Coding agents on cloud machines with a record of every session
Operating System for Agentic AI
Stage
Not given
Not given
Founded
Not given
2023
Based in
Not given
US
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 plan with 5,000 credits and 50 runs/day for 7 days (includes building up to 7 applications, single-user access, 100MB storage, 50+ pre-built apps, tracing, basic admin controls, version control, and single sign-on). Enterprise plan with custom credits per month and custom runs/day, requiring a
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
Agent Builder for creating modular agents with defined roles, memory, and evaluation parameters
Workflow Builder for composing multi-step processes
Knowledge Base for agent training and context
Agent orchestration with multi-step execution and native lifecycle control
Runtime isolation to prevent cross-agent and cross-tenant data leakage
Secrets Management with native vault for secure credential storage
Agent-to-Agent Communication for structured coordination between agents
Audit trails and decision-level logging for compliance
Role-based and attribute-based access control across agents and tools
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
Governed operating system with built-in compliance and audit trails for regulated enterprises
Deployment flexibility across cloud, on-premises, private cloud, hybrid, and air-gapped environments
Hands-on go-live support with fast production rollout in 2 days or less
Multi-LLM orchestration with unified reasoning and routing
Citation-backed answers and grounded responses for reducing hallucinations