# Qwen Code Open coding agent with terminal, editor integration and a choice of model providers. Canonical profile: https://ki-agentenkompass.de/en/agents/qwen-code/ Editor: [Michael Meierhoff](https://ki-agentenkompass.de/en/about/) Sources reviewed: 2026-10-19 Basis: provider documentation. Examples are editorial suggestions, not hands-on product tests. ## Overview Available coding agent from the Qwen team, developed independently. - Provider: Alibaba / Qwen - Product family: Qwen Code - Profile type: Coding agent - Environment: Own computer; terminal and editor - Connections: Choose models, Connect editors, Agent teams, Tools, Automate - Setup: Install and connect an API provider or local model server. - Pricing model: Apache-2.0 software; model and operating costs are separate. ## Key features ### Choose models Use multiple API protocols and local models. Source: https://github.com/QwenLM/qwen-code ### Connect editors Integration with VS Code, Zed and JetBrains. Source: https://github.com/QwenLM/qwen-code ### Agent teams Delegate subtasks to subagents. Source: https://github.com/QwenLM/qwen-code ### Tools Connect MCP servers for additional capabilities. Source: https://github.com/QwenLM/qwen-code ### Automate Use headless mode for scripts and CI. Source: https://github.com/QwenLM/qwen-code ## Example workflows ### Example task 1 - Your input: Fix a bug with a reproducible test. - Possible result: A draft for expert review. - What to check: Check inputs, output and performed actions. ### Example task 2 - Your input: Explain a module and suggest refactoring. - Possible result: A draft for expert review. - What to check: Check inputs, output and performed actions. ## Requirements and limits ### Setup Requirement: Install and connect an API provider or local model server. Source: https://github.com/QwenLM/qwen-code ### Product boundaries Limitation: Web UI and daemon are experimental; review code changes. Source: https://github.com/QwenLM/qwen-code ### Output quality Not yet confirmed: Success rates and German-language operation have not been tested here. Source: https://github.com/QwenLM/qwen-code ## A good fit if … - you want a terminal coding agent and choose the model yourself - you want to build it into scripts or CI through headless calls - you can configure approval modes and sandbox yourself in settings files ## Less suitable if … - you expect the former free Qwen OAuth tier; it was discontinued on 15 April 2026 - you need central management with roles and audit logs; the reviewed pages describe only system-scope settings Editorial assessment based on provider documentation. Not a product test. ## Usable AI models Open choice You use Qwen Code with a Qwen subscription, the Alibaba Coding Plan or your own API keys for OpenAI, Anthropic and Gemini interfaces. An OpenAI-compatible endpoint also lets you use OpenRouter and local servers such as Ollama, LM Studio or vLLM. You can switch models during a session. - Model families named: Alibaba (Qwen), OpenAI (GPT), Anthropic (Claude), Google (Gemini), Z.ai (GLM), Moonshot (Kimi), MiniMax · Other models can be connected freely - Model choice: You choose - Your own API key: Yes - Router or custom endpoint: Yes - Local models: Yes Documented · Sources accessed on: 2026-11-05 - [Qwen Code: Repository](https://github.com/QwenLM/qwen-code) - [Qwen Code: Model providers](https://github.com/QwenLM/qwen-code/blob/main/docs/users/configuration/model-providers.md) - [Qwen Code: Authentication](https://github.com/QwenLM/qwen-code/blob/main/docs/users/configuration/auth.md) ## Europe & regional availability Installation instructions and model prerequisites reviewed. The assessment covers the local operating path described; complete country and feature availability of all connected services remains open. Reviewed scope: Local software and documented self-hosting; external services assessed separately Reviewed on: 2026-10-19 ### Self-hosting with own model access With requirements Qwen Code documents local installation for Linux, macOS and Windows and own API providers or local models through Ollama and vLLM. Regional conditions apply to the model service actually selected. Region covered: Europe: own computer or server; model services are country-specific Documented reason: Technical assessment based on installation and provider selection. These sources do not establish a legal cause for regional restrictions. Official source: https://raw.githubusercontent.com/QwenLM/qwen-code/main/README.md ## Accounts & permissions Based on provider documentation. Permissions depend on the account, integration and organization policies. Review the permissions actually requested before use. Configuration covered: Qwen Code as a local command-line tool with a model access of your choice Sources reviewed: 2026-11-05 ### Account used Documented: You sign in through /auth: with QwenCloud or Alibaba ModelStudio, a third-party provider or your own compatible endpoint. The free Qwen OAuth tier was discontinued on 15 April 2026. API keys are read from environment variables or a .env file; settings.json is a lower-priority fallback. Evidence: https://qwenlm.github.io/qwen-code-docs/en/users/configuration/auth/ ### Admin approval Documented with conditions: Control lies in settings files. Operators can set, among other things, the approval modes offered by the Web Shell and a Linux sandbox policy in the system scope. According to the page, the mode selection is presentation only and does not enforce backend permissions. The page does not describe an organisation approval. Evidence: https://qwenlm.github.io/qwen-code-docs/en/users/configuration/settings/ ### Data access & team sharing Documented with conditions: In YOLO mode the AI can execute any command with your terminal permissions. Session backups for /rewind live under ~/.qwen/file-history. The reviewed pages do not describe team sharing; the experimental qwen serve daemon lets several clients share sessions and by default listens on loopback without bearer authentication. Evidence: