- fix(serve): preserve session creation failure diagnostics
- feat(sdk-java): Add managed runtime attestation client
- feat(web-shell): select a time range on the trajectory overview to narrow the table
- feat(serve,web-shell): set the Qwen Live endpoint and model from settings
- feat(channels): separate private and group access policies
- fix(core): bound oversized images returned by MCP tools
Qwen Code by Alibaba Cloud (Qwen)
Overview
Alibaba's open-source terminal coding agent for Qwen models that also offers a desktop app, web UI, IDE plugins (VS Code, Zed, JetBrains) and SDKs. It accepts OpenAI-, Anthropic- and Gemini-style provider APIs as well as local models.
Qwen Code was downloaded 105K times from npm in the week ending Oct 4, 2026, up 30.8% on the week before and up 5.5% over the last 30 days compared with the 30 before. Its VS Code extension has 373K installs and average 3.2 out of 5 across 52 marketplace ratings. The GitHub repository has 28.3K stars, 778 of them added in the last 30 days. The latest stable release is 0.25.0, published Oct 5, 2026; there were 32 stable releases in the past 30 days. It was mentioned in 5 Hacker News posts and comments over the last 30 days.
Recent developments
- 2026-04-15: Qwen OAuth free tier discontinued
Qwen Code usage and attention over time
Download the raw daily series: qwen-code.csv
Install Qwen Code
| npm | npm install -g @qwen-code/qwen-code |
|---|---|
| Homebrew | brew install qwen-code |
| VS Code | code --install-extension qwenlm.qwen-code-vscode-ide-companion |
These commands use the packages tracked on this page. The vendor may recommend a different installer; see the official documentation.
Key facts
| Maker | Alibaba Cloud (Qwen) |
|---|---|
| Type | Terminal agent + IDE extensions |
| First released | July 2025 |
| License | Apache-2.0 |
| Interfaces | CLI, Desktop, Web, IDE extension, SDK |
| Platforms | macOS, Linux, Windows |
| Models | Qwen models (Alibaba ModelStudio Coding Plan, Token Plan or API key) plus third-party and local providers |
| Local models | Ollama or vLLM through an OpenAI-compatible provider (docs) |
| Bring your own API key | Yes |
| Main language | TypeScript |
| Open issues and PRs | 1,691 |
| Open VSX downloads | 821,449 (includes updates) |
| Homebrew installs | 2,472 in 30 days · 69,006 in a year |
Pricing
The CLI is free and open source; model access is via Alibaba Cloud ModelStudio (Coding Plan with weekly quota for individuals, Token Plan with usage billing for teams), an API key, or third-party/local providers. The Qwen OAuth free tier was discontinued on 2026-04-15; plan prices were not verified.
Source: official pricing page, checked Oct 5, 2026. Prices change often; confirm before you buy.
Pulse Score breakdown
Each component is scored 0 to 100 from public signals; a dash means no data for it. Methodology.
What changed: recent Qwen Code releases
- Managed memory availability now respects the memory.enableManagedAutoMemory setting (#6941). Hosts that disable managed auto memory no longer see remember/dream requests admitted or managed-memory…
- Size-triggered microcompaction now clears old tool results toward a low watermark (#8464), so it no longer rewrites another part of the conversation prefix on every subsequent turn. Provider…
- chore: bump version to 0.8.2
- chore(release): sdk-typescript v0.1.4
- Fix: Use resolved authType to initialize ACP agent
- Add parentToolCallId and subagentType for ACP subagent tracking
- feat(agents): add local workspace-agent collaboration
- Introduces generic Broker provider controls with a versioned worker contract for manifest, turn preparation, tool approval, preflight, and file history.
