Conversation memory and workspace management MCP server for Amazon Q CLI with ChromaDB real-time sync
Project description
AWS Q Memory MCP Server (q_mem_mcp_server)
A Model Context Protocol (MCP) server that provides conversation memory and workspace management for Amazon Q CLI.
๐ฏ Key Features
- Automatic Conversation Saving: Real-time sync of Q CLI conversations to ChromaDB
- Workspace Management: Organize conversations by topics/workspaces with natural language support
- Context Restoration: Resume previous conversations with full context memory
- Semantic Search: Search through conversation history using natural language
๐ Quick Start
1. MCP Configuration
Add to ~/.aws/amazonq/mcp.json:
{
"mcpServers": {
"q-mem": {
"command": "uvx",
"args": ["q_mem_mcp_server@latest"],
"env": {
"Q_CLI_DB_PATH": "~/Library/Application Support/amazon-q/data.sqlite3",
"Q_MEM_VERBOSE": "true"
},
"disabled": false,
"autoApprove": [
"start_workspace",
"resume_workspace",
"search_memory_by_workspace",
"get_storage_stats",
"list_workspaces"
]
}
}
}
2. Usage Examples
# Start Q CLI
q chat
# Start a new workspace
start_workspace(description="backendDev")
# OR natural language: "๋ฐฑ์๋๊ฐ๋ฐ ์ํฌ์คํ์ด์ค๋ก ์์ํด์ค"
# Chat normally (automatically saved)
# ... have conversations ...
# List workspaces
list_workspaces()
# OR natural language: "์ํฌ์คํ์ด์ค ๋ชฉ๋ก ๋ณด์ฌ์ค"
# Resume workspace (loads full context)
resume_workspace(workspace_id="backendDev")
# OR natural language: "๋ฐฑ์๋๊ฐ๋ฐ ์ํฌ์คํ์ด์ค๋ก ์ฌ๊ฐํด์ค"
๐ ๏ธ Available Commands
| Command | Description |
|---|---|
start_workspace(description) |
Start a new workspace |
list_workspaces() |
List all workspaces |
resume_workspace(workspace_id) |
Resume workspace with full context |
search_memory_by_workspace(workspace_id, query) |
Search previous conversations |
delete_workspace(workspace_id, confirm=true) |
Delete a workspace |
get_storage_stats() |
Check storage status |
Natural Language Support: You can also use natural language like "๋ฐฑ์๋๊ฐ๋ฐ ์ํฌ์คํ์ด์ค๋ก ์์ํด์ค" or "resume backend development workspace"
๐ง Technology Stack
- ChromaDB: Vector database for conversation storage and search
- SQLite WAL: Real-time sync with Q CLI database
- Sentence Transformers: Semantic search embeddings
- MCP Protocol: Communication with Amazon Q
๐ Data Storage
- ChromaDB:
~/.Q_mem/chroma_db/ - Sync State:
~/.Q_mem/sync_state.json - Logs:
~/.Q_mem/q_mem.log
๐ Auto-Sync Features
Q CLI conversations are automatically saved to ChromaDB in real-time:
- Real-time Detection: Checks for new conversations every 2 seconds
- Partial Failure Handling: Saves successful conversations even if some fail
- Auto Recovery: Automatically recovers from consecutive failures
- State Restoration: Restores sync state after restart
๐ Revolutionary Multi-Persona Workflow Example
Experience the power of seamless context switching between different expert personas:
# === Day 1: Backend Development Context ===
q chat
> start_session(description="backendDev")
# OR natural language: "Start backend development context"
โ
Context 'backendDev' started
> "You are now a backend developer persona. Help me design a microservices architecture"
๐ฏ Backend Developer: I'll help you design a robust microservices architecture...
> "Store my PyPI API key: pypi-AgEI..."
โ
PyPI API key stored for future deployments
> "Design a user authentication service with JWT"
๐ฏ Backend Developer: Here's a comprehensive JWT authentication service design...
