Asklv

MimiClaw: Run OpenClaw on a $5 chip. Local-first memory. Shareable. Privacy-first. No OS(Linux). No Node.js. No Mac mini. No Raspberry Pi. No VPS.😗

Training operators on Kubernetes.

No description.

The memory-driven personalized health management app with private AI.

An open-source framework for detecting, redacting, masking, and anonymizing sensitive data (PII) across text, images, and structured data. Supports NLP, pattern matching, and customizable pipelines.

This package features data-science related tasks for developing new recognizers for Presidio. It is used for the evaluation of the entire system, as well as for evaluating specific PII recognizers or PII detection models.

High-performance distributed KV storage based on LSM Tree

https://wavespeed.ai/ Context parallel attention that accelerates DiT model inference with dynamic caching

将博导十年科研经验炼化为可直接调用的 AI 技能。从 Idea 构思到论文投稿，你的 AI 科研副导师。

GPT-Image-2 PPT Generator Skill for Creating Image-Based PowerPoint Presentations in Codex and Other Skill-Compatible Agents

Rust async runtime based on io-uring.

[MLsys2026]: RAG on Everything with LEANN. Enjoy 97% storage savings while running a fast, accurate, and 100% private RAG application on your personal device.

A MCP server for our beloved terminal multiplexer tmux.

[ICLR 2026] dParallel: Learnable Parallel Decoding for dLLMs

Garry's Opinionated OpenClaw/Hermes Agent Brain

Programmable debugger

Podman: A tool for managing OCI containers and pods.

A tool that facilitates building OCI images.

Work with remote images registries - retrieving information, images, signing content

Browser automation CLI for AI agents

Tools for checking ACL paper submissions

🤖 AI Gateway | AI Native API Gateway

A native gRPC client & server implementation with async/await support.

AI Agent 驱动的开源视频生成工作台 — 小说→角色/场景/道具设计→剧本→分镜图→视频，跨镜头角色与场景一致 | Open-source AI video workspace powered by AI Agents, Nano Banana 2 & Veo 3.1 / Grok / Seedance / OpenAI

Distributed RL System for LLM Reasoning

No description.

AI agent toolkit: coding agent CLI, unified LLM API, TUI & web UI libraries, Slack bot, vLLM pods

A Go compiler based on LLVM in order to better integrate Go with the C ecosystem including Python

⚒ Evolutionary self-improvement for Hermes Agent — optimize skills, prompts, and code using DSPy + GEPA

Costea: Know the Cost Before You Run Your Agents(OpenClaw, Claude Code & Codex...)

OME is a Kubernetes operator for enterprise-grade management and serving of Large Language Models (LLMs)

Use Microsoft Edge's online text-to-speech service from Python WITHOUT needing Microsoft Edge or Windows or an API key

The agent that grows with you

Your own personal AI assistant. Any OS. Any Platform. The lobster way. 🦞

agent casino for fun and glory

A paper list of Awesome Latent Space.

Claude Code is an agentic coding tool that lives in your terminal, understands your codebase, and helps you code faster by executing routine tasks, explaining complex code, and handling git workflows - all through natural language commands.

Forma Takeoff to Cost Sample: A sample demonstrates displaying package information from Autodesk Takeoff product, and calculate the budget based on the quantity of takeoff items and price which is stored in database.

OpenShell is the safe, private runtime for autonomous AI agents.

NVIDIA plugin for secure installation of OpenClaw

Let's use AI to Earn!

A skill that automatically retrieves and analyzes emails via SMTP and POP3.

AI agents running research on single-GPU nanochat training automatically

Efficient and easy multi-instance LLM serving

A curated list of recipes and repos that can be used to build your rusty projects. Rusty Book = Cookbook + Awesome Rust！

A simple tool to generate e-signature

No description.

[ICLR'25] OpenRCA: Can Large Language Models Locate the Root Cause of Software Failures?

KAI Scheduler is an open source Kubernetes Native scheduler for AI workloads at large scale

MimiBox — Turn browsers into sandbox for AI agents.

An implementation for FinTech-Copilot implementation.

A pixel office for your OpenClaw: turn invisible work states into a cozy little space with characters, daily notes, and guest agents. Code under MIT; art assets for non-commercial learning only.

Sandboxes for every agent. Embeddable, stateful, snapshots, and hardware isolation.

An open-source SuperAgent harness that researches, codes, and creates. With the help of sandboxes, memories, tools, skills and subagents, it handles different levels of tasks that could take minutes to hours.

