---
title: "Our team uses multiple coding agents in daily development.                                          ..."
source_name: "Milvus(@milvusio)"
original_url: "https://x.com/milvusio/status/2049143097762762921"
canonical_url: "https://www.traeai.com/articles/04057dab-e09e-47fe-85c6-08ce116c87aa"
content_type: "tweet"
language: "英文"
score: 7.5
tags: ["AI辅助编程","Claude Code","Codex"]
published_at: "2026-04-28T15:06:00+00:00"
created_at: "2026-04-30T05:47:15.462552+00:00"
---

# Our team uses multiple coding agents in daily development.                                          ...

Canonical URL: https://www.traeai.com/articles/04057dab-e09e-47fe-85c6-08ce116c87aa
Original source: https://x.com/milvusio/status/2049143097762762921

## Summary

Milvus团队在日常开发中使用多个编码代理，Claude Code和Codex分别适用于快速交互和慢速细致的工作流。为解决上下文切换问题，他们开发了开源记忆层Memsarch。

## Key Takeaways

- Claude Code适合快速、互动的代码探索与修改。
- Codex更适合缓慢、细致的本地工作流程。
- Memsarch作为记忆层，帮助不同代理间共享历史上下文。

## Content

Title: Milvus on X: "Our team uses multiple coding agents in daily development.                                                                          

𝗖𝗹𝗮𝘂𝗱𝗲 𝗖𝗼𝗱𝗲 is useful when we want fast, interactive work inside a repo. It helps us explore code, make changes quickly, and iterate in https://t.co/iB9lkcqBl9" / X

URL Source: http://x.com/milvusio/status/2049143097762762921

Published Time: Thu, 30 Apr 2026 05:45:16 GMT

Markdown Content:
## Post

## Conversation

Our team uses multiple coding agents in daily development. 𝗖𝗹𝗮𝘂𝗱𝗲 𝗖𝗼𝗱𝗲 is useful when we want fast, interactive work inside a repo. It helps us explore code, make changes quickly, and iterate in real time. 𝗖𝗼𝗱𝗲𝘅 is useful when we want a slower, more deliberate local workflow. It can take longer and often produces cleaner output. Using both has helped us move faster. But it also showed us a problem. We were spending too much time moving context between agents. Project history. Past decisions. User preferences. Things that failed last time. Reasons behind a certain implementation. Each agent could help with the task at hand. But the memory remained within a single workflow. That is the part we wanted to fix. 𝗠𝗲𝗺𝘀𝗲𝗮𝗿𝗰𝗵 𝗶𝘀 𝗮𝗻 𝗼𝗽𝗲𝗻-𝘀𝗼𝘂𝗿𝗰𝗲 𝗺𝗲𝗺𝗼𝗿𝘆 𝗹𝗮𝘆𝗲𝗿 𝗳𝗼𝗿 𝗰𝗼𝗱𝗶𝗻𝗴 𝗮𝗴𝗲𝗻𝘁𝘀, 𝗽𝗼𝘄𝗲𝗿𝗲𝗱 𝗯𝘆 𝗠𝗶𝗹𝘃𝘂𝘀. It stores past context in a vector database. Agents can search for that memory when they need it. So when a team moves from Claude Code to Codex, or uses both in the same project, the useful context can stay available. The agent can change. The memory can stay. GitHub: [github.com/zilliztech/mem](https://t.co/rbSO5eVWhp)

[![Image 1: Image](https://pbs.twimg.com/media/HG_AQf3a0AAWSEO?format=jpg&name=small)](https://x.com/milvusio/status/2049143097762762921/photo/1)