接入你的智能体
發布者自己的指令。不是 PlugMCP 端點。
用我們的金鑰與日誌託管一份副本。
npx -y [email protected]Claude Code 沒有本機指令的安裝連結。複製下方指令並在終端機中執行。
OPENAI_API_KEY=<secret> claude mcp add io.github.hustada-collective-memory -- npx -y collective-memory@0.1.2在終端機中執行。
{ "mcpServers": { "io.github.hustada-collective-memory": { "command": "npx", "args": [ "-y", "[email protected]" ], "env": { "OPENAI_API_KEY": "<secret>" } } }}claude_desktop_config.json
遠端 URL 還是本機指令？ 兩種安裝方式的差異
來自發布者
MCP server for persistent, semantic memory across AI sessions. Store context, decisions, and learnings — recall them later with natural language search.
AI assistants forget everything between sessions. Collective Memory fixes that. Store what matters, search by meaning, build context that compounds.
MCP server for persistent, semantic memory across AI sessions
decision, milestone, context, learning, or session_summarynpm install -g collective-memory
Or clone and build:
git clone https://github.com/Hustada/collective-memory.git
cd collective-memory
npm install
npm run build
Required for embeddings. Get one at platform.openai.com.
Add to ~/.claude/settings.json under mcpServers:
{
"mcpServers": {
"collective-memory": {
"type": "stdio",
"command": "npx",
"args": ["collective-memory"],
"env": {
"OPENAI_API_KEY": "sk-..."
}
}
}
}
Or if installed from source:
{
"mcpServers": {
"collective-memory": {
"type": "stdio",
"command": "node",
"args": ["/path/to/collective-memory/dist/index.js"],
"env": {
"OPENAI_API_KEY": "sk-..."
}
}
}
}
Add to your global ~/.claude/CLAUDE.md:
## Memory
Collective Memory is active. Two tools:
- `remember(content, project?, type?, tags?)` — Persist important context
- `recall(query, project?, type?, limit?)` — Search memory
**On session start**: Run `recall("recent decisions and context")` to load relevant memory.
When to remember: after decisions, milestones, completed work, learned patterns.
When to recall: session start, context switches, referencing past work.
Types: decision, milestone, context, learning, session_summary.
Store a memory with semantic embedding.
Returns the stored memory ID, or existing ID if deduplicated.
Search memories by semantic similarity.
Returns array of matching memories with similarity scores.
Also usable from command line:
# Store a memory
collective-memory remember --content "Decided to use PostgreSQL for the auth service"
# Search memories
collective-memory recall --query "database decisions" --limit 5
# Pipe content from stdin
echo "Long content here" | collective-memory remember --content-stdin --project myapp
text-embedding-3-small (768 dimensions)Memories are stored locally at ~/.collective-memory/data (or COLLECTIVE_MEMORY_PATH). It's a LanceDB database — portable, no server process.
To export memories:
npm run export # Outputs to viz/memories.json
To visualize:
npm run dash # Opens UMAP visualization at localhost:3333
MIT
Built by The Victor Collective.
MCP server for persistent, semantic memory across AI sessions
{ "mcpServers": { "io.github.hustada-collective-memory": { "command": "npx", "args": [ "-y", "[email protected]" ], "env": { "OPENAI_API_KEY": "<secret>" } } }}工具
尚無工具清單。遠端伺服器會在首次健康檢查後取得工具清單。
常見問題
在本頁複製適用於 Cursor、Claude Desktop、Claude Code 或 VS Code 的 stdio 設定。它使用發布者的安裝方式，而不是 PlugMCP 代理伺服器。
發布者列出了以下環境變數：OPENAI_API_KEY。
Collective Memory 透過 stdio 在本機執行。
上次檢查時間：2026-11-09。 MCP server for persistent, semantic memory across AI sessions