Knowledge Engine that distills experience into sovereign, reusable skills for AI agents
Coding agents on cloud machines with a record of every session
Stage
Not given
Not given
Founded
Not given
Not given
Based in
Not given
Not given
Pricing model
Freemium
Free trial
Pricing
IKKF CLI: free forever, no license required. IKKF for macOS: $9.99 one-off purchase.
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.
Key features
Seven-phase execution protocol
Synthesis Gate ensures expertise is distilled before task completion
Universal AI provider support
Local-first operation with no cloud or telemetry
Work decomposed into 10-15 minute chunks
Plain-text skill files you can read and audit
Real deliverables written to your workspace
Skill library and synthesis
Two execution modes: Light and Full
Resume and restore interrupted tasks
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
What makes it different
Ownership of all skills—your expertise stays yours, not locked in opaque third-party systems
Synthesis Gate forces real learning and skill building alongside task completion
Free CLI forever with no license, key, or machine-lock
Local-first privacy—no cloud, no telemetry, full control
Works with any AI agent—one protocol, instant provider swaps
Your Agent. Not a Vendor's.
The work ends. The proof remains.
Complete session records and operational transparency