# ... detailed backend discussion continues ...
# === Day 2: Database Design Context ===
q chat
> start_session(description="dba")
# OR natural language: "Start database administrator context"
โ
Context 'dba' started
> "You are now a database administrator persona. Help me optimize the user service database"
๐ฏ Database Administrator: I'll help you optimize your database design...
> "What's the best indexing strategy for user lookups?"
๐ฏ Database Administrator: For optimal user lookup performance, consider these indexing strategies...
# ... detailed database discussion continues ...
# === Day 3: Seamless Context Switching ===
q chat
> list_sessions()
# OR natural language: "Show me all contexts"
๐ Your contexts:
1. backendDev (15 conversations) - Backend development and API design
2. dba (8 conversations) - Database optimization and indexing
> resume_session(context_id="backendDev")
# OR natural language: "Resume backend development context"
๐ Context 'backendDev' resumed with full context
๐ฏ Backend Developer: Welcome back! We were discussing JWT authentication service...
> "Remember my PyPI key? I need to deploy the auth service we designed"
๐ฏ Backend Developer: Yes! Using your stored PyPI key: pypi-AgEI...
โ
Deploying q_auth_service v1.0.0 to PyPI...
> "Now switch to DBA context to check if our database design supports this deployment"
> resume_session(context_id="dba")
# OR natural language: "Switch to database administrator context"
๐ Context 'dba' resumed with full context
๐ฏ Database Administrator: Checking the indexing strategy we discussed for the auth service...
> "The backend team deployed the JWT service. Does our index design handle the expected load?"
๐ฏ Database Administrator: Based on our previous optimization discussion, the composite index on (user_id, created_at) will handle the JWT validation queries efficiently...
# === Day 4: Cross-Context Knowledge Integration ===
> search_memory_by_context(context_id="backendDev", query="JWT token expiration")
# OR natural language: "Search for JWT token expiration in backend context"
๐ Found in backendDev context:
- "JWT tokens should expire in 15 minutes for security"
- "Refresh tokens valid for 7 days"
- "Store refresh tokens in Redis for fast lookup"
> resume_session(context_id="dba")
# OR natural language: "Switch back to database context"
๐ฏ Database Administrator: I remember we need to optimize for JWT refresh token storage...
> "Based on the backend context, we need Redis optimization for 7-day refresh tokens"
๐ฏ Database Administrator: Perfect! Let me design a Redis clustering strategy for high-availability refresh token storage...
๐ Why This Is Revolutionary
- Persistent Expertise: Each session maintains specialized knowledge and context
- Seamless Switching: Jump between expert personas without losing conversation flow
- Cross-Session Intelligence: Search and reference knowledge across different expert contexts
- Secure Credential Storage: API keys and sensitive data persist across sessions
- Natural Workflow: Mirrors real-world collaboration between different specialists
๐ฏ Real-World Applications
- DevOps Teams: Switch between developer, DBA, and infrastructure personas
- Full-Stack Projects: Frontend, backend, and database expert contexts
- Learning Paths: Separate contexts for different technologies or concepts
- Client Projects: Dedicated contexts per client with persistent context
- Code Reviews: Different perspectives from various expert personas
๐ก Usage Tips
- Context Organization: Separate conversations by topics, roles, or projects
- Semantic Search: Use natural language rather than exact keywords
- Context Utilization: Use
resume_sessionfor complete conversation restoration - Regular Cleanup: Delete unnecessary contexts to maintain performance
- Cross-Context References: Use
search_memory_by_contextto find relevant information across personas - Natural Language: Use natural language commands like "๋ฐฑ์๋๊ฐ๋ฐ ์ปจํ ์คํธ๋ก ์์ํด์ค"
Memory Management
# Clean up old contexts
cleanup_old_contexts(days=30, confirm=true)
# or natural language: "remove old contexts"
# Delete specific context
delete_context(context_id="context_name", confirm=true)
# or natural language: "delete context context_name"
๐ License
MIT License
๐ Links
- PyPI: https://pypi.org/project/q_mem_mcp_server/
- GitHub: https://github.com/jikang-jeong/aws-q-mem-mcp-server
- Issues: https://github.com/jikang-jeong/aws-q-mem-mcp-server/issues
AWS Q Memory MCP Server (q_mem_mcp_server) - KOR
Amazon Q CLI๋ฅผ ์ํ ๋ํ ๋ฉ๋ชจ๋ฆฌ ๋ฐ ์ธ์ ๊ด๋ฆฌ ๊ธฐ๋ฅ์ ์ ๊ณตํ๋ Model Context Protocol (MCP) ์๋ฒ์ ๋๋ค.
