sqlite-memory-mcp
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@sqlite-memory-mcp search my memories for TypeScript patterns"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
sqlite-memory-mcp
統一的 SQLite Memory MCP Server,為 Claude Code 生態系提供智能記憶管理
特色
跨專案記憶共享 — 學一次,處處可用
FTS5 全文搜尋 — 毫秒級搜尋,精確匹配
Skill 效果追蹤 — 知道什麼最有效
失敗經驗索引 — 不重複犯錯
Context 狀態共享 — 跨 Skill 無縫傳遞
零外部依賴 — 純 SQLite,無需 PyTorch/ONNX
Related MCP server: Memory MCP
效能
指標 | 傳統方案 | sqlite-memory-mcp |
Token/搜尋 | ~2300 | ~200 (-91%) |
搜尋速度 | ~20ms | ~3.5ms (5.7x) |
外部依賴 | PyTorch/ONNX | 無 |
並發支援 | JSONL 無 | SQLite WAL |
安裝
從 npm 安裝(推薦)
npm install -g sqlite-memory-mcp從源碼安裝
git clone https://github.com/miles990/claude-memory-mcp.git
cd claude-memory-mcp
npm install
npm run build配置 Claude Code
在 ~/.claude/.mcp.json 加入:
{
"mcpServers": {
"memory": {
"command": "npx",
"args": ["sqlite-memory-mcp"]
}
}
}或如果從源碼安裝:
{
"mcpServers": {
"memory": {
"command": "node",
"args": ["/path/to/claude-memory-mcp/dist/index.js"]
}
}
}工具列表 (23 tools)
Memory 工具 (6)
工具 | 說明 |
| 寫入記憶到知識庫 |
| 讀取特定記憶 |
| FTS5 全文搜尋 |
| 列出記憶(可過濾) |
| 刪除記憶 |
| 統計資訊 |
Skill 工具 (7)
工具 | 說明 |
| 註冊 skill 安裝 |
| 取得 skill 資訊 |
| 列出所有 skill |
| 開始使用追蹤 |
| 結束使用追蹤 |
| 智能推薦(基於成功率) |
| 使用統計 |
Context 工具 (5)
工具 | 說明 |
| 設定 context 值 |
| 取得 context 值 |
| 列出 session context |
| 清除 context |
| 跨 session 共享 |
Failure 工具 (5)
工具 | 說明 |
| 記錄失敗經驗 |
| FTS5 搜尋解法 |
| 列出失敗記錄 |
| 更新解法 |
| 失敗統計 |
資料庫
位置:~/.claude/claude.db
自動建立 schema,包含:
memory表 +memory_ftsFTS5skills表skill_usage表failures表 +failures_ftsFTS5context表
使用範例
記憶搜尋
memory_search query="TypeScript pattern"
memory_list scope="global"Skill 追蹤
skill_usage_start skill_name="evolve"
skill_usage_end usage_id=1 success=true outcome="completed"
skill_recommend project_type="typescript"失敗經驗
failure_record error_pattern="TypeError: undefined" solution="Check null values"
failure_search query="TypeError undefined"與競品比較
功能 | server-memory | doobidoo | sqlite-memory-mcp |
存儲 | JSONL | SQLite-vec | SQLite WAL |
搜尋 | 關鍵字 | 向量 | FTS5 全文 |
Skill 追蹤 | - | - | 有 |
失敗索引 | - | - | 有 |
Context 共享 | - | - | 有 |
外部依賴 | 無 | PyTorch | 無 |
與 evolve skill 整合
此 MCP Server 設計為與 self-evolving-agent 整合:
CP1: 使用
memory_search+failure_search搜尋經驗CP3.5: 使用
memory_write記錄學習CP5: 使用
failure_record記錄失敗Skill 追蹤: 自動追蹤使用成功率
License
MIT
Available Tools
23 toolscontext_clearC
Clear context values
Inputs: session_id.
context_getC
Get a context value
Inputs: key (required), session_id (required).
context_listA
List all context values for a session
Inputs: session_id (required).
context_setB
Set a context value for cross-skill state sharing
Inputs: key (required), value (required), session_id (required), skill_name, +1 more.
failure_listC
List failure experiences
Inputs: limit, skill_name.
failure_recordC
Record a failure experience for future reference
Inputs: error_pattern (required), solution, skill_name, project_path, +1 more.
failure_searchB
Search for failure experiences and solutions using FTS5
Inputs: query (required), limit.
failure_statsC
Get failure statistics
Inputs: no named parameters.
failure_updateB
Update a failure record with a solution
Inputs: id (required), solution (required).
memory_deleteB
Delete a memory entry
Inputs: key (required).
memory_listC
List memory entries with optional filters
Inputs: limit, scope, prefix.
memory_readA
Read a specific memory entry by key
Inputs: key (required).
memory_searchB
Search memories using full-text search (FTS5)
Inputs: query (required), limit, scope.
memory_statsC
Get memory statistics
Inputs: no named parameters.
memory_writeC
Write a memory entry to the knowledge base
Inputs: key (required), content (required), tags, scope, +1 more.
skill_getC
Get skill information
Inputs: name (required).
skill_listA
List all registered skills
Inputs: project_path.
skill_recommendC
Get skill recommendations based on project type and success rates
Inputs: limit, project_type.
skill_registerC
Register a skill installation
Inputs: name (required), source (required), version (required), installed_by, +1 more.
skill_statsB
Get skill usage statistics
Inputs: no named parameters.
skill_usage_endC
End skill usage tracking
Inputs: success (required), usage_id (required), notes, outcome, +1 more.
skill_usage_startC
Start tracking skill usage
Inputs: skill_name (required), project_path.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 23 tools
Tools are grouped into clear domains: context, memory, skill, and failure, which makes their purposes generally obvious. A few retrieval tools like memory_read, memory_list, and memory_search have overlapping connotations, but their descriptions specify distinct lookup modes.
All tool names follow a consistent lowercase snake_case verb_noun pattern, such as memory_write, context_set, skill_register, and failure_record. Each domain uses predictable verbs, so the naming convention is uniform and scannable.
23 tools is on the higher end and feels slightly heavy, but the server covers four distinct subdomains that each need CRUD, search, and stats operations. The count is reasonable given the combined scope, though it could be tightened.
Each core domain has solid coverage: create, read, list, search, and delete/update where expected. Minor gaps exist, such as no memory update, no single-key context delete, and no skill unregister, but agents can generally work around these.
Maintenance
Related MCP Connectors
Persistent cross-session memory shared by Codex, Claude Code, ChatGPT, and other AI agents.
Shared work memory for Claude Code, Codex, Cursor and chat, scoped to each repository.
Persistent memory for AI agents across Claude, ChatGPT and any MCP client.
Shared memory for coding agents. Stop re-explaining your codebase every session.
Related MCP Servers
- AlicenseAqualityDmaintenanceCross-surface persistent memory for Claude. Bridges context between Claude Chat, Code, and Cowork via local SQLite with full-text search.610 npm7MIT
- AlicenseAqualityDmaintenanceProvides persistent cross-session memory and full-text search for AI coding assistants, storing project context, decisions, and preferences while enabling searchable access to conversation history via local SQLite.81MIT
- -licenseNot gradedqualityDmaintenanceProvides persistent memory for AI assistants like Claude, storing and retrieving information across conversations using a local SQLite database.-
- AlicenseNot gradedqualityBmaintenanceEnables Claude Code to query and store memories from past conversations using FTS5 search and topic-based retrieval, with no API costs.54 npm1Apache 2.0