Self-host ibl.ai/os
v0.182.2Open-source AI agent platform for building agents
- Stars
- 793
- Ports
- 3000 (Development server), 5000 (Docker production server), 3001 (Alternative development port)
- Requires
- ASGI/WebSocket Server, ibl.ai API Gateway, ibl.ai Auth Service, LiveKit server
What is ibl.ai/os?
ibl.ai/os is the open-source frontend for the ibl.ai platform, giving organizations a way to build and run their own AI agents. The software works with many LLM providers and includes real-time chat, voice conversations through LiveKit WebRTC, screen sharing, retrieval-augmented generation for document training, Model Context Protocol server support, analytics dashboards, multi-tenancy with per-organization branding, single sign-on via OAuth/OIDC/SAML, role-based access control, Stripe billing, iframe embedding, API access, and white-labeling options. One codebase delivers a web application (deployable via Docker or as a standalone Node.js server), native desktop applications for macOS, Windows, and Linux, native mobile applications for iOS and Android, and a Chrome side-panel extension. Running it yourself requires the separate ibl.ai backend (authentication, API gateway, LiveKit, ASGI) which is not part of this repository; the frontend connects through environment variables. The code is MIT-licensed and receives frequent updates.
Should you self-host ibl.ai/os?
ibl.ai/os scores 55/100 on selfhost.directory (how scoring works) and ranks #65 of 209 in AI Agents. It has 793 GitHub stars.
It shipped 10 stable releases in the past year. The latest, v0.182.2, came out on 27 October 2026.
Setup is advanced: plan for several services and some ongoing maintenance. It is MIT-licensed and written mostly in Typescript.
Its closest alternative on selfhost.directory is Orca (91/100, 108 446 stars). It scores higher overall, so compare the two before you pick. See ibl.ai/os vs Orca side by side.
Features
- AI Agents
- Analytics
- Canvas / Artifacts
- Deep Research
- Embed & API
- MCP Servers
- Multi-tenancy
- Projects
- RAG Training
- Screen sharing
- SSO & RBAC
- Stripe Billing
- Voice calls
- Web Search
- Whitelabeling
ibl.ai/os README
More in AI Automation
JobNavigatorJobNavigator is a self-hosted job automation platform that scrapes career pages, scores jobs with AI, tailors résumés and cover letters, auto-fills applications.
LeastActionLeastAction is a self-hosted data workflow platform where an AI operator runs and repairs pipelines end-to-end against your stack with a shared team catalog.
librefangLibreFang is a self-hosted, open-source Agent OS in Rust running autonomous AI agents 24/7 with 17 Hands, 44 channels, and 57 LLM providers.
LimeJourneySelf-hosted open-source platform for AI-driven user journeys, visual builder, dynamic segmentation, and BYOI integrations — a Customer.io alternative.
LocalAGIA self-hosted, open-source platform for building local AI agents and chat bots with a web UI, RAG knowledge base, skills, MCP, and OpenAI Responses-compatible APIs.
local-ai-home-assistantNova Assistant is a self-hosted, open-source AI operations console for Home Assistant automation using local LLMs via Ollama.
MachinaOSSelf-hosted open-source AI organisation with six specialised employees owning business functions end-to-end. Token budget, bring your own model keys.
markusSelf-hosted open-source AI workforce platform running autonomous agent teams locally with your own API keys.
microclawSelf-hosted Rust agent platform with Server, Work desktop app, and SDK sharing one Agent Engine for multi-step tools, memory, and chat automation.
MindRoomSelf-hosted AI agent platform with persistent memory, 100+ tool integrations, and Matrix-based chat. Run locally or on your servers with local or cloud models per agent.
model-composemodel-compose is a self-hosted, open-source tool for building AI pipelines in YAML with local/cloud models, streaming, Gradio UI, and Docker deployment.
muxiMUXI is a self-hosted, open-source AI application server that lets you declare AI agents in YAML as deployable formations, then run them with a single command.





0 comments