Build on an AI platform you own
ibl.ai is the agentic AI platform where you own all the code and the data. Its 6 repositories are public on GitHub — the application layer, the SDK, the agent skills and MCP server, and the infrastructure CLI — so you can read the source, scaffold an app, and run the whole stack on your own cloud, on-premise, or fully air-gapped, model-agnostic across any LLM and with no per-seat pricing.
Not an API you rent — a full platform you keep. 1.6M+ users across 400+ organizations run the platform this way, including NVIDIA, MIT, and Syracuse University.
$ npx skills add iblai/vibe$ npx skills add iblai/apiWhich ibl.ai repositories can I read and run myself?
These 6 repositories are the platform. Most AI vendors give you an endpoint; ibl.ai gives you the source you can read, fork, run, and extend — from the app your users touch down to the infrastructure it runs on. Every card below shows the live release straight from GitHub.
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.
Skills-intelligence platform on the same SDK — discover courses, track competencies, and earn credentials. A second complete application you can read end to end.
Scaffold a production-ready Next.js app on ibl.ai — SSO auth, AI chat, profiles, notifications, and analytics wired up out of the box, with pre-built components and Claude Code skills.
$ npx skills add iblai/vibeAgent skills plus a chat MCP server that 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.
$ npx skills add iblai/apiAn interactive CLI that provisions the whole platform on your own AWS or GCP account with Terraform and configures servers with Ansible — and it can bootstrap any existing server.
The documentation source — every page published at ibl.ai/docs, versioned in the open and available for contributions.
How do I drive the ibl.ai platform from code or an agent?
Every capability of the ibl.ai 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, so it never drifts from what the server accepts.
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.
$ npx skills add iblai/apiWhere are the deployment guides for claws and the ontology?
The guides below are mirrored from their own public repositories — self-hosted OpenClaw and NemoClaw servers, the portable .iblai agent format, and the on-premise ontology layer that makes your existing systems queryable by agents over MCP. Each one is generated from the repository, so it cannot drift from the code.
What do I actually own when I build on ibl.ai?
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
1.6M+ users across 400+ organizations run the platform this way, including NVIDIA, MIT, and Syracuse University. ibl.ai is family-owned and operated from New York, NY. Explore the self-hosted platform or the full-code license.
Clone a repo and run it today
On ibl.ai you own all the code and the data, run it model-agnostic across any LLM, and pay with no per-seat pricing — so you can deploy anywhere, from your own cloud to a fully air-gapped network.