CLI-first local AI stacks

Install complete AI stacks with one command

Llanite bundles local models, runtimes, agent layers, tools, and permission rules into portable stack profiles. Inspect before you run. Own everything locally.

$npm install -g @llanite/cli
Browse StacksView Docs
llanite
3 stacks available
~$llanite stacks
local-coderllama3.2 · ollama · continue
researchmistral · ollama · brave
code-reviewphi3 · ollama · diff
~$llanite doctor local-coder
ollama running
model cached
agent installed
ready to run
~$
~$llanite inspect local-coder
local-coder
modelllama3.2-3b
runtimeollama
agentcontinue
toolsedit, read, shell
permissions
file_writeconfirm
shellconfirm
networkdeny
secretsblock

How it works

From zero to running in minutes

Llanite is designed to get out of your way. Three commands cover the entire workflow.

01

Install Llanite

One npm command gets you the CLI globally. No config files, no setup wizard, no accounts.

$ npm install -g @llanite/cli
02

Install a stack

Pick a stack profile. Llanite pulls the model and wires up the runtime — no manual configuration.

$ llanite install local-coder
03

Run it locally

Launch the stack. All inference runs on your machine. Nothing phones home.

$ llanite run local-coder

Registry to runtime

A stack should feel like one package, not six setup guides.

Llanite turns registry metadata into a runnable local agent profile: model, runtime, agent layer, tools, permissions, and launch command all resolved before anything runs.

inspectable

Every profile is plain YAML.

local-first

Ollama and local model caches stay on device.

permissioned

Shell, file writes, network, and secrets are explicit.

Runtime

Ollama

Local model server

Model

Qwen Coder

7B coding model

Agent

Llanite Agent

Chat, tools, memory

Tools

Filesystem

Read/write with policy

Tool

Git

Diffs and status

Policy

Confirm Shell

Permission gates

local-coder setup
~$llanite install local-coder
Registry cache updated
12 stacks
Ollama runtime detected
0.7.0
Pulling qwen2.5-coder:7b
local-coder
Writing stack profile
~/.llanite
~$llanite run local-coder
Stack ready. Shell commands require confirmation. Secrets are blocked.

local-coder

resolved manifest

modelqwen2.5-coder:7b
runtimeollama
agentllanite-agent
memorylocal logs
toolsfs, git, shell

Built different

Everything you need, nothing you don't

One ID. One command. Complete environment.

Every stack bundles a model, runtime, agent layer, tool set, and permission policy into a single portable profile. No scattered configs, no dependency hunting across docs.

$llanite stacks
local-coderqwen2.5-coder · ollama · continue
repo-reviewerqwen2.5-coder · ollama · read-only
private-chatllama3.1 · ollama · no tools
Start local

Your first stack is one command away.

Install Llanite, inspect the registry, and launch a local AI environment with explicit tools and permission gates.

$npm install -g @llanite/cli
llanite

$ llanite fetch

registry updated

$ llanite inspect local-coder

qwen2.5-coder:7b · ollama

$ llanite run local-coder

shell confirm · secrets block