Overview
Qoder is an Agentic AI programming platform launched by Alibaba, first released in August 2025, with version 1.0 officially launched on May 15, 2026, upgrading from an 'AI IDE' to a comprehensive 'Agent Autonomous Development Workbench'.
The core concept is 'Autonomous Driving Programming': developers only need to define the goal, and the entire process of execution, verification, and delivery is autonomously completed by the AI Agent. Qoder integrates the world's top programming models, provides ultra-long context capabilities (retrieving 100,000 code files at once), supports cross-project parallel tasks, and allows the creation of dedicated Agent teams. The concurrently launched QoderWork design workbench supports voice-generated professional design, achieving 'Design as Code'.
**Major Update on 2026/6/8: Team Knowledge Engine**, completely addressing the shortcomings of traditional AI programming tools such as 'easy to forget, hard to reuse, and low efficiency'—upgrading AI from a simple Q&A tool to a collaborative partner that can continuously accumulate team engineering experience and reuse knowledge across sessions and members. **Note**: Qoder and another Alibaba Cloud product line 'Qoder CN' (formerly Tongyi Lingma, renamed on 2026/5/20) are two related but independent brands—Qoder focuses on a global Agentic programming platform, while Qoder CN is positioned as a full-scenario agent matrix upgraded from domestic IDE plugins. Both are backed by Alibaba's Tongyi Qwen3 series code models.
Key Features
- Team Knowledge Engine (New): Updated on 2026/6/8, AI continuously accumulates team engineering experience, reuses knowledge across sessions and members, solving the pain points of traditional AI programming being 'easy to forget and hard to reuse'
- Quest Mode Independent Workbench: Upgraded to an independent window in version 1.0, integrating task management, status tracking, artifact tracing, and knowledge invocation; developers only need to define the goal
- Agent Autonomous Development: The entire process of execution, verification, and delivery is autonomously completed by the Agent, ushering AI programming into 'autonomous driving' mode
- Cross-Project Parallel Capability: Parallel scope extended to cross-project and cross-codebase, with multiple Workspaces running different Agent tasks simultaneously, providing a global view on one screen
- Ultra-Long Context: Retrieves 100,000 code files at once, offering the industry's strongest codebase context engineering capability
- Custom Expert Agent: Allows creation of dedicated Agent teams, configuring domain knowledge, task skills, and external tool interfaces to fit business scenarios
- Spec-Driven Development: Requirements → Specifications → Code automatic transformation, automatically breaking down complex tasks into detailed design specifications and implementing them
- Deep Context View: View file directories, code changes, terminal output, and browser preview without leaving the current workflow
- Summary Delivery Checklist: Automatically generates a complete delivery summary after task completion, facilitating review and acceptance
- QoderWork Design Workbench: Supports voice input to generate professional designs, outputting runnable, editable, and deliverable artifacts on an infinite canvas, with over 100 built-in style references
- MCP Tool Ecosystem: Supports MCP (Model Context Protocol) extensions, allowing integration with a rich variety of external tools and services
Use Cases
- Full-stack development of enterprise-level complex projects, requiring AI to autonomously complete requirement decomposition to code delivery
- Senior developers who need to handle multiple projects or codebases in parallel
- Product and engineering teams looking to quickly generate complete business systems through natural language descriptions
- High-complexity tasks such as refactoring, migration, and test writing for large codebases
- Collaboration between designers and developers, leveraging Design Desk to achieve 'Design as Code'
Pros
- The entire process from 'goal definition to automatic delivery' is autonomously completed by the Agent, achieving revolutionary efficiency improvements
- Ultra-long context (retrieval of 100,000 files), handling large projects with ease
- Cross-project parallel capability, managing multiple Quest tasks on one screen
- Customizable dedicated Agent teams, accumulating team best practices
- Supports Windows/macOS/Linux three platforms + VS Code/JetBrains plugins + CLI
- Backed by Alibaba Cloud, stable domestic access, free download for trial
- QoderWork design workbench bridges design and development, achieving 'Design as Code'
Pricing
Free download for trial. Basic features are free to use, with the team version launching in December 2025. For detailed enterprise-level subscription pricing, please refer to the latest official website announcement.
Summary
Qoder 1.0 is a significant milestone in the AI programming track in 2026. It no longer positions itself as an 'IDE plugin for assistance' but as a 'full-stack development team that can deliver'—developers only need to define the goal, and the rest of execution, verification, and delivery are all handled by the AI Agent. For enterprise development teams, individual full-stack developers, and engineers facing complex projects, Qoder 1.0 offers autonomy and efficiency far beyond traditional AI programming tools, making it a representative work of domestic Agentic Coding platforms.