๐ฏ ์ฃผ์ ๊ธฐ๋ฅ
- ์๋ ๋ํ ์ ์ฅ: Q CLI ๋ํ๋ฅผ ChromaDB์ ์ค์๊ฐ ๋๊ธฐํ
- ์ธ์ ๊ด๋ฆฌ: ์ฃผ์ /์ธ์ ๋ณ๋ก ๋ํ ์ ๋ฆฌ
- ์ปจํ ์คํธ ๋ณต์: ์ด์ ๋ํ์ ์ ์ฒด ์ปจํ ์คํธ์ ํจ๊ป ์ฌ๊ฐ
- ์๋ฏธ ๊ฒ์: ์์ฐ์ด๋ฅผ ์ฌ์ฉํ ๋ํ ๊ธฐ๋ก ๊ฒ์
๐ ๋น ๋ฅธ ์์
1. MCP ์ค์
~/.aws/amazonq/mcp.json์ ์ถ๊ฐ:
{
"mcpServers": {
"q-mem": {
"command": "uvx",
"args": ["q_mem_mcp_server@latest"],
"env": {
"Q_CLI_DB_PATH": "~/Library/Application Support/amazon-q/data.sqlite3",
"Q_MEM_VERBOSE": "true"
},
"disabled": false,
"autoApprove": [
"start_session",
"resume_session",
"search_memory_by_session_id",
"get_storage_stats",
"list_sessions"
]
}
}
}
2. ์ฌ์ฉ ์์
# Q CLI ์์
q chat
# ์ ์ธ์
์์
start_session(description="๋ฐฑ์๋๊ฐ๋ฐ")
# ๋๋ ์์ฐ์ด: "๋ฐฑ์๋๊ฐ๋ฐ ์ธ์
์์ํด์ค"
# ์ผ๋ฐ์ ์ผ๋ก ๋ํ (์๋ ์ ์ฅ๋จ)
# ... ๋ํ ์งํ ...
# ์ธ์
๋ชฉ๋ก ๋ณด๊ธฐ
list_sessions()
# ๋๋ ์์ฐ์ด: "์ธ์
๋ชฉ๋ก ๋ณด์ฌ์ค"
# ์ธ์
์ฌ๊ฐ (์ ์ฒด ์ปจํ
์คํธ ๋ก๋)
resume_session(session_id="๋ฐฑ์๋๊ฐ๋ฐ")
# ๋๋ ์์ฐ์ด: "๋ฐฑ์๋๊ฐ๋ฐ ์ธ์
์ผ๋ก ์ฌ๊ฐํด์ค"
๐ ๏ธ ์ฌ์ฉ ๊ฐ๋ฅํ ๋ช ๋ น์ด
| ๋ช ๋ น์ด | ์ค๋ช |
|---|---|
start_session(description) |
์ ์ธ์ ์์ |
list_sessions() |
๋ชจ๋ ์ธ์ ๋ชฉ๋ก ๋ณด๊ธฐ |
resume_session(session_id) |
์ ์ฒด ์ปจํ ์คํธ์ ํจ๊ป ์ธ์ ์ฌ๊ฐ |
search_memory_by_session_id(session_id, query) |
์ด์ ๋ํ ๊ฒ์ |
