Top AI Repos — open-source AI, indexed and scored
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
RamaLama is an open-source developer tool that simplifies the local serving of AI models from any source and facilitates their use for inference in production, all through the familiar language of containers.
| Date | Stars |
|---|---|
| 2026-07-24 | 2973 |
| 2026-07-25 | 2973 |
| 2026-07-28 | 2977 |
| 2026-07-30 | 2977 |
| 2026-08-07 | 2989 |
| 2026-08-15 | 3000 |
| 2026-08-18 | 3001 |
| 2026-08-19 | 3003 |
| 2026-08-20 | 3004 |
| 2026-08-21 | 3006 |
| 2026-08-22 | 3008 |
| 2026-08-23 | 3012 |
| 2026-08-24 | 3013 |
| 2026-08-26 | 3017 |
| 2026-08-27 | 3019 |
| 2026-08-28 | 3023 |
| 2026-08-29 | 3025 |
| 2026-08-30 | 3025 |
| 2026-08-31 | 3026 |
| 2026-09-01 | 3029 |
| 2026-09-02 | 3030 |
| 2026-09-03 | 3032 |
| 2026-09-04 | 3031 |
| 2026-09-05 | 3032 |
| 2026-09-06 | 3033 |
| 2026-09-07 | 3032 |
| 2026-09-08 | 3037 |
| 2026-09-09 | 3041 |
| 2026-09-10 | 3041 |
| 2026-09-11 | 3042 |
| 2026-09-12 | 3043 |
| 2026-09-13 | 3044 |
| 2026-09-14 | 3045 |
| 2026-09-15 | 3051 |
| 2026-09-16 | 3051 |
| 2026-09-17 | 3050 |
| 2026-09-18 | 3051 |
| 2026-09-19 | 3051 |
| 2026-09-20 | 3053 |
Today
+2 stars today
This week
+9 stars this week
This month
+47 stars this month
Momentum
52.0
growth rate 0.30%/day
<p align="center">
<img src="https://github.com/user-attachments/assets/1a338ecf-dc84-4495-8c70-16882955da47" width=50%>
</p>
<p align="center">
<a href="https://github.com/containers/ramalama/issues">
<img src="https://img.shields.io/github/issues/containers/ramalama?style=flat-square" height="22" alt="Open Issues"/>
</a>
<a href="https://github.com/containers/ramalama/blob/main/LICENSE"><img src="https://img.shields.io/github/license/containers/ramalama?style=flat-square" height="22" alt="License"/>
</a>
<a href="https://github.com/containers/ramalama">
<img src="https://img.shields.io/github/languages/top/containers/ramalama?style=flat-square" height="22" alt="Top language"/>
</a>
<a href="https://pypi.org/project/ramalama/">
<img src="https://img.shields.io/pypi/v/ramalama?style=flat-square" height="22" alt="PyPI version"/>
</a>
<a href="https://pypi.org/project/ramalama/">
<img src="https://img.shields.io/pypi/pyversions/ramalama?style=flat-square" height="22" alt="Supported Python versions"/>
</a>
<a href="https://discord.gg/MkCXuTRBUn">
<img src="https://img.shields.io/discord/1388199960503128165?style=flat-square&logo=discord&label=discord" height="22" alt="Join Discord"/>
</a>
<a href="https://matrix.to/#/#ramalama:fedoraproject.org">
<img src="https://img.shields.io/badge/matrix-join-blue?style=flat-square&logo=matrix" height="22" alt="Join Matrix"/>
</a>
</p>
[RamaLama](https://ramalama.ai) strives to make working with AI simple, straightforward, and familiar by using OCI containers.
<br>
<br>
## Description
RamaLama is an open-source tool that simplifies the local use and serving of AI models for inference from any source through the familiar approach of containers. It allows engineers to use container-centric development patterns and benefits to extend to AI use cases.
RamaLama eliminates the need to configure the host system by instead pulling a container image specific to the GPUs discovered on the host system, and allowing you to work with various models and platforms.
- Eliminates the complexity for users to configure the host system for AI.
- Detects and pulls an [accelerated container image](#accelerated-images) specific to the GPUs on the host system, handling dependencies and hardware optimization.
- RamaLama supports multiple [AI model registries](#transports), including OCI Container Registries.
- Models are treated similarly to how Podman and Docker treat container images.
- Use common [container commands](#commands) to work with AI models.
- Run AI models [securely](#security) in rootless containers, isolating the model from the underlying host.
- Keep data secure by defaulting to no network access and removing all temporary data on application exits.
- Interact with models via REST API or as a chatbot.
<br>
## Install
### Install on macOS (Self-Contained Installer)
Download the self-contained macOS installer that includes Python and all dependencies:
1. Download the latest `.pkg` installer from [Releases](https://github.com/containers/ramalama/releases)
2. Double-click to install, or run: `sudo installer -pkg RamaLama-*-macOS-Installer.pkg -target /`
See [macOS Installation Guide](docs/MACOS_INSTALL.md) for detailed instructions.
### Install on Fedora
RamaLama is available in [Fedora](https://fedoraproject.org/) and later. To install it, run:
```
sudo dnf install ramalama
```
### Fedora Silverblue and Toolbox
On [Fedora Silverblue](https://docs.fedoraproject.org/en-US/fedora-silverblue/) and other immutable variants, the system is read-only. You can run RamaLama in either of these ways:
- **Toolbox**: Create a [Toolbox](https://docs.fedoraproject.org/en-US/fedora-silverblue/toolbox/) container and install RamaLama inside it (`pip install ramalama` or `dnf install ramalama` if available). Use the same Podman (or Docker) from the host so that RamaLama can start model containers; ensure the container engine is installed and that the toolboxExcerpt of 55,864 characters
Read on GitHub
1.5k
Eric Curtin · Docker, Inc
971
377
Oliver Walsh · Red Hat
341
Michael Engel · Red Hat
165
162
152
135
Kush Gupta · Red Hat
53
49
35
Nathan Weinberg · Red Hat · United States
31
R0CKSTAR · @MooreThreads · China
23
Sergio Arroutbi · Red Hat, Inc. · Spain
22
21
Matteo Mortari · Red Hat @RedHatOfficial
20
20
20
18
18
Would you bet a product on this? Bounded 0–100 and slow moving.
matched fp:ffc52eced36ba39d, topic:vllm, topic:llamacpp
matched fp:ffc52eced36ba39d, topic:cuda
matched fp:ffc52eced36ba39d, topic:llm