Low-level unprivileged sandboxing tool used by Flatpak and similar projects

Applications based on Wi-Fi CSI (Channel state information), such as indoor positioning, human detection

No description.

[CNCF Sandbox Project] Managing your Kubernetes clusters (including public, private, edge, etc.) as easily as visiting the Internet

No description.

🚀 The fast, Pythonic way to build MCP servers and clients

ECCV 2026 paper template

Kimi Code CLI is your next CLI agent.

Kode CLI — Design for post-human workflows. One unit agent for every human & computer task.

"🐈 nanobot: The Ultra-Lightweight OpenClaw"

🌐 Make websites accessible for AI agents. Automate tasks online with ease.

SleepyTube: turns any youtube video into sleep-friendly audio.

[ICLR 2025] BRIGHT: A Realistic and Challenging Benchmark for Reasoning-Intensive Retrieval

No description.

Official repository for "CODI: Compressing Chain-of-Thought into Continuous Space via Self-Distillation"

Document Ranking with Large Language Models.

Collection of awesome LLM apps with AI Agents and RAG using OpenAI, Anthropic, Gemini and opensource models.

GoReplay is an open-source tool for capturing and replaying live HTTP traffic into a test environment in order to continuously test your system with real data. It can be used to increase confidence in code deployments, configuration changes and infrastructure changes.

verl: Volcano Engine Reinforcement Learning for LLMs

Mem MCP Server — Beyond-Git memory and process partner for AI coding.

Curated systems, benchmarks, and papers etc. on memory for LLMs/MLLMs --- long-term context, retrieval, and reasoning.

A curated list of vibe coding references, collaborating with AI to write code.

A hand-picked collection of tools and resources for Vibe Coding

Survey: A collection of AWESOME papers and resources on the large language model (LLM) related recommender system topics.

The official Go SDK for Model Context Protocol servers and clients. Maintained in collaboration with Google.

Democratizing Reinforcement Learning for LLMs

Conditional Memory via Scalable Lookup: A New Axis of Sparsity for Large Language Models

CV/resume generator for academics and engineers, YAML to PDF

[NeurIPS 2025] Hybrid Latent Reasoning via Reinforcement Learning

The most powerful and modular stable diffusion GUI, api and backend with a graph/nodes interface.

The open source coding agent.

No description.

Lighteval is your all-in-one toolkit for evaluating LLMs across multiple backends

A light weight vLLM simulator, for mocking out replicas.

This repository contains a regularly updated paper list for LLMs-reasoning-in-latent-space.

Nuitka is a Python compiler written in Python. It's fully compatible with Python 2.6, 2.7, 3.4-3.13. You feed it your Python app, it does a lot of clever things, and spits out an executable or extension module.

An Open Phone Agent Model & Framework. Unlocking the AI Phone for Everyone

No description.

Lightweight coding agent that runs in your terminal

Next-Token Prediction is All You Need

Doodling our way to AGI ✏️ 🖼️ 🧠

OCR-VQGAN, a discrete image encoder (tokenizer and detokenizer) for figure images in Paper2Fig100k dataset. Implementation of OCR Perceptual loss for clear text-within-image generation. Fork from VQGAN in CompVis/taming-transformers

[ICLR & NeurIPS 2025] Repository for Show-o series, One Single Transformer to Unify Multimodal Understanding and Generation.

Anole: An Open, Autoregressive and Native Multimodal Models for Interleaved Image-Text Generation

Awesome Unified Multimodal Models

No description.

An Open-source RL System from ByteDance Seed and Tsinghua AIR

A list of awesome academic researches and industrial materials about Large Language Model (LLM) and Artificial Intelligence for IT Operations (AIOps).

EVE Series: Encoder-Free Vision-Language Models from BAAI

Moxin: a Rust AI LLM client built atop Robius

Modern columnar data format for ML and LLMs implemented in Rust. Convert from parquet in 2 lines of code for 100x faster random access, vector index, and data versioning. Compatible with Pandas, DuckDB, Polars, Pyarrow, and PyTorch with more integrations coming..

Giving Kubernetes Superpowers to everyone

agent-sandbox enables easy management of isolated, stateful, singleton workloads, ideal for use cases like AI agent runtimes.

