2 phút đọc
zilliztech/memsearch: A persistent, unified memory layer for all your AI agents (e.g. Claude Code, Codex), backe – Repository zilliztech/memsearch. Mô tả: A persistent, unified memory layer for all your AI agents (e.g. Claude Code, Codex), backed by Markdown and Milvus.. 2494 stars, 232 forks, ngôn ngữ chính Python, cập nhật 2026-08-23.
1. Repository làm gì?
Cross-platform semantic memory for AI coding agents.
Pick your platform, install the plugin, and you're done. Each plugin captures conversations automatically and provides semantic recall with zero configuration.
After restarting, just chat with Claude Code as usual. The plugin captures every conversation turn automatically.
Verify it's working — after a few conversations, check your memory files:
Recall memories — two ways to trigger:
Or just ask naturally — Claude auto-invokes the skill when it senses the question needs history:
2. Dữ liệu và cấu trúc đáng chú ý
📖 Claude Code Plugin docs · Troubleshooting
After installing, chat as usual. Hooks capture and summarize each turn.
Recall memories — use the skill:
After installing, use DSH normally. Completed turns are captured automatically, and relevant memories are injected before the first model step only when they are useful.
Recall memories — ask naturally or tell DSH to use the registered memory-recall skill:
The web profile also adds a compact MemSearch dock where you can review skill candidates and browse supported files under .memsearch/ without editing them.
After installing, chat in TUI as usual. The plugin captures each turn automatically.
3. Khả năng ứng dụng và giới hạn
Verify it's working — memory files are stored in your agent's workspace:
Or just ask naturally — the LLM auto-invokes memory tools when it senses the question needs history:
📖 OpenClaw Plugin docs · Browse on ClawHub
After installing, chat in TUI as usual. A background daemon captures conversations.
⚙️ Configuration (all platforms)
All plugins share the same memsearch backend. Configure once, works everywhere.
Defaults to ONNX bge-m3 — runs locally on CPU, no API key, no cost. On first launch the model (~558 MB) is downloaded from HuggingFace Hub.
All providers and models: Configuration — Embedding Provider
Just change milvus_uri (and optionally milvus_token) to switch between deployment modes:
Số liệu repository có thể thay đổi; nên mở liên kết nguồn để kiểm tra README, giấy phép và trạng thái phát hành.
Nguồn tham khảo: Xem bài gốc
