Run large language models locally on your machine. Supports Llama 3, Mistral, Gemma, Phi, and dozens more. One-command install, OpenAI-compatible API.
This block should tell both the user and the agent what to copy, install, and apply first.
# Install
curl -fsSL https://ollama.com/install.sh | sh
# Run a model
ollama run llama3.1Ollama makes it dead simple to run open-source LLMs locally. Download and run Llama 3, Mistral, Gemma, Phi, CodeLlama, and 100+ other models with a single command. Includes an OpenAI-compatible API for easy integration.
Best for: Local AI development, privacy-sensitive workloads, offline coding, model experimentation Works with: Any tool supporting OpenAI API format
| Model | Size | Use Case |
|---|---|---|
llama3.1:8b |
4.7 GB | General purpose |
codellama:13b |
7.4 GB | Code generation |
mistral:7b |
4.1 GB | Fast, capable |
gemma2:9b |
5.4 GB | Google's open model |
phi3:mini |
2.3 GB | Small & efficient |
deepseek-coder-v2 |
8.9 GB | Code specialist |
curl http://localhost:11434/api/chat -d '{
"model": "llama3.1",
"messages": [{"role": "user", "content": "Hello!"}]
}'OpenAI-compatible endpoint at http://localhost:11434/v1/.
Created by Ollama. Licensed under MIT. ollama/ollama — 120K+ GitHub stars
Rust-powered Python linter and formatter. 10-100x faster than Flake8 + Black combined. 800+ lint rules, auto-fix, import sorting, and format-on-save.
Rust-powered Python package and project manager. 10-100x faster than pip. Drop-in replacement with lockfiles, virtual environments, and Python version management.
Turn any website into LLM-ready markdown. API-first web scraping with JavaScript rendering, auto-pagination, structured extraction, and batch crawling.