Milvus 刚开源了 MFS，能把各种数据源像文件一样搜索浏览。Agent 调用的神器，快试试！
MFS（Multi-source File-like Search）可将代码仓库、Slack 线程、设计文档、Jira 问题、CRM 笔记、数据库行等来源转化为统一文件系统命名空间，提供稳定 URI。它通过连接器将数据送入 mfs-server，利用队列、缓存、元数据和索引实现可搜索和浏览。Agent 可通过 CLI、Python/TypeScript SDK 使用，或调用 mfs-ingest 和 mfs-find 两个技能分别管理源注册和跨源搜索。架构采用“先语义定位，再逐步验证”的策略，将内存、技能、文档、消息等整合到单一上下文层。该项目已在 GitHub 上以 Apache 2.0 协议开源。
𝗪𝗲 𝗼𝗽𝗲𝗻-𝘀𝗼𝘂𝗿𝗰𝗲𝗱 𝗠𝗙𝗦 (𝗠𝘂𝗹𝘁𝗶-𝘀𝗼𝘂𝗿𝗰𝗲 𝗙𝗶𝗹𝗲-𝗹𝗶𝗸𝗲 𝗦𝗲𝗮𝗿𝗰𝗵), a tool...
𝗪𝗲 𝗼𝗽𝗲𝗻-𝘀𝗼𝘂𝗿𝗰𝗲𝗱 𝗠𝗙𝗦 (𝗠𝘂𝗹𝘁𝗶-𝘀𝗼𝘂𝗿𝗰𝗲 𝗙𝗶𝗹𝗲-𝗹𝗶𝗸𝗲 𝗦𝗲𝗮𝗿𝗰𝗵), a tool that can turn a repo, a Slack thread, a design doc, a Jira issue, a CRM note, or a database row those sources into one file-like namespace with stable URIs. Connectors feed data into mfs-server, where queue, cache, metadata, and index keep the sources searchable and browsable. Agents can use it through the CLI, Python/TypeScript SDKs, or two skills: • mfs-ingest registers sources, syncs updates, builds indexes, and helps inspect connectors. • mfs-find searches across what has been ingested, then browses into the original source with commands like tree, ls, cat, head, and tail. The architecture is straightforward: locate semantically, then verify progressively. For agents, that means memory, skills, docs, messages, issues, PRs, emails, customer records, and tables can live in one context layer instead of github.com/zilliztech/mfs ate tools. Repo: https://t.co/RJI5lMigrE 💬 0 🔄 0 ❤️ 0 👀 81 ⚡