delete_session(session_id, confirm=true) |
์ธ์ ์ญ์ |
get_storage_stats() |
์ ์ฅ์ ์ํ ํ์ธ |
๐ง ๊ธฐ์ ์คํ
- ChromaDB: ๋ํ ์ ์ฅ ๋ฐ ๊ฒ์์ ์ํ ๋ฒกํฐ ๋ฐ์ดํฐ๋ฒ ์ด์ค
- SQLite WAL: Q CLI ๋ฐ์ดํฐ๋ฒ ์ด์ค์ ์ค์๊ฐ ๋๊ธฐํ
- Sentence Transformers: ์๋ฏธ ๊ฒ์ ์๋ฒ ๋ฉ
- MCP Protocol: Amazon Q์์ ํต์
๐ ๋ฐ์ดํฐ ์ ์ฅ
- ChromaDB:
~/.Q_mem/chroma_db/ - ๋๊ธฐํ ์ํ:
~/.Q_mem/sync_state.json - ๋ก๊ทธ:
~/.Q_mem/q_mem.log
๐ ์๋ ๋๊ธฐํ ๊ธฐ๋ฅ
Q CLI ๋ํ๊ฐ ChromaDB์ ์ค์๊ฐ์ผ๋ก ์๋ ์ ์ฅ๋ฉ๋๋ค:
- ์ค์๊ฐ ๊ฐ์ง: 2์ด๋ง๋ค ์๋ก์ด ๋ํ ํ์ธ
- ๋ถ๋ถ ์คํจ ์ฒ๋ฆฌ: ์ผ๋ถ ์คํจํด๋ ์ฑ๊ณตํ ๋ํ๋ ์ ์ฅ
- ์๋ ๋ณต๊ตฌ: ์ฐ์ ์คํจ ์ ์๋ ๋ณต๊ตฌ
- ์ํ ๋ณต์: ์ฌ์์ ํ ๋๊ธฐํ ์ํ ๋ณต์
๐ ํ์ ์ ์ธ ๋ฉํฐ ํ๋ฅด์๋ ์ํฌํ๋ก์ฐ ์์
์๋ก ๋ค๋ฅธ ์ ๋ฌธ๊ฐ ํ๋ฅด์๋ ๊ฐ์ ๋งค๋๋ฌ์ด ์ปจํ ์คํธ ์ ํ์ ํ์ ๊ฒฝํํด๋ณด์ธ์:
# === 1์ผ์ฐจ: ๋ฐฑ์๋ ๊ฐ๋ฐ ์ปจํ
์คํธ ===
q chat
> start_session(description="๋ฐฑ์๋๊ฐ๋ฐ")
# ๋๋ ์์ฐ์ด: "๋ฐฑ์๋๊ฐ๋ฐ ์ปจํ
์คํธ๋ก ์์ํด์ค"
โ
'๋ฐฑ์๋๊ฐ๋ฐ' ์ปจํ
์คํธ๊ฐ ์์๋์์ต๋๋ค
> "๋๋ ์ด์ ๋ถํฐ ๋ฐฑ์๋ ๊ฐ๋ฐ์ ํ๋ฅด์๋์ผ. ๋ง์ดํฌ๋ก์๋น์ค ์ํคํ
์ฒ ์ค๊ณ๋ฅผ ๋์์ค"
๐ฏ ๋ฐฑ์๋ ๊ฐ๋ฐ์: ๊ฒฌ๊ณ ํ ๋ง์ดํฌ๋ก์๋น์ค ์ํคํ
์ฒ ์ค๊ณ๋ฅผ ๋์๋๋ฆฌ๊ฒ ์ต๋๋ค...
> "PyPI API ํค ์ ์ฅํด์ค: pypi-AgEI..."
โ
ํฅํ ๋ฐฐํฌ๋ฅผ ์ํด PyPI API ํค๊ฐ ์ ์ฅ๋์์ต๋๋ค
> "JWT๋ฅผ ์ฌ์ฉํ ์ฌ์ฉ์ ์ธ์ฆ ์๋น์ค ์ค๊ณํด์ค"
๐ฏ ๋ฐฑ์๋ ๊ฐ๋ฐ์: ํฌ๊ด์ ์ธ JWT ์ธ์ฆ ์๋น์ค ์ค๊ณ