Checkpoint-engine is a simple middleware to update model weights in LLM inference engines

Official Repository for "Glyph: Scaling Context Windows via Visual-Text Compression"

A high-throughput and memory-efficient inference and serving engine for LLMs

An Industrial-Level Controllable and Efficient Zero-Shot Text-To-Speech System

Open-source evaluation toolkit of large multi-modality models (LMMs), support 220+ LMMs, 80+ benchmarks

[ICCV 2025] LLaVA-CoT, a visual language model capable of spontaneous, systematic reasoning

Welcome to the Llama Cookbook! This is your go to guide for Building with Llama: Getting started with Inference, Fine-Tuning, RAG. We also show you how to solve end to end problems using Llama model family and using them on various provider services

The AI Toolkit for TypeScript. From the creators of Next.js, the AI SDK is a free open-source library for building AI-powered applications and agents

UCCL is an efficient communication library for GPUs, covering collectives, P2P (e.g., KV cache transfer, RL weight transfer), and EP (e.g., GPU-driven)

[Neurips'24 Spotlight] Visual CoT: Advancing Multi-Modal Language Models with a Comprehensive Dataset and Benchmark for Chain-of-Thought Reasoning

LLM model quantization (compression) toolkit with hw acceleration support for Nvidia CUDA, AMD ROCm, Intel XPU and Intel/AMD/Apple CPU via HF, vLLM, and SGLang.

PyTorch native quantization and sparsity for training and inference

🤗 PEFT: State-of-the-art Parameter-Efficient Fine-Tuning.

Open Source DeepWiki: AI-Powered Wiki Generator for GitHub/Gitlab/Bitbucket Repositories. Join the discord: https://discord.gg/gMwThUMeme

Fast key-value DB in Go.

The high-performance database for modern applications

A high performance memory-bound Go cache

Training Large Language Model to Reason in a Continuous Latent Space

Open-source industrial-grade ASR models supporting Mandarin, Chinese dialects and English, achieving a new SOTA on public Mandarin ASR benchmarks, while also offering outstanding singing lyrics recognition capability.

VibeGit, Track Interaction with Diffs in AI Coding

Automagically group and commit semantically related changes in your Git repository with AI.

Byterover Cipher is an opensource memory layer specifically designed for coding agents. Compatible with Cursor, Codex, Claude Code, Windsurf, Cline, Claude Desktop, Gemini CLI, AWS's Kiro, VS Code, Roo Code, Trae, Amp Code and Warp through MCP. Built by https://byterover.dev/

DiffuCoder: Understanding and Improving Masked Diffusion Models for Code Generation

An Easy-to-use, Scalable and High-performance RLHF Framework based on Ray (PPO & GRPO & REINFORCE++ & vLLM & Ray & Dynamic Sampling & Async Agentic RL)

Official Implementation for the paper "d1: Scaling Reasoning in Diffusion Large Language Models via Reinforcement Learning"

TraceRL & TraDo-8B: Revolutionizing Reinforcement Learning Framework for Diffusion Large Language Models

Production-grade client-side tracing, profiling, and analysis for complex software systems.

Cloud Native Artifacial Intelligence Model Format Specification

Command-line tools for managing OCI model artifacts, which are bundled based on Model Spec

Official PyTorch implementation for "Large Language Diffusion Models"

A streamlined and customizable framework for efficient large model evaluation and performance benchmarking

Kubernetes-native IoT gateway

An end-to-end machine learning and data mining framework on Hadoop

[NeurIPS 2025] Efficient Reasoning Vision Language Models

A paper list of some recent works about Token Compress for Vit and VLM

[ICML'25] Official implementation of paper "SparseVLM: Visual Token Sparsification for Efficient Vision-Language Model Inference".

No description.

reddacted lets you analyze & sanitize your online footprint using LLMs, PII detection & sentiment analysis to identify anything that might reveal personal info you may not want correlated with your anonymous profile

pix2tex: Using a ViT to convert images of equations into LaTeX code.

Open-source infrastructure for Computer-Use Agents. Sandboxes, SDKs, and benchmarks to train and evaluate AI agents that can control full desktops (macOS, Linux, Windows).

[WACV 2025] Patch Ranking: Efficient CLIP by Learning to Rank Local Patches

The simplest, fastest repository for training/finetuning medium-sized GPTs.

[ECCV 2024 Oral] Code for paper: An Image is Worth 1/2 Tokens After Layer 2: Plug-and-Play Inference Acceleration for Large Vision-Language Models

AI Inference Operator for Kubernetes. The easiest way to serve ML models in production. Supports VLMs, LLMs, embeddings, and speech-to-text.

PyTorch native post-training library

The simplest, fastest repository for training/finetuning small-sized VLMs.

