Open Source Project

The world's first open-source quantum AI model series, through AI-driven quantum chip calibration and error correction, provides a high-performance tool chain for practical quantum computing and reshapes the quantum industry ecosystem.

The new generation of domestic open-source flagship big model has become one of the strongest all-around AIs on the ground with millions of ultra-long contexts, performance comparable to the top international closed-source models, and extreme cost-effectiveness.

A 4.2 billion-parameter open source body intelligence model developed by Variable Robotics realizes “out-of-the-box” zero-sample deployment capability by virtue of its innovative end-to-end architecture, allowing developers to empower robots with powerful cognitive, reasoning, and fine manipulation capabilities with only a consumer-grade graphics card.

An extreme Token-saving, open-source, general-purpose AI Agent with Skill skill ecosystem support that automates programming, office and all kinds of complex tasks for you locally at a very low cost.

An open-source AI short-form drama production platform—a fully automated pipeline that takes a novel and turns it into a finished video. It features skeleton binding to prevent face distortion, produces an episode in 8 minutes, and keeps costs down to just over ten yuan.

An open-source project based on Claude Code that uses 48 layered AI agents to simulate an entire game development team, enabling a single person to manage the entire process from design to launch.

Alibaba's open-source AI code review CLI tool employs a hybrid architecture combining "deterministic engineering" and an "LLM agent." It performs line-level code defect detection, supports multiple models, and can be integrated into CI/CD pipelines. It is fully open-sourced under the Apache 2.0 license.

AliQianwen, the first native language world model released on June 24, 2026, uses plain text to uniformly simulate seven major digital environments, allowing agents to practice in a "virtual world."

A Microsoft open-source framework that automatically optimizes agent skills—just like training a neural network—without fine-tuning the model, enabling consistent improvement in capabilities and cross-environment transfer.

Alibaba's open-source large-scale speech model supports zero-shot cloning in 3 seconds, multilingual capabilities, and command-based emotional control, enabling ultra-low-latency streaming synthesis at 150 ms.

An open-source, pure front-end GUI agent framework from Alibaba that requires no screenshots or backend; with just one line of code, it enables any web page to support natural language interaction and automated operations.

Ant Group has launched a new-generation spatial perception model for robots that enhances 3D depth perception capabilities and improves performance in grasping, navigation, and environmental understanding.

A multi-agent collaboration framework jointly open-sourced by Ant Group and Renmin University of China, it schedules search agents much like an operating system and efficiently completes complex, long-duration deep information retrieval tasks through global shared state and pipelined parallel mechanisms.

An open-source, AI-driven PowerPoint generation workflow that automatically converts various types of documents into natively editable PowerPoint files, rather than static images.

The main agent breaks down tasks, coordinates research, writing, administrative, and development assistants, and handles multi-step workflows continuously within the desktop.

NVIDIA OpenShell provides a controlled execution environment for AI agents through sandboxing, file and network policies, and credential proxy, making it ideal for development teams to deploy and manage permissions.

Paperclip centralizes the management of tasks, roles, budgets, approvals, and operational logs for multiple AI agents. It supports self-hosting and is ideal for individual developers and small teams to collaborate on AI projects.

OpenCode is an open-source AI programming agent launched by Anomaly that assists users in understanding projects, modifying code, and reviewing changes via terminal, desktop, and web interfaces, and supports integration with multiple models. This article covers how to use V2, pricing limits, and recent updates from October 2026.

A "local-first" shared memory app launched by Tencent Hunyuan allows authorized AI tools to access conversation and coding context; it is currently still in preview.

Run open models on-premises or in the cloud, with desktop chat, command-line, and development interfaces available, making it ideal for local AI experiments and application integration.

An open-weight model for locally programming agents, designed to work with Pi, OpenCode, and OpenHands for code understanding, modification, and testing.

An open source AI intelligence framework for local file management, cross-tool automation, and lightweight development assistance via natural language commands, balancing privacy protection with low-code ease of use.

Alibaba launched an efficient video generation model that can accurately simulate complex scenes and actions, support Chinese and English special effects, and lead a new era of AI video creation.

The AI model, which is open-source under the MIT License, has advanced reasoning capabilities and supports model distillation. Its performance is benchmarked against OpenAI o1 official version and has performed well in multi task testing.