Repository Index

Offline multi-agent simulation & prediction engine. English fork of MiroFish with Neo4j + Ollama local stack.

• ai
• neo4j
• offline
• ollama

vLLM’s reference system for K8S-native cluster-wide deployment with community-driven performance optimization

Client/server to synchronize media playback on mpv/VLC/MPC-HC/MPC-BE on many computers

Code for "Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks"

MambaOut: Do We Really Need Mamba for Vision? (CVPR 2025)

MusePose: a Pose-Driven Image-to-Video Framework for Virtual Human Generation

Apache Ossie, industry wide specification effort to standardize how we exchange semantic metadata across analytics, AI and BI platforms, providing a vendor neutral, single source of truth for semantic data

• metadata
• semantic

A unified framework for privacy-preserving data analysis and machine learning

• differential-privacy
• homomorphic-encryption
• machine-learning
• privacy-preserving

I have created this addons for export asset from Blender to Unreal Engine

• blender
• camera
• unreal-engine
• animations

TranslatedTencent CodeBuddy account pool management console with a built-in OpenAI-compatible reverse proxy gateway: bulk onboarding of accounts via QR code scan, scheduled check-ins and keep-alive, key grouping and distribution, IP and model whitelists, call logs and usage statistics; supports one-click updates with signature verification.

• account-manager
• api-gateway
• codebuddy
• fastapi

[ICLR 2024] Official implementation of " 🦙 Time-LLM: Time Series Forecasting by Reprogramming Large Language Models"

• cross-modal-learning
• cross-modality
• deep-learning
• language-model

A tool for converting dictionary files aka glossaries. Mainly to help use our offline glossaries in any Open Source dictionary we like on any operating system / device.

• dictionary
• pygi
• tkinter
• linux

Auto-detect the connected display hardware and load the appropriate X11 setup using xrandr

• xrandr
• x11
• configuration-management

[SIGGRAPH Asia 2026] UniMate: One Unified Model to Animate Diverse Skeletons

robosuite: A Modular Simulation Framework and Benchmark for Robot Learning

• robotics
• robot-manipulation
• reinforcement-learning
• physics-simulation

Serve large Qwen models fast on the GPUs you actually own. Qwen3.8-27B on a single 24 GB card with vLLM: 127 tok/s single-user (381 when the answer quotes the prompt), ~1,035 tok/s at 64 concurrent, 150k-262k context. vLLM patches, requant pipeline, benchmarks.

• kv-cache
• llm-inference
• local-llm
• quantization

Multi-tool for semantic search

• cli
• machine-learning
• semantic-search

Multimodal Unsupervised Image-to-Image Translation

• gan
• deep-learning
• pix2pix
• image-translation

Self-hosted LLM router with a managed safety net. OpenAI-compatible. BYOK. Single-workspace. Streaming. For more advanced routing choose hosted OrcaRouter

• ai-gateway
• ai-gateways
• anthropic-api
• byok

SkyReels V1: The first and most advanced open-source human-centric video foundation model

• i2v
• t2v
• video-diffusion-transformers

Just draw a bounding box and you can remove the object you want to remove.

• pytorch
• inpainting
• video-inpainting
• image-inpainting

The fastest way to run Qwen 3.8 Flash Next, Qwen 3.8 27B and Ternary Bonsai 2 27B on a Mac: 125 tok/s in OpenCode on an M5 Max, and a 27B model on 16 GB Macs. Native MTP speculative decoding on Apple Silicon, exact at any temperature. OpenAI and Anthropic compatible local server.

• apple-silicon
• local-ai
• mlx
• mtp

Semi Supervised Learning for Medical Image Segmentation, a collection of literature reviews and code implementations.

• semi-supervised-learning

一款部署于云端或本地的隧道代理池中间件，可将静态代理IP灵活运用成隧道IP，提供固定请求地址，一次部署终身使用

• cyber-security
• proxy
• proxypool
• security