RepoRadar
Leave a tipDaily brief
Item detail
github.com

QwenLM/qwen-code

QwenLM/qwen-code is a developer tool in RepoRadar's AI Coding section, holding Gold tier and a 'try now' verdict. Its strongest signal is workflow potential, scored 10.0 out of 10.

Produced and maintained by RepoRadar Research · Methodology · Corrections.

Open on GitHub →Back to radar
Score8.9
Popularity96.0
Riskconditional
TierGold
Score breakdown
Usefulness9.0
Novelty8.0
Momentum9.0
Maturity8.9
Open-source/build8.4
Evidence7.2
Workflow potential10.0
Setup ease6.4

Popularity is tracked separately. Support, ads, sponsorships, and tips never affect these signals.

Why it matters

This is useful because serious coding-agent users want the terminal workflow, but they also want memory, tool use, local-model support, and multi-client options without having to bolt those features on themselves.

Where this stands now

QwenLM/qwen-code ranks #1 of 14 tracked AI Coding items by composite score (8.9 against a section median of 8.2). The section currently carries 12 Gold, 2 Silver. RepoRadar has retained observations for this record since 2026-06-19 (102 days in the current window). Signal extremes versus the section: momentum at the 93th percentile.

Who should use it

AI coding users developers who prefer terminal workflows self-hosters using local models teams comparing open coding agents

Who should skip it

Skip QwenLM/qwen-code if the source link, documentation, or setup requirements do not align with your current workflow or stack.

About this signal

QwenLM/qwen-code is tracked by RepoRadar as a developer tool in the AI Coding section. First seen 2026-06-19; the source record was last checked on 2026-06-19. The current verdict is 'try now' with a Gold tier and moderate setup difficulty. QwenLM/qwen-code leads on workflow potential (10.0) and practical usefulness (9.0); its lowest signal is setup ease (6.4), so factor that in before investing setup time. This page summarizes the public evidence on the linked source page and states where additional review is still needed.

How this item is evaluated

The QwenLM/qwen-code record combines a 8.9/10 composite score with separate popularity (96.0), risk (conditional), and setup (moderate) signals. See the scoring methodology for the current weights and evidence definitions.

Questions worth asking before you adopt this
RepoRadar analyses featuring this item

Putting this into practice? Read How to evaluate an AI tool before you adopt it for the checklist behind this score.

Risk explanation

This agent can edit files, call tools, and route prompts to third-party or local model backends, so review tool permissions and keep it on a non-critical repository before broader use.

Evidence links
Closest alternatives / related signals
ai-coding terminal mcp agent local-models
Verification record

What RepoRadar actually verified

Tested in a bounded workflow Source-only update since test

Bounded representative workflow retained by RepoRadar verification harness. Last checked 2026-07-14T05:09:18.406791Z.

A source release dated 2026-09-26 is newer than the retained test dated 2026-07-14; the previous test may no longer represent the current release.

Read as a sequence: 4 retained check(s) between 2026-07-13 and 2026-07-14 with outcomes of 2 failed, 1 partial, 1 passed; evidence scopes covered bounded representative workflows and bounded setup checks. Recorded setup time totals 3 minute(s).

partial · cohort-20260712-qwen-code-isolated

Tester
RepoRadar automated local verification harness
Started
2026-07-13T03:20:27.263062Z
Completed
2026-07-13T03:20:30.852130Z
Environment
Windows 10 AMD64; Python 3.11.9; credential-stripped child environment; disposable home/cache
Install/setup time
0 minute(s)
Evidence scope
Bounded setup or capability check
Cleanup
Per-check temporary home and work directory removed. Shared cohort package cache removed.
Actions exercised
  • Created a disposable home, work directory, and isolated package cache with credential-like environment variables excluded.
  • Executed bounded check: Resolve and launch the Qwen Code CLI package.
  • Captured the complete sanitized stdout, stderr, exit status, and 3.59-second wall time.
Observed results
  • Command exited 0 after 3.59 seconds.
  • The command produced a successful local process exit; complete output is retained.
Observed strengths
  • The pinned @qwen-code/[email protected] package resolved in the isolated npm cache, launched, and reported version 0.19.9.
Friction
  • No blocking friction was observed during this bounded local check.
Limitations
  • Only package resolution and version startup were checked; no provider or coding task was configured.
  • This bounded cohort check is not a production benchmark or a claim of real user-workflow adoption.

