Tencent open-sources LoopForge for team-oriented AI development
Tencent's Lightweight Cloud team open-sourced LoopForge, a cloud-based AI development platform built around persistent workspaces, shared multi-role agent sessions, gated SOP pipelines, unattended issue automation, and engineering-level recursive self-improvement. InfoQ reported that the platform supports tools including Claude Code, Codex, and CodeBuddy, while also drawing on DeepSeek's Super-agent research. The team says LoopForge is used internally across more than 20 businesses and automatically completes over 200 requirements and routine work items per month.
LoopForge packages several team-level coding-agent patterns into an open-source platform, including cloud execution, shared context, automated validation, and workflow-level self-improvement.

导 读单机 Coding Agent 已经能飞快写出代码,但一旦走进真实研发团队,合盖断流、多人上下文割裂、自由 Vibe Coding 质量失控、日常盯单耗时以及同类问题反复踩坑,很快就会把团队卡在“单兵提效、全局内耗”的瓶颈里。为此,腾讯轻量云团队打造并开源了云端自进化 AI 研发平台 LoopForge——集 7×24 小时云端工作区、多角色共享会话、工程级 SOP 流水线、无人值守自动化与工程级 RSI 自进化于一体。目前平台已在内部 20+ 业务落地使用,单月自动完成 200+ 需求与日常单据交付。本文结合 DeepSeek 的 Super-agent 探索,完整复盘这套体系背后的五步工程演进。

#Tencent#LoopForge#Tencent Lightweight Cloud#DeepSeek#Claude Code#Codex#CodeBuddy