Local by default
Weights and inference remain on your own hardware.
Open source · Local AI
Ollama
Ollama manages model downloads and exposes a local HTTP service. Your scripts, notebooks, and editors all talk to the same endpoint.
- GitHub stars
- 181K
- Language
- Go
- License
- MIT
- Runs on
- macOS · Windows · Linux · Docker
01
/ 03What it is
A local service that answers like a cloud API.
Ollama manages model downloads and exposes a local HTTP service. Your scripts, notebooks, and editors all talk to the same endpoint.
One endpoint
CLI, scripts, and editors share the service on port 11434.
Existing clients work
OpenAI-style clients can switch to a local base URL.
02
/ 03Capabilities
Build with models locally.
Model management, chat, embeddings, and tool calling work out of the box.
On-demand model library
Pull and cache open models such as Qwen, Gemma, and DeepSeek.
REST and OpenAI APIs
Generate text, chat, create embeddings, and manage models over HTTP.
Python and JavaScript SDKs
Typed helpers make streaming chat and embeddings a few lines of code.
03
/ 03How to use
Install once, then run a model.
The first run downloads model weights; later runs reuse the local copy.
01
Install Ollama
Install the desktop service for your platform.
terminal
curl -fsSL https://ollama.com/install.sh | sh02
Pull a model and chat
Download a model once and begin an offline conversation.
terminal
ollama run gemma4
# list locally cached models
ollama listKeep exploring
More open-source projects
BioinformaticsBiopython
Python tools for computational biology — read sequence files, query NCBI, parse protein structures, and build phylogenetic trees.
PythonBiopython License5.2K
View Project
Scientific computingNumPy
The foundation of scientific computing in Python — N-dimensional arrays, broadcasting, and fast vectorized math.
Python / CBSD-3-Clause32.7K
View Project
Data appsStreamlit
Turn a normal Python script into an interactive web app in minutes — dashboards, reports, and chat interfaces without a frontend build.
PythonApache-2.045.7K
View Project