Coding agents on cloud machines with a record of every session
AI agent software with its own cloud computer
Stage
Not given
Not given
Founded
Not given
Not given
Based in
Not given
Not given
Pricing model
Free trial
Freemium
Pricing
Free trial: two machines, up to 2 vCPU and 4 GiB. Cuna Inference pricing: models available at varying rates, such as GLM-5.2 at $1.00 per million input tokens and $4.00 per million output tokens.
Free for 24 hours. Paid plans: Spark $19/month with $10/month in AI credits, Surge $39/month with $25/month in AI credits, Apex $79/month with $60/month in AI credits, Godmode $159/month with $140/month in AI credits. First-time customers may see Spark at $1 for the first month. Cancel anytime from
Key features
Isolated session execution with bounded authority
Web console for machine management
Complete action recording and visibility
OpenAI-compatible Chat Completions API
OpenCuna terminal agent
Multiple model provider support
Cuna Memory for agent state persistence
Token-based pay-as-you-go pricing
Connect to ChatGPT, Claude, Cursor, VS Code, Claude Code and Windsurf
Cloud desktop with real browser and GUI apps
Persistent memory and dreaming consolidation
Own dedicated email address
Live monitoring and control via dashboard
Fail-closed spending with rolling usage windows
Agent network for peer-to-peer clone discovery
Private mode for sensitive conversations
MCP (Model Context Protocol) support
What makes it different
Your Agent. Not a Vendor's.
The work ends. The proof remains.
Complete session records and operational transparency
Use any model with visible per-token pricing
Dedicated cloud computer that stays running even when you close the chat, with its own email address and persistent memory
Same clone answers multiple AI assistants (ChatGPT, Claude, Cursor, VS Code), so tasks started in one can be followed up in another
Fail-closed spending controls and rolling usage windows prevent autonomous overspending
Agent network allows clones to discover and collaborate with other users' clones for peer-to-peer task completion
Four-phase dreaming system consolidates memories nightly into long-term storage and refines clone identity