RinaWarp is a local-first AI terminal assistant that helps you plan, explain, and optionally execute commands with guardrails. It remembers your workflow context across sessions, surfaces logs and timeline events, and can integrate with cloud services for

tools

ollama run rinawarptech/Rinawarptech

curl http://localhost:11434/api/chat \
  -d '{
    "model": "rinawarptech/Rinawarptech",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

from ollama import chat

response = chat(
    model='rinawarptech/Rinawarptech',
    messages=[{'role': 'user', 'content': 'Hello!'}],
)
print(response.message.content)

import ollama from 'ollama'

const response = await ollama.chat({
  model: 'rinawarptech/Rinawarptech',
  messages: [{role: 'user', content: 'Hello!'}],
})
console.log(response.message.content)

Details

Updated 5 months ago

5 months ago

3ebe18bca633 · 4.9GB ·

model

archllama

parameters8.03B

quantizationQ4_K_M

4.9GB

license

LLAMA 3.1 COMMUNITY LICENSE AGREEMENT Llama 3.1 Version Release Date: July 23, 2024 “Agreement”

12kB

system

You are RinaWarp — a futuristic AI terminal assistant...

62B

params

{ "num_ctx": 4096, "stop": [ "<|start_header_id|>", "<|end_header_id|>",

141B

template

{{- if or .System .Tools }}<|start_header_id|>system<|end_header_id|> {{- if .System }} {{ .System }

1.5kB

Readme

RinaWarp AI Terminal Assistant

RinaWarp is a local-first AI terminal assistant that helps you plan, explain, and (optionally) run terminal commands with guardrails. It’s designed for daily developer workflows: troubleshooting, setup, deployment checks, and repeatable automation.

Default behavior is safe: it explains first and only executes commands when you allow it.

Quick Start (Local / Ollama)

1) Install Ollama

macOS: download from Ollama site
Linux: follow Ollama install docs
Windows:

”`bash winget install Ollama.Ollama