Embedding Atlas is a tool that provides interactive visualizations for large embeddings. It allows you to visualize, cross-filter, and search embeddings and metadata.

🦔 PostHog provides open-source web & product analytics, session recording, feature flagging and A/B testing that you can self-host. Get started - free.

🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training.

Machine Learning Containers for NVIDIA Jetson and JetPack-L4T

Fast and memory-efficient exact attention

LLM inference in C/C++

ONVIF Client Implementation in Python 3 (using https://github.com/mvantellingen/python-zeep instead of suds as SOAP client)

HLS.js is a JavaScript library that plays HLS in browsers with support for MSE.

Ready-to-use SRT / WebRTC / RTSP / RTMP / LL-HLS media server and media proxy that allows to read, publish, proxy, record and playback video and audio streams.

For developers, who are building real-time data-driven applications, Redis is the preferred, fastest, and most feature-rich cache, data structure server, and document and vector query engine.

Debian packaging

Copilot Chat extension for VS Code

🪢 Open source LLM engineering platform: LLM Observability, metrics, evals, prompt management, playground, datasets. Integrates with OpenTelemetry, Langchain, OpenAI SDK, LiteLLM, and more. 🍊YC W23

A reactive notebook for Python — run reproducible experiments, query with SQL, execute as a script, deploy as an app, and version with git. All in a modern, AI-native editor.

An open-source prompt engineering framework.

LLM abstractions that aren't obstructions

Official codebase used to develop Vision Transformer, SigLIP, MLP-Mixer, LiT and more.

LuxCore source repository

C++/CUDA/Python multimedia utilities for NVIDIA Jetson

Zero-copy multimodal vector DB with CUDA and CLIP/SigLIP

Blender Integration for LuxCore

A library for efficient similarity search and clustering of dense vectors.

A better light source for scanning color negative film

Build and query dynamic, temporally-aware Knowledge Graphs

Python tool for converting files and office documents to Markdown.

Robust Speech Recognition via Large-Scale Weak Supervision

⏩ Continue is the leading open-source AI code assistant. You can connect any models and any context to build custom autocomplete and chat experiences inside VS Code and JetBrains

Hello AI World guide to deploying deep-learning inference networks and deep vision primitives with TensorRT and NVIDIA Jetson.