Stars
1 Line of code data quality profiling & exploratory data analysis for Pandas and Spark DataFrames.
Fast, Accurate, Lightweight Python library to make State of the Art Embedding
Tiny Model, Big Logic: Diversity-Driven Optimization Elicits Large-Model Reasoning Ability in VibeThinker-1.5B
Codex CLI multi-account OAuth manager with account switching, health checks, runtime rotation, diagnostics, and recovery tools for @openai/codex
Access a database of word frequencies, in various natural languages.
Lightpanda: the headless browser designed for AI and automation
Codex Desktop App - Cross-platform Rebuild
Unofficial ChatGPT desktop app for Linux (formerly the Codex app), built locally from OpenAI’s official macOS app. Includes Chat, Work, and Codex. Packages for Debian/Ubuntu (.deb), Fedora/openSUSE…
Allen Institute for AI: WildDet3D: Scaling Promptable 3D Detection in the Wild
Run agents like Hermes, LangChain Deep Agents, and OpenClaw more securely inside NVIDIA OpenShell with managed inference
[Official Repo] SpatialEdit: Benchmarking Fine-Grained Image Spatial Editing
[CVPR 2026 Highlight] Vanast: Virtual Try-On with Human Image Animation via Synthetic Triplet Supervision
KV cache compression via block-diagonal rotation. Beats TurboQuant: better PPL (6.91 vs 7.07), 28% faster decode, 5.3x faster prefill, 44x fewer params. Drop-in llama.cpp integration.
A time-series database for high-performance real-time analytics packaged as a Postgres extension
Development at the speed of light
Use Codex from Claude Code to review code or delegate tasks.
[ICLR-26, ECCV-26, NeurIPS-25] Lumos-Custom Project: research for customized video generation in the Lumos Project.
Our method reconstructs 3D worlds from video diffusion models using non-rigid alignment to resolve inherent 3D inconsistencies in the generated sequences.
This repo contains the code for "VLM2Vec / MMEB" [ICLR 2025], "VLM2Vec-V2 / MMEB-V2" [TMLR 2026], and "MMEB-V3" [COLM 2026]
[NeurIPS 2025] PyTorch implementation of [ThinkSound], a unified framework for generating audio from any modality, guided by Chain-of-Thought (CoT) reasoning.
A unified inference and post-training framework for accelerated video generation.
MiroThinker is a deep research agent optimized for complex research and prediction tasks. Our latest models, MiroThinker-1.7, achieves 74.0 and 75.3 on the BrowseComp and BrowseComp Zh, respectively.