- feat(managed-agent): enable G0 public Workspace file turns
- feat(sdk-java): Add audited Hosted Workspace operator recovery
- feat(memory): bundle Mem0 with the main CLI
- feat(agents): add A2A access and sharing for workspace agents
- Managed memory availability now respects the memory.enableManagedAutoMemory setting (#6941). Hosts that disable managed auto memory no longer see remember/dream requests admitted or managed-memory…
- Size-triggered microcompaction now clears old tool results toward a low watermark (#8464), so it no longer rewrites another part of the conversation prefix on every subsequent turn. Provider…
- chore: bump version to 0.8.2
- chore(release): sdk-typescript v0.1.4
- Fix: Use resolved authType to initialize ACP agent
- Add parentToolCallId and subagentType for ACP subagent tracking
- fix(serve): preserve session creation failure diagnostics
- feat(sdk-java): Add managed runtime attestation client
- feat(web-shell): select a time range on the trajectory overview to narrow the table
- feat(serve,web-shell): set the Qwen Live endpoint and model from settings
- feat(channels): separate private and group access policies
- fix(core): bound oversized images returned by MCP tools
- feat(managed-agent): admit workspace-bound sessions without execution
- feat(cli): Run Managed Runtime tools in the Session's Workspace directory
- feat(acp-bridge): route sessions across legacy and managed engines
- feat(serve): Enable private Hosted Harness no-tool text turns
- feat(managed-agent): Define the managed-tool-result/1 contract (O1a)
- feat(acp-bridge): back paired engine selection with session owners and typed rejections
Qwen Code alternatives
| # | Agent | Pulse | Downloads 7d | 7d | 30d | VS Code installs | Stars | Latest release | Price | Last 90 days | |
|---|---|---|---|---|---|---|---|---|---|---|---|
| 1 |
OpenAI CodexOpenAI |
83 | 25.6M | up 5.7% | up 21.2% | 15.2M | 128K+153/day | 0.160.1yesterday | Free + $8/mo | ||
| 3 |
Claude CodeAnthropic |
80 | 14.8M | up 11.6% | down 36.4% | 27.1M | 150K+161/day | 2.1.290yesterday | $20/mo | ||
| 5 |
PiEarendil Inc. (created by Mario Zechner) |
75 | 5.2M | up 29.8% | up 52.1% | — | 113K+378/day | 1.0.4yesterday | Free (OSS) | ||
| 7 |
OpenCodeAnomaly (SST team) |
73 | 3.3M | up 22.0% | up 6.1% | 1.2M | 212K+200/day | 1.18.346d ago | Free + $10/mo | ||
| 24 |
Gemini CLIGoogle |
57 | 453K | up 4.7% | up 1.8% | 1.1M | 107K+24/day | 0.62.07d ago | Varies | ||
| 26 |
Oh My PiStencil Labs (Can Bölük) |
56 | 241K | up 11.4% | up 53.9% | — | 34.4K+111/day | 18.6.12d ago | Free (OSS) | ||
| No agents match that filter. | |||||||||||
Qwen Code FAQ
How much does Qwen Code cost?
The CLI is free and open source; model access is via Alibaba Cloud ModelStudio (Coding Plan with weekly quota for individuals, Token Plan with usage billing for teams), an API key, or third-party/local providers. The Qwen OAuth free tier was discontinued on 2026-04-15; plan prices were not verified.
Is Qwen Code open source?
Yes. Qwen Code is open source, released under the Apache-2.0 license.
How popular is Qwen Code?
Qwen Code was downloaded 105K times from npm in the week ending Oct 4, 2026, up 30.8% on the week before and up 5.5% over the last 30 days compared with the 30 before. Its VS Code extension has 373K installs and average 3.2 out of 5 across 52 marketplace ratings. The GitHub repository has 28.3K stars, 778 of them added in the last 30 days.
What is the latest version of Qwen Code?
The latest stable release we track is 0.25.0, published on Oct 5, 2026.
What are the alternatives to Qwen Code?
The closest alternatives in the same category by Pulse Score are OpenAI Codex, Claude Code, Pi, OpenCode.
Where these numbers come from
npm: @qwen-code/qwen-code. GitHub: QwenLM/qwen-code. VS Code Marketplace: qwenlm.qwen-code-vscode-ide-companion. Homebrew: qwen-code. See data sources for how each one is collected.
Product facts and pricing were checked against: github.com, qwenlm.github.io, registry.npmjs.org, formulae.brew.sh, marketplace.visualstudio.com, open-vsx.org.
