Official code for world model Kairos

[ICML 2026] Towards Streaming Synchronized Spatial Audio Generation via Autoregressive Diffusion Transformer

Automatic and end-to-end scientific research workflow enabled by OpenClaw. Produces state-of-the-art level research results.

[AutoArk] GPA (General Purpose Audio) can do ASR, TTS and voice conversion with one tiny model!

OpenGUI is an Android GUI agent framework for phone-use AI that can see, plan, and operate real mobile apps through the GUI.

Agent skill for migrating Tableau, Looker, and Power BI dashboards to Hex apps: extract specs, rebuild with Hex AI, verify parity

A blueprint-driven AutoResearch runtime for orchestrating AI research workflows from idea generation and experiments to paper writing and peer review.

Easy Data Preparation with latest LLMs-based Operators and Pipelines.

MemoryBear Equip AI with human-like memory capability

本项目实现了从传统机器学习到 BERT 预训练模型的完整迭代，并通过动态量化与知识蒸馏技术，在保障高准确率（93.64%）的同时，实现了极致的推理加速与模型轻量化，完美适配线上高并发推荐场景

AI-driven inverse antenna design with real NEC2 + openEMS in the loop. Try the live in-browser playground.

One portable memory layer for every AI agent: local-first, Markdown-native, user-owned, and self-evolving across apps, tools, and workflows.

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

An agent capable of self-evolving and dynamically hardening security

Benchmark for Large Model Feature Coding

OpenTalking: An industrial-grade open-source AI digital human framework that supports real-time conversation, private deployment, and pluggable models.

Context drive for your AI agents

Replace coding puzzles with real-work simulations.

Unified real-time search engine skill for AI agents. Supports general web search, vertical domain search, parallel batch search, and full-page content extraction.

Official repository for textual frequency law

Search-Then-Verify natural language querying over time series databases (ICML 2026). Includes NLQTSBench.

Built by DeepSeek, for DeepSeek — a Swift-native macOS coding agent

Drift: DLM Reinforcement Learning Training Framework

[CVPR 2026] Official implementation of "Robo-Dopamine: General Process Reward Modeling for High-Precision Robotic Manipulation"

Your First AI Agents Company

Estimate whether a Hugging Face model fits and fine-tunes on your local GPU.

Machine learning and optimization models designed to enhance financial system stability through portfolio optimization, risk forecasting, and network-based financial risk analysis.

ClawProBench is a live-first benchmark harness for evaluating LLM agents in the OpenClaw runtime with deterministic grading and repeated-trial reliability.

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