Mistral AI maintains a public GitHub presence featuring a wide range of repositories primarily developed in Python, Jupyter Notebook, and JavaScript. Notable projects include mistral-inference, a library for Mistral models, and mistral-vibe, a minimal CLI coding agent. The organization is focused on open-source contributions and collaborative development.
Official inference library for Mistral models
Minimal CLI coding agent by Mistral
No description provided for this repository.
No description provided for this repository.
Official inference library for pre-processing of Mistral models
No description provided for this repository.
Python client library for Mistral AI platform
JS Client library for Mistral AI platform
TS Client library for Mistral AI platform
No description provided for this repository.
No description provided for this repository.
A high-throughput and memory-efficient inference and serving engine for LLMs
An open platform for training, serving, and evaluating large language models. Release repo for Vicuna and Chatbot Arena.
Base template to register and invoke workflows
🤗 Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.
TensorRT-LLM provides users with an easy-to-use Python API to define Large Language Models (LLMs) and build TensorRT engines that contain state-of-the-art optimizations to perform inference efficiently on NVIDIA GPUs. TensorRT-LLM also contains components to create Python and C++ runtimes that execute those TensorRT engines.
Base template to build, manage and improve search engines
A protocol for connecting any editor to any agent
Extensions for the Zed editor
Mistral AI documentation for SageMaker
Prometheus instrumentation library for Python applications
Distributed KV cache coordinator
Gateway API Inference Extension
Inference scheduler for llm-d
Mistralai develops several repositories focused on AI and machine learning, including libraries for model inference, CLI tools, and fine-tuning capabilities. Their projects facilitate the use and integration of Mistral models.
Mistralai primarily utilizes Python, Jupyter Notebook, and JavaScript for their projects. They also incorporate TypeScript, MDX, and Jinja in various repositories, showcasing a versatile approach to development.
Yes, all of mistralai's repositories are publicly accessible on GitHub. This open approach allows developers and researchers to collaborate and contribute to their projects, enhancing the availability of AI tools.
Monitor Mistral AI with RepoGuard and get alerted the moment a new public repository appears.
Monitor this account