Agents — custom AI agents with role, skills, and memory
Use built-in templates or create custom agents with their own role, skills, instructions, and memory across the app.
Build your AI team
Launch specialists for coding, research, QA, and operations in one shared workspace.


Create your own agents
Create your own agents with a name, role, instructions, and category.


Skills and memory
Add skills and memory so each agent keeps context and follows its role.


Use agents across the app
Use the same agents in threads, tasks, and automations across the app.


Built in templates
Start with ready made agents for coding, QA, security, research, and analytics.
Which agent CLIs and GUI Lifetime plan does Aiola support?
Aiola supports five agent CLIs: Claude Code, Codex, Cursor, Grok CLI (including grok-4.5), and OpenCode.
GUI Lifetime is available now at launch pricing: first 10 customers $49, next 30 $89, then $129. One-time payment.
Your code and repos stay on your machine. Agent prompts and file context are sent only to the AI provider you choose — Anthropic (Claude Code), OpenAI (Codex), Cursor, xAI (Grok CLI), or whichever provider you configure in OpenCode — under your own subscription. Aiola never proxies, stores, or resells your code or model traffic. Threads, tasks, notes, and automations are stored locally (SQLite + plain files in your repo). If you use the optional analytics/logs/feedback layer for your shipped products, that telemetry is ingested via Aiola's cloud (Supabase/Tinybird). Offline: agent orchestration UI works offline; running agents requires provider access; GUI Lifetime keeps the local app opening even if Aiola's servers are unreachable.
Frequently asked questions
What are agents in Aiola?
Built-in templates or custom agents, each with its own role, skills, instructions, and memory, usable across the app.
Which providers back an agent?
Claude Code, Codex, Cursor, Grok CLI, or OpenCode — your own provider access.
Can agents remember context?
Yes. Each agent keeps its own instructions and memory across threads and workspaces.