ltm
v0.5.0Retrieve past Claude Code conversations from this machine's own transcript corpus, with pointers back to the original turns.
By che cheng0 GitHub starsUpdated 1 hour ago
Directory evidence
- Runtimes
- Claude Code
- Parsed components
- 3 skill or MCP entries
- Source updated
- Oct 2, 2026
- Manifest status
- Canonical path parsed
The directory validates manifest shape and source location. It does not execute the plugin or provide a security endorsement. Review the indexing methodology →
Install ltm for Claude Code
claude plugin marketplace add IchenDEV/agent-plugin-mkt
claude plugin marketplace update agent-plugin-marketplace
claude plugin install ltm@agent-plugin-marketplacePaste and run these commands in a terminal with Claude Code. They add and refresh the PluginsMP catalog, then install this plugin.
The installer fetches third-party code from the source repository shown on this page. This directory validates manifest structure and source location, but does not perform a security audit; review the manifest, components, and source before installing.
Get the source manually
git clone https://github.com/PsychQuant/claude-code-ltmClone the source repository, then follow its setup instructions to add the plugin to a compatible client. The plugin root is plugin/.
Plugin files
├── .claude-plugin/plugin.json├── skills/ltm-recall/SKILL.md├── skills/ltm-setup/SKILL.md└── .mcp.json
Included Skills2
Use when the user refers to something from a past Claude Code conversation on this machine — "我們之前討論過…", "那次量測的數字是多少", "為什麼當初決定…", "上次那個 bug 怎麼修的" — or whenever answering would require knowing what was decided in an earlier session. Searches the local transcript corpus and returns pointers to the original turns.
Use when claude-code-ltm is not yet usable — the user just installed the plugin, a `ltm_query` call came back with `索引不存在` / `indexMissing`, the user asks "how do I set this up", "為什麼查不到", "ltm 要怎麼開始用", "要先做什麼嗎", or wants to rebuild the index after an upgrade. Checks binary and index state, explains the one-time cost, and runs `ltm build` with the user's consent.
MCP servers1
- command
- ${CLAUDE_PLUGIN_ROOT}/bin/ltm-mcp-wrapper.sh
Plugin manifests1
{
"name": "ltm",
"version": "0.5.0",
"description": "Retrieve past Claude Code conversations from this machine's own transcript corpus, with pointers back to the original turns.",
"author": {
"name": "che cheng"
},
"mcpServers": {
"ltm": {
"command": "${CLAUDE_PLUGIN_ROOT}/bin/ltm-mcp-wrapper.sh",
"args": []
}
}
}For maintainers
If you maintain this plugin, link to this source-backed listing from your README so users can review its manifest and indexed components.
[ltm on Agent Plugins Marketplace](https://pluginsmp.com/plugins/ltm)