https://qwenlm.github.io/qwen-code-docs/en/users/features/approval-mode/ Evidence: https://qwenlm.github.io/qwen-code-docs/en/users/configuration/settings/ Evidence: https://github.com/QwenLM/qwen-code ## Prices and included usage Pricing checked: 2026-10-19 Apache-2.0 software; model and operating costs are separate. Billing depends on plan, usage and setup. Pricing details: https://github.com/QwenLM/qwen-code ## Operation & oversight Based on public provider documentation. Assessments are editorial inferences from the stated properties. Actual time requirements and reliability have not been measured. Deployment covered: Local operation in the terminal and in headless mode (qwen -p) Sources reviewed: 2026-11-05 ### Files and working state Documented with conditions: Saving chat history to disk is on by default. Session backups used by /rewind are retained for 30 days by default. Turning recording off also stops --continue and --resume from working. Evidence: https://qwenlm.github.io/qwen-code-docs/en/users/configuration/settings/ ### Sign-ins Documented with conditions: The page gives no expiry for API keys. Previously cached Qwen OAuth tokens may keep working briefly, but new requests are rejected. Evidence: https://qwenlm.github.io/qwen-code-docs/en/users/configuration/auth/ ### Starting further runs Documented with conditions: Runs start interactively or by headless call (qwen -p) from scripts and automation; the qwen serve daemon is labelled experimental. Scheduled tasks (/loop, cron tools) are on by default but live only in the running process and vanish on exit; recurring tasks expire after 7 days by default. Evidence: https://qwenlm.github.io/qwen-code-docs/en/users/features/headless/ Evidence: https://qwenlm.github.io/qwen-code-docs/en/users/features/scheduled-tasks/ Evidence: https://github.com/QwenLM/qwen-code ### Human intervention Documented with conditions: There are five modes: Plan, Ask Permissions, Auto-Edit, Auto and YOLO. Which mode is the default is inconsistent within the page. In YOLO mode the AI can execute any command with your terminal permissions. Evidence: https://qwenlm.github.io/qwen-code-docs/en/users/features/approval-mode/ ### Detecting errors Documented: Headless mode produces text, JSON or stream-JSON with usage data. Budgets for wall time, tool calls and turns end with exit code 53 or 55, an interrupt with 130. An exit code for ordinary failures is not documented there. Evidence: https://qwenlm.github.io/qwen-code-docs/en/users/features/headless/ ### Resuming after failures Documented with conditions: With --continue or --resume you resume sessions with their history. /rewind rolls the conversation back to an earlier turn; /restore reverts project files from a checkpoint, but checkpointing is off by default. For unattended runs the variable QWEN_CODE_UNATTENDED_RETRY retries requests with delays capped at 5 minutes. Evidence: https://qwenlm.github.io/qwen-code-docs/en/users/features/headless/ Evidence: https://qwenlm.github.io/qwen-code-docs/en/users/features/commands/ Evidence: https://qwenlm.github.io/qwen-code-docs/en/users/features/checkpointing/ ### Editorial assessment Operation and control are with you: you set approval mode, sandbox, budgets and scheduling yourself. Scheduled tasks do not survive ending the session; unattended runs need budgets and an external trigger such as cron or CI. ## Memory and conversation continuity Scope: Qwen Code documentation dated 2026-10-22 Sources accessed: 2026-11-04 Instruction files plus automatic Markdown memories and optional structured recall. ### Storage and scope Documented: QWEN.md contains instructions; auto-memory is Markdown under ~/.qwen/projects//memory/. - [Qwen Code Memory](https://qwenlm.github.io/qwen-code-docs/en/users/features/memory/) - [Qwen Code repository](https://github.com/QwenLM/qwen-code) ### Selection and timing Documented: Auto-memory saves useful preferences, feedback and context after conversations; it is enabled by default. Periodic maintenance has a separate toggle. - [Qwen Code Memory](https://qwenlm.github.io/qwen-code-docs/en/users/features/memory/) - [Qwen Code repository](https://github.com/QwenLM/qwen-code) ### Inspect, edit and delete Documented: /memory opens management and files; /remember, /forget and /dream control saving, forgetting and maintenance. Markdown can be edited directly. - [Qwen Code Memory](https://qwenlm.github.io/qwen-code-docs/en/users/features/memory/) - [Qwen Code repository](https://github.com/QwenLM/qwen-code) ### Agent and channel boundaries Documented: Branches in one checkout share memory; linked worktrees have their own memory. Optional team memory is shared through Git. - [Qwen Code Memory](https://qwenlm.github.io/qwen-code-docs/en/users/features/memory/) - [Qwen Code repository](https://github.com/QwenLM/qwen-code) ### Retrieval Documented: The default is a MEMORY.md index. Optional structured recall injects relevant subtrees and adds search_memory for full entries. - [Qwen Code Memory](https://qwenlm.github.io/qwen-code-docs/en/users/features/memory/) - [Qwen Code repository](https://github.com/QwenLM/qwen-code) ### Session reset and compaction Partly documented: New sessions begin with fresh context and reload durable knowledge. /dream maintains memories; this memory page does not explain conversation-window compaction. - [Qwen Code Memory](https://qwenlm.github.io/qwen-code-docs/en/users/features/memory/) - [Qwen Code repository](https://github.com/QwenLM/qwen-code) ## Context Web UI and daemon are experimental; review code changes. Provider sources reviewed; examples are editorial suggestions. No hands-on test. ## Open points Requirements and limits, not yet confirmed: - Output quality ## Sources - https://github.com/QwenLM/qwen-code ## Provider Product and provider are documented through the linked original sources. - Operator: Alibaba / Qwen - Organization: Provider - Website: https://github.com/QwenLM/qwen-code - Reviewed: 2026-10-19 - Provider source: https://github.com/QwenLM/qwen-code [Sources and method](https://ki-agentenkompass.de/en/sources/)