ### What are agent skills and the MCP server? The iblai/api repository ships agent skills plus a Model Context Protocol (MCP) server, so an AI agent can operate the entire ibl.ai platform through its REST API. Install them with `npx skills add iblai/api` and your coding agent can create agents, manage users, and run workflows directly. ### Can I run the whole platform on my own infrastructure? Yes. iblai/infra-cli is an interactive CLI that provisions the platform on your own AWS account with Terraform and configures servers with Ansible — and it can bootstrap any existing server. You own the code, the data, and the infrastructure: cloud, VPC, on-premise, or fully air-gapped. ### Which LLMs can I use? ibl.ai is model-agnostic. Run any LLM — Claude, GPT, Gemini, Llama, Mistral, Qwen, or your own fine-tune — and switch per workload without rebuilding your application. You are never locked to a single vendor's models. ### What does it cost, and what do I actually own? Instead of per-seat SaaS, ibl.ai is usage-based or a flat perpetual license. What you build is a durable asset you own outright — not credits that evaporate when a subscription lapses. ibl.ai serves 1.6M+ users from 400+ organizations and is family-owned and operated from New York, NY.