🔥 [ICML 2026] GenShield: Unified Detection and Artifact Correction for AI-Generated Images

Sealos is an AI-native Cloud Operating System built on Kubernetes that unifies the entire application lifecycle, from development in cloud IDEs to production deployment and management. It is perfec…

OpenSquilla — Token-Efficient AI Agent with same budget, higher intelligence density

OSCAR: Offline Spectral Covariance-Aware Rotation for 2-bit KV Cache Quantization

Modular SenseNova skills for building AI-powered office assistants and productivity workflows

An autonomous research colleague — from a question to a compiled manuscript, while you sleep.

Official Implementation of "PRTS: A Primitive Reasoning and Tasking System via Contrastive Representations"

DeepBot is a system-level AI assistant built for both personal productivity and enterprise workflows — one-click setup, seamless experience, and native Feishu integration.

An agent capable of self-evolving and dynamically hardening security

Lifecycle-Aware Memory for long-horizon LLM agents — 66.05% on PaperBench, 94.66% on SurveyBench, 10 peer-reviewed acceptances at FSE/ICML/TOSEM/AEI/ICoGB

Artificial Socialnics Program Operation System

A curated list of AI-powered browser extensions, plugins, and add-ons.

Text and code embeddings research from CodeFuse: C2LLM, D2LLM, E2LLM, F2LLM, ML-Embed

An auto-company works for 24/7 on your own PC - Windows/Linux/macOS.

[NeurIPS2025 spotlight★] Official implementation for "RepLDM: Reprogramming Pretrained Latent Diffusion Models for High-Quality, High-Efficiency, High-Resolution Image Generation".

Self-evolving cognitive memory and context engine for AI agents in Java. Empowering 24/7 proactive agents like OpenClaw with understanding and SOTA performance.

Source code of wikispeedrun.io

MemoryBear Equip AI with human-like memory capability

High Performance Redis-API Compatible Distributed Database with Persistency, Scalability, Full ACID Transactions, and Tiered S3 Storage Cost Efficiency

ICLR 2026 code for Echoes as Anchors: Echo-of-Prompt, attention refocusing, and probabilistic analysis of LLM reasoning.

A clean Bot running on your PC, interacting with you on Telegram via Claude or Codex.

Track how your AI agents work, what they cost, and your agents heatmaps. Stop guessing your AI spend.

The code of MedArk is available for SIGIR'25.

Privacy-focused fork of Claude Code with all telemetry and analytics removed

Replace coding puzzles with real-work simulations.

A curated list of awesome skills for agents in Web3 and crypto.