Highlights
Stars
SenseNova-U series: Native Unified Paradigm with NEO-unify from the First Principles
[NeurIPS 24] PromptFix: You Prompt and We Fix the Photo
Anoamly-detection-driven deployment safety for production AI/ML systems
One portable memory layer for every AI agent: local-first, Markdown-native, user-owned, and self-evolving across apps, tools, and workflows.
Machine learning and decision intelligence models designed to improve healthcare safety through clinical risk prediction and medical interaction analysis.
JAVEdit: Joint Audio-Visual Instruction-Guided Video Editing with Agentic Data Curation
Scaling the Horizon, Not the Parameters
MemoryBear Equip AI with human-like memory capability
Inference-native Tokenmaxxing Agent Harness for Loop Engineering
🎯 A general-purpose protocol stack analysis and debugging tool based on eBPF 🧰
An agent capable of self-evolving and dynamically hardening security
Automatic and end-to-end scientific research workflow enabled by OpenClaw. Produces state-of-the-art level research results.
🚀 Ultra Recipe for Training Long-Horizon Search Agents - matching frontier AI's search capability with a 20B model + stateful harness
AdaRubric: Adaptive Dynamic Rubric Evaluator for Agent Trajectories
Cloud-native agent-as-a-service framework with one-click IaC deployment.
[ICLR2026] This is the first paper to explore how to effectively use R1-like RL for MLLMs and introduce Vision-R1, a reasoning MLLM that leverages cold-start initialization and RL training to incen…
Modular SenseNova skills for building AI-powered office assistants and productivity workflows
Unified real-time search engine skill for AI agents.
Estimate whether a Hugging Face model fits and fine-tunes on your local GPU.
Built by DeepSeek, for DeepSeek — a Swift-native macOS coding agent
Turns corrections into Preferences, Project-specific skills, and Shared skills for Claude Code, Codex, and OpenCode.
Repository for EffOPD. We are working on polishing the details.
Open-source room for humans + cross-vendor AI agents. Every agent gets its own name, memory, skills, and workstation. Any runtime, your infra — no per-agent fees.
Federation over Text (FoT) is a federated-learning-like paradigm for multi-agent reasoning.
A benchmark for evaluating LLMs on Chinese traditional fortune telling — Bazi (八字) and Ziwei Doushu (紫微斗数).
Tutorials, Guides and Agent Skills Directories