Introduction
What OrgInaBox is, who it's for, and how it works.
OrgInaBox — Enterprise AI Workforce Platform
OrgInaBox (OIAB) gives every employee in your organisation their own team of autonomous AI agents. Agents live inside sandboxed VMs, communicate over channels your team already uses (Slack, Teams, email, iMessage, Telegram), and execute long-running tasks while you focus on higher-level work.
Key Concepts
| Concept | Description |
|---|---|
| Sandbox | Each user gets an isolated Ubuntu VM running opencode serve. Agents execute tools (bash, file edit, browser) inside that sandbox — nothing touches the host. |
| Channel Gateway | Inbound messages from Slack / Teams / Telegram / email are routed through a gateway into the job queue, which dispatches an agent-turn job. |
| Job Queue | PostgreSQL-backed queue with SELECT FOR UPDATE SKIP LOCKED. LISTEN/NOTIFY wakes the drainer immediately when a new job lands. |
| Memory | pgvector stores 1536-dim embeddings per memory. system.transform injects the top-K semantically-similar memories into each agent turn. |
| Orchestrator | An LLM decomposes complex tasks into parallel sub-tasks with a dependency graph. Each sub-task runs in its own session. A synthesis step combines all results. |
| Learning Loop | After each session, a reflection LLM extracts a trajectory hash. Three similar trajectories auto-propose a reusable skill. Admins promote skills to make them available globally. |
| RBAC | Four system roles (owner / admin / member / viewer) map to structured permission objects. Azure AD groups auto-map to roles on first login. |
When to Use OIAB
- You want every employee to have an AI agent accessible through existing channels
- You need SOC 2-style audit logs of every tool call, memory read, and auth event
- Your organisation is on Azure / Microsoft 365 and wants seamless SSO
- You want parallel multi-task execution — not just a single chat thread
Navigation
- Quick Start — Up and running in 5 minutes with Docker Compose.
- Features — Deep-dives on every major feature.
- Architecture — Database schema, component topology, data flows.
- API Reference — Every REST endpoint with request/response shapes.
- Deployment — Azure Container Apps, Bicep IaC, CI/CD pipeline.
- Changelog — Release notes for every version.