Run multiple local LLMs in parallel. Coreling divides tasks, manages memory, and unifies your AI workflow — without a single byte leaving your machine.
Private · Air-gapped · Open
Capabilities
One install command. Coreling auto-downloads everything it needs on first launch. No config, no API keys, no prerequisites.
Tell it something once — it silently writes to brain.md and remembers forever. Context survives restarts and sessions.
Zero telemetry. Zero cloud calls. Every prompt, completion, and memory artifact stays on-device. Fully air-gap compatible.
Drop any image path into chat. Coreling auto-switches to its vision model — no extra commands or model management needed.
Uni-Core for deep reasoning and coding. Multi-Core for speed — with a deterministic math coprocessor for exact answers.
Everything lives in ~/.coreling/ as ordinary files. Brain, models, history — inspect, edit, or wipe with a single command.
Architecture
Run
Type coreling to start
Auto-Setup
Engine downloads silently
Pick Mode
Uni-Core or Multi-Core
Chat
It learns and remembers
Private
0 bytes leave your machine
No account. No telemetry. No model provider reading your prompts. Coreling was built air-gap-first — your data stays exactly where it belongs.
Open Source
Coreling is and will always be free for everyone. Our mission is to democratize local AI orchestration.
Stop sending your most sensitive work to someone else's server. Multi-agent AI running entirely on your hardware.
Installation
One command to get started. Coreling automatically detects your system and installs the appropriate version.
macOS
curl -fsSL https://coreling.org/install.sh | bashLinux
curl -fsSL https://coreling.org/install.sh | bashWindows
irm https://coreling.org/install.ps1 | iex