~ / agents / codebuddy

CodeBuddy

Tencent Cloud's coding arm under the Buddy AI umbrella, the first Chinese assistant to ship MCP, with Craft and Plan agent modes across IDE, plugin and CLI.

VendorTencent
FormIDE + plugin + CLI (the coding arm of Buddy AI)
LaunchedMay 2025
ARscorenot scored
Pricing tierFree (500 credits) / ¥99 / ¥199 / ¥999; ent ¥198/seat
Coding modelsHunyuan + DeepSeek (dual); GLM / Kimi / MiniMax selectable
Open sourceNo

Official links

Outbound, for trial and verification.

Official sitehttps://copilot.tencent.com/
Pricinghttps://cloud.tencent.com/document/product/1749
English interface / changeloghttps://copilot.tencent.com/home/

Capabilities

What it ships, in its own terms.

Craft mode generates multi-file changes; Plan mode plans first; MCP connects external tools; CodeBuddy Code 2.0 (Jan 2026) added sub-agents and hooks. Runs on Hunyuan plus DeepSeek and covers 200+ languages across 15+ IDEs. Shares credits with the workplace sibling WorkBuddy.

Use cases

Scenario coverage (presence, not benchmark performance).

ScenarioLocal filesDocs / PPTExcel reportsAnalysisWeb searchMini-programsWeb building
CodeBuddy

✓ 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 (shares accounts with WorkBuddy)Source: —

Third-party review

Independent coverage, not vendor marketing.

Third-party editorial: ★★★★☆ RECATOOLS 7/10

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

RECATOOLS scored it 7/10. A 2026 incident inserted ad strings into generated code; Tencent attributed it to a DeepSeek-side bug. No DeepSWE or Terminal-Bench score.

Source: RECATOOLS / Press (36Kr)

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