MemSearch is a cross-platform semantic memory layer for AI coding agents that stores human-readable Markdown memories and indexes them with Milvus for searchable retrieval. It is used by agent users who want persistent context and by developers building memory features into agents across tools such as Claude Code, Codex, DeepSeek Harness, OpenClaw, and OpenCode. Catalogue add-ons provide the hooks, skills, and plugin workflows that capture, retrieve, and maintain this memory.
Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add zilliztech/memsearch/plugin install memsearchWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/hooks/zilliztech/memsearch/user-prompt-submit)<a href="https://agentmods.dev/hooks/zilliztech/memsearch/user-prompt-submit"><img src="https://agentmods.dev/badge/hooks/zilliztech/memsearch/user-prompt-submit.svg" alt="Measured on agentmods" height="20"></a>Grade A, and why
UserPromptSubmit scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 5d ago.
A static scan of the commands this hook runs, not an audit. A hook is shell that executes on your machine at the event it names, which is why every command in it is printed with what was found.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
This is a copy
69% identical to SessionStart — 8 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
What it actually says
{
"UserPromptSubmit": [
{
"hooks": [
{
"type": "command",
"command": "bash ${CLAUDE_PLUGIN_ROOT}/hooks/user-prompt-submit.sh",
"timeout": 15
}
]
}
]
}What else hooks.json configures
This page is one entry in a file that holds 4. Installing the file brings all of them; each is measured and scanned on its own page.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 5d ago First seen · 13 lines scan A 7efd313221f9
UserPromptSubmit is a hook published in the GitHub repository zilliztech/memsearch (2,559 stars, last pushed 2d ago), licensed MIT. Its token cost is not measured: a hook is shell that never enters the context. A static security scan graded it A with 0 findings. It is 69% identical to SessionStart, differing in 8 lines, and is treated as a copy.
Other hooks, from other repositories
SessionStart
Runs when a session starts, executing session-start.sh via bash. From yucai0302/memory-loop.
Stop
Runs when the agent finishes a response, executing check-compress.sh via bash. From yucai0302/memory-loop.
PreCompact
Runs before the context is compacted, executing memforge_hook.py via sh with --client. From shno-labs/mem-forge.
PreToolUse
Runs before the agent uses a tool for Bash tool calls, executing on_pre_tool.js via node. From baodq97/tencentdb-agent-memory.
PostToolUse
Runs after a tool call finishes for Write and Edit tool calls, executing format_and_lint.sh. From supabase/supabase.
SessionStart
Runs when a session starts, executing on-start.js via node. From google-gemini/gemini-cli.