🧠 AI Cortex#

The unified Python toolkit for accessing any LLM through Ollama — zero API keys, zero signup, completely free.

What is AI Cortex?#

AI Cortex gives you a single, clean Python interface to hundreds of language models — Llama, Mistral, Gemma, DeepSeek, Qwen, and more — all served through Ollama. No accounts. No credit cards. No rate limits.

Whether you’re building a chatbot, a code assistant, a research tool, or an AI-powered app, AI Cortex handles the model discovery, server routing, and API compatibility so you don’t have to.

from aicortex import chat

# That's it. One line of Python, any model, any server.
response = chat("Explain neural networks like I'm five.")
print(response)

✨ Why AI Cortex?#

Feature	What it means for you
🆓 100% Free	No API keys, no billing, no subscriptions — ever
🤖 Any Model	Llama, Mistral, Gemma, DeepSeek, Qwen, and more
🌐 Any Server	Local Ollama, remote servers, or community endpoints
⚡ Streaming	Real-time token streaming for responsive UIs
🔌 OpenAI-Compatible	Drop-in replacement for `openai` client apps
🛡️ Type-Safe	Full type hints, stubs, and IDE autocomplete
🔧 Production Ready	Automatic failover, multi-server routing, error handling
📦 Lightweight	One dependency (`ollama`) for the core package

🚀 Get Started in 60 Seconds#

pip install aicortex-core

from aicortex import chat, models, families

# Chat with any model
print(chat("What is the speed of light?"))

# Discover what's available
print(families())   # ['llama', 'mistral', 'gemma', 'deepseek', 'qwen']
print(models("mistral"))  # ['mistral:7b', 'mistral:instruct', ...]

→ Full Quick Start Guide

📚 Documentation#

Getting Started#

Installation — install options, requirements, and verification
Quick Start — your first chat in 5 minutes
Basic Usage — parameters, patterns, and error handling

Core Reference#

Core API — complete function and class reference
Streaming — real-time token streaming guide
Model Management — families, discovery, metadata

Deployment#

Server Mode — OpenAI-compatible REST API server
Tools — endpoint validation, model fetch/resolve/apply pipeline

Contributing#

Contributing Guide — how to submit issues and PRs
Development Setup — local dev environment, tests, CI

🏗️ Architecture at a Glance#

aicortex/
├── chat()          ← Your main entry point
├── api.py          ← Ollama client, model registry, server routing
├── chat.py         ← Stream / StreamEvent types
├── models/         ← Bundled model metadata (JSON per family)
└── tools/
    ├── check_models.py    ← Validate live Ollama endpoints
    ├── fetch_models.py    ← Pull model lists from valid endpoints
    ├── resolve_models.py  ← Merge fetched data with IP metadata
    ├── apply_valid_models.py  ← Write resolved models into family JSONs
    └── server.py          ← OpenAI-compatible FastAPI proxy

📄 License#

AI Cortex is released under the GNU Lesser General Public License v3.0. You can use it freely in open-source and commercial projects.

🧠 AI Cortex

Contents