Pricing assessment: No paid plan or metered provider usage was exercised; package or licensing, hosting, and provider costs remain workflow-dependent.

Privacy assessment: No repository content, user data, or provider prompt was transmitted; broader product data handling was not assessed by this bounded run.

Open retained test log →

failed · cohort-20260714-qwen-code-local-read-agent-workflow

Tester
RepoRadar automated local verification harness
Started
2026-07-14T05:08:04.657022Z
Completed
2026-07-14T05:08:10.668655Z
Environment
Windows 10 AMD64; Python 3.11.9; credential-stripped child environment; disposable home/cache
Install/setup time
1 minute(s)
Evidence scope
Bounded setup or capability check
Cleanup
Per-check temporary home and work directory removed. Shared cohort package cache removed.
Actions exercised
  • Created a disposable home, work directory, and isolated package cache with credential-like environment variables excluded.
  • Created 4 synthetic fixture file(s) inside the disposable work directory; retained hashes prove the exact inputs.
  • Installed the pinned official @qwen-code/[email protected] package with lifecycle scripts disabled inside the disposable work directory.
  • Bound a deterministic OpenAI-compatible fixture server to an operating-system-assigned 127.0.0.1 port and configured the CLI to deny non-read tools.
  • Prompted the CLI to read one synthetic marker through its built-in read_file tool, then asserted exactly two streamed /v1/chat/completions requests.
  • Verified the second request contained the actual tool output, the final CLI output contained the mock's exact response, and the fixture hash was unchanged.
  • Executed bounded check: Run Qwen Code's official CLI against a loopback-only deterministic model that requests its built-in read tool, then verify the real tool result reaches the second model turn.
  • Captured the complete sanitized stdout, stderr, exit status, artifact checks, and 6.01-second wall time.
Observed results
  • Check exited 1 after 6.01 seconds; failure output is retained and the verification stage must not advance.
Observed strengths
  • No product strength was established in this failed attempt; diagnostic evidence is retained.
Friction
  • A deterministic protocol fixture required product-specific isolation flags and provider configuration; real model behavior, authentication, latency, and cost remain deliberately outside this check.
  • Setup or runtime emitted 94 stderr line(s); the complete warnings/errors are preserved in the retained log.
Limitations
  • The local mock validates Qwen Code's provider wire path, agent loop, tool schema, built-in read execution, and final event output; it does not measure hosted-model quality, authentication, provider reliability, interactive UX, long tasks, or write-tool safety.
  • This credential-free disposable workflow does not establish operator use, production scale, model quality, reliability under sustained use, or team adoption.

Pricing assessment: The CLI and loopback model fixture used no account, subscription, API credit, or paid inference; npm was contacted only to retrieve the pinned package.

Privacy assessment: Only a synthetic marker was read and sent to a server bound to 127.0.0.1; package installation contacted npm, while no prompt or fixture content was sent to a model provider.

