~ / agents / qoder

Qoder

Alibaba's first-party agentic IDE, distinct from the open-source Qwen Code CLI: a full editor built around Repo Wiki codebase mapping and autonomous Quest tasks.

VendorAlibaba
FormAgentic IDE + CLI (+ QoderWork CN desktop)
LaunchedAugust 2025 (preview); Qoder CN renamed 2026-05-20
ARscorenot scored
Pricing tierPro $20 / Pro+ $60 / Ultra $200 / Teams $30 per seat
Coding modelsClaude / GPT / Gemini / Qwen (intl); GLM / DeepSeek / Kimi / MiniMax / Qwen (CN selector)
Open sourceNo

Official links

Outbound, for trial and verification.

Official sitehttps://qoder.com/
Pricinghttps://qoder.com/
English interface / changeloghttps://qoder.com/changelog

Capabilities

What it ships, in its own terms.

Repo Wiki builds a navigable map of a codebase's architecture before prompting; Quest mode takes a written spec and delivers a tested multi-file change unattended; an Experts team and Computer Use ship in 2026 releases. The CN client (renamed from Tongyi Lingma) adds a model selector across GLM, DeepSeek, Kimi, MiniMax and Qwen; office scenarios (docs, analysis) come via the separate QoderWork CN desktop app.

Use cases

Scenario coverage (presence, not benchmark performance).

ScenarioLocal filesDocs / PPTExcel reportsAnalysisWeb searchMini-programsWeb building
Qoder

✓ supported · ◐ partial or via a sibling product · ? unclear · — not in scope. Presence, not benchmark performance.

Users

Subscriber and active-user counts, source-labelled.

not published (separate product from Qwen Code)Source: —

Third-party review

Independent coverage, not vendor marketing.

Third-party editorial: ★★★★☆ RECATOOLS 7.3/10

Coding ability (benchmark): not scored — no DeepSWE or Terminal-Bench measurement.

RECATOOLS scored it 7.3/10, citing Repo Wiki as the standout; reviewers noted indexing is slow (about 5% after 2 hours on a medium repo) and Chat mode over-edits. No DeepSWE or Terminal-Bench score.

Source: RECATOOLS (Jul 2026)

Compare further

The reference agents and the scored Chinese entry.

China big-tech hub

all entries vs Codex and Claude Code

comparison

Claude Code

the architecture leader

score 86

ChatGPT Codex

the reference OpenAI terminal agent

score 84

Qwen CodeOS

the scored open-source Alibaba CLI

score 45