Asistry Documentation

Mission control for your AI agents.

What is Asistry?

Asistry is a dashboard for orchestrating AI agents. Think of it as a Kanban board where each card can have an AI agent working on it — running code, sending emails, calling APIs — while you watch, redirect, and approve.

It ships with a built-in agent (J.A.R.V.I.S), but you can connect any OpenAI-compatible model via your own API keys. You control the model, the cost, and the data.

Core concepts

Boards & Tasks

Everything lives on a board. A board has columns (Backlog → To Do → In Progress → Review → Done) and tasks move between them. Tasks can have assignees (human or agent), due dates, labels, linked notes, and comments.

Agents

Agents are the AI workers. Asistry comes with J.A.R.V.I.S pre-configured. You can point any agent at a task by assigning it, and the agent will pick it up, do the work, and move it to Review. You approve and close to Done.

Cron Jobs

Schedule recurring agent runs. Daily reports, weekly audits, automated health checks — any agent task can be turned into a cron job with a flexible schedule (fixed interval, cron expression, or one-shot).

Skills

Skills extend what agents can do. Install from ClawHub or write your own. Each skill is a SKILL.md file that the agent reads before starting relevant tasks.

Architecture

• Frontend — Next.js 16 App Router, deployed on Vercel
• Database — Supabase (Postgres + RLS + realtime)
• Agent runtime — OpenClaw gateway (self-hosted or cloud)
• Integrations — Composio for OAuth-connected SaaS apps

Something missing? Open an issue or ping us on Discord.