Open retained test log →

failed · cohort-20260714-qwen-code-local-read-agent-workflow-v2

Tester
RepoRadar automated local verification harness
Started
2026-07-14T05:08:46.052126Z
Completed
2026-07-14T05:08:51.575993Z
Environment
Windows 10 AMD64; Python 3.11.9; credential-stripped child environment; disposable home/cache
Install/setup time
1 minute(s)
Evidence scope
Bounded setup or capability check
Cleanup
Per-check temporary home and work directory removed. Shared cohort package cache removed.
Actions exercised
  • Created a disposable home, work directory, and isolated package cache with credential-like environment variables excluded.
  • Created 4 synthetic fixture file(s) inside the disposable work directory; retained hashes prove the exact inputs.
  • Installed the pinned official @qwen-code/[email protected] package with lifecycle scripts disabled inside the disposable work directory.
  • Bound a deterministic OpenAI-compatible fixture server to an operating-system-assigned 127.0.0.1 port and configured the CLI to deny non-read tools.
  • Prompted the CLI to read one synthetic marker through its built-in read_file tool, then asserted exactly two streamed /v1/chat/completions requests.
  • Verified the second request contained the actual tool output, the final CLI output contained the mock's exact response, and the fixture hash was unchanged.
  • Executed bounded check: Run Qwen Code's official CLI against a loopback-only deterministic model that requests its built-in read tool, then verify the real tool result reaches the second model turn.
  • Captured the complete sanitized stdout, stderr, exit status, artifact checks, and 5.52-second wall time.
Observed results
  • Check exited 1 after 5.52 seconds; failure output is retained and the verification stage must not advance.
Observed strengths
  • No product strength was established in this failed attempt; diagnostic evidence is retained.
Friction
  • A deterministic protocol fixture required product-specific isolation flags and provider configuration; real model behavior, authentication, latency, and cost remain deliberately outside this check.
  • Setup or runtime emitted 20 stderr line(s); the complete warnings/errors are preserved in the retained log.
Limitations
  • The local mock validates Qwen Code's provider wire path, agent loop, tool schema, built-in read execution, and final event output; it does not measure hosted-model quality, authentication, provider reliability, interactive UX, long tasks, or write-tool safety.
  • This credential-free disposable workflow does not establish operator use, production scale, model quality, reliability under sustained use, or team adoption.

Pricing assessment: The CLI and loopback model fixture used no account, subscription, API credit, or paid inference; npm was contacted only to retrieve the pinned package.

Privacy assessment: Only a synthetic marker was read and sent to a server bound to 127.0.0.1; package installation contacted npm, while no prompt or fixture content was sent to a model provider.

Open retained test log →

passed · cohort-20260714-qwen-code-local-read-agent-workflow-v3

Tester
RepoRadar automated local verification harness
Started
2026-07-14T05:09:09.104270Z
Completed
2026-07-14T05:09:18.406791Z
Environment
Windows 10 AMD64; Python 3.11.9; credential-stripped child environment; disposable home/cache
Install/setup time
1 minute(s)
Evidence scope
Bounded representative workflow
Cleanup
Per-check temporary home and work directory removed. Shared cohort package cache removed.
Actions exercised
  • Created a disposable home, work directory, and isolated package cache with credential-like environment variables excluded.
  • Created 4 synthetic fixture file(s) inside the disposable work directory; retained hashes prove the exact inputs.
  • Installed the pinned official @qwen-code/[email protected] package with lifecycle scripts disabled inside the disposable work directory.
  • Bound a deterministic OpenAI-compatible fixture server to an operating-system-assigned 127.0.0.1 port and configured the CLI to deny non-read tools.
  • Prompted the CLI to read one synthetic marker through its built-in read_file tool, then asserted exactly two streamed /v1/chat/completions requests.
  • Verified the second request contained the actual tool output, the final CLI output contained the mock's exact response, and the fixture hash was unchanged.
  • Executed bounded check: Run Qwen Code's official CLI against a loopback-only deterministic model that requests its built-in read tool, then verify the real tool result reaches the second model turn.
  • Captured the complete sanitized stdout, stderr, exit status, artifact checks, and 9.30-second wall time.
Observed results
  • Command exited 0 after 9.30 seconds.
  • Qwen Code exposed and executed its built-in read_file tool once, returned the synthetic marker to the loopback model, completed the second turn, and left the fixture byte-identical.
  • Expected marker 'CHECK_OK cli=qwen requests=2 tool=read_file unchanged=true' was observed in retained output.
  • Validated result.json: 9 required marker(s) present and 0 excluded marker(s) absent; size and SHA-256 are retained.
  • Validated transcript.json: 3 required marker(s) present and 0 excluded marker(s) absent; size and SHA-256 are retained.
Observed strengths
  • The official CLI completed a full provider-to-tool-to-provider agent turn with an allowlisted built-in read tool and machine-readable output, without an account or hosted model.
Friction
  • A deterministic protocol fixture required product-specific isolation flags and provider configuration; real model behavior, authentication, latency, and cost remain deliberately outside this check.
  • Setup or runtime emitted 5 stderr line(s); the complete warnings/errors are preserved in the retained log.
Limitations
  • The local mock validates Qwen Code's provider wire path, agent loop, tool schema, built-in read execution, and final event output; it does not measure hosted-model quality, authentication, provider reliability, interactive UX, long tasks, or write-tool safety.
  • This credential-free disposable workflow does not establish operator use, production scale, model quality, reliability under sustained use, or team adoption.