Inference code for CodeLlama models

A workload for deploying LLM inference services on Kubernetes

No description.

DeepSeek-VL: Towards Real-World Vision-Language Understanding

No description.

The code for "TokenPacker: Efficient Visual Projector for Multimodal LLM", IJCV2025

🚀 「大模型」1小时从0训练26M参数的视觉多模态VLM！🌏 Train a 26M-parameter VLM from scratch in just 1 hours!

[CVPR 2024 Oral] InternVL Family: A Pioneering Open-Source Alternative to GPT-4o. 接近GPT-4o表现的开源多模态对话模型

llm-d enables high-performance distributed LLM inference on Kubernetes

Detect and redact PII locally with SOTA performance

Eko (Eko Keeps Operating) - Build Production-ready Agentic Workflow with Natural Language - eko.fellou.ai

An AI-powered Personal Identifiable Information (PII) scanner.

Analyze the inference of Large Language Models (LLMs). Analyze aspects like computation, storage, transmission, and hardware roofline model in a user-friendly interface.

A simple, fast, embeddable, persistent key/value store written in pure Go. It supports fully serializable transactions and many data structures such as list, set, sorted set.

MCP for xiaohongshu.com

Kubeflow Website

☸️ Easy, advanced inference platform for large language models on Kubernetes. 🌟 Star to support our work!

kro | Kube Resource Orchestrator

SpotServe: Serving Generative Large Language Models on Preemptible Instances

Cross-platform asynchronous I/O

The Cloud-Native API Gateway and AI Gateway

Dynolog is a telemetry daemon for performance monitoring and tracing. It exports metrics from different components in the system like the linux kernel, CPU, disks, Intel PT, GPUs etc. Dynolog also integrates with pytorch and can trigger traces for distributed training applications.

NVIDIA GPU metrics exporter for Prometheus leveraging DCGM

sched_ext schedulers and tools

Making large AI models cheaper, faster and more accessible

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

Fast container image distribution plugin with lazy pulling

A scalable generative AI framework built for researchers and developers working on Large Language Models, Multimodal, and Speech AI (Automatic Speech Recognition and Text-to-Speech)

Wan: Open and Advanced Large-Scale Video Generative Models

开源白板工具（SaaS），一体化白板，包含思维导图、流程图、自由画等。All in one open-source whiteboard tool with mind, flowchart, freehand and etc.

Python SDK, Proxy Server (LLM Gateway) to call 100+ LLM APIs in OpenAI format - [Bedrock, Azure, OpenAI, VertexAI, Cohere, Anthropic, Sagemaker, HuggingFace, Replicate, Groq]

Clean personally identifiable information from dirty dirty text.

An offical implementation of PatchTST: "A Time Series is Worth 64 Words: Long-term Forecasting with Transformers." (ICLR 2023) https://arxiv.org/abs/2211.14730

Blazing-fast query execution engine speaks Apache Spark language and has Arrow-DataFusion at its core.

CRIU based GPU workload migration in Kubernetes

💖🧸 Self hosted, you owned Grok Companion, a container of souls of waifu, cyber livings to bring them into our worlds, wishing to achieve Neuro-sama's altitude. Capable of realtime voice chat, Minecraft, Factorio playing. Web / macOS / Windows supported.

Github Pages template based upon HTML and Markdown for personal, portfolio-based websites.

Train transformer language models with reinforcement learning.

Enable macOS HiDPI and have a native setting.

Unlock your displays on your Mac! Flexible HiDPI scaling, XDR/HDR extra brightness, virtual screens, DDC control, extra dimming, PIP/streaming, EDID override and lots more!

Easily embed, cluster and semantically label text datasets

Command-line client for WebSockets, like netcat (or curl) for ws:// with advanced socat-like functions

Run your own AI cluster at home with everyday devices 📱💻 🖥️⌚

A Library for Advanced Deep Time Series Models.

Official implement of ATFNet: Adaptive Time-Frequency Ensembled Network for Long-term Time Series Forecasting

[VLDB' 25] ChatTS: Understanding, Chat, Reasoning about Time Series with TS-MLLM

PySpark Tutorial for Beginners - Practical Examples in Jupyter Notebook with Spark version 3.4.1. The tutorial covers various topics like Spark Introduction, Spark Installation, Spark RDD Transformations and Actions, Spark DataFrame, Spark SQL, and more. It is completely free on YouTube and is beginner-friendly without any prerequisites.