Pricing assessment: The CLI and loopback model fixture used no account, subscription, API credit, or paid inference; npm was contacted only to retrieve the pinned package.

Privacy assessment: Only a synthetic marker was read and sent to a server bound to 127.0.0.1; package installation contacted npm, while no prompt or fixture content was sent to a model provider.

Open retained test log →

Verification sources

Longitudinal intelligence

How this decision record is moving

Raw history JSON →

81 dated snapshots retained from 2026-06-19 through 2026-09-29; see the snapshot index for explicit coverage gaps. Stars, version, release, pricing, integration, risk, maintenance, verdict, score, and momentum fields remain explicit even when a source has not reported them. Repository momentum is a normalized 0–10 RepoRadar signal; GitHub stars appear only where the popularity monitor retained exact timestamped observations.

RepoRadar score8.9 current · +0.0 net
Repository momentum9.6 current · +0.6 net
GitHub stars (observed)28,207 current · +2,198 net
GitHub stars28,207 exact observation
Versionv0.24.6-nightly.20260926.d6f414190a
Last release2026-09-26T22:20:46Z
MaintenanceActive
Current riskConditional
Current verdictTry now
Pricing baselineNo structured commercial pricing baseline
Pricing checkedNot applicable or not recorded
Pricing freshnessNo dated commercial pricing review
Integrations baselineModel Context Protocol

Recent dated points

DateScoreMomentumStarsRiskVerdictMaintenance
2026-09-298.99.628,207ConditionalTry nowActive
2026-09-288.99.628,192ConditionalTry nowActive
2026-09-278.99.328,143ConditionalTry nowActive
2026-09-268.99.328,137ConditionalTry nowActive
2026-09-258.99.628,130ConditionalTry nowActive
2026-09-248.99.628,112ConditionalTry nowActive
2026-09-238.99.628,094ConditionalTry nowActive
2026-09-228.99.028,069ConditionalTry nowActive
2026-09-218.99.028,047ConditionalTry nowActive
2026-09-208.99.628,014ConditionalTry nowActive
2026-09-198.99.027,989ConditionalTry nowActive
2026-09-178.99.027,930ConditionalTry nowActive

Why the record changed

Stars change

Stars changed: 28192 → 28207.

Stars change

Stars changed: 28143 → 28192.

Version change

Version changed: sdk-typescript-v0.1.16 → v0.24.6-nightly.20260926.d6f414190a.

Stars change

Stars changed: 28137 → 28143.

Stars change

Stars changed: 28130 → 28137.

Version change

Version changed: v0.24.5-nightly.20260924.ffea2d024e → sdk-typescript-v0.1.16.

Stars change

Stars changed: 28112 → 28130.

Version change

Version changed: sdk-typescript-v0.1.15 → v0.24.5-nightly.20260924.ffea2d024e.

Stars change

Stars changed: 28105 → 28112.

Version change

Version changed: v0.24.4-nightly.20260923.d0cd622a68 → sdk-typescript-v0.1.15.

Stars change

Stars changed: 28094 → 28105.

Version change

Version changed: cua-driver-rs-v0.20.11 → v0.24.4-nightly.20260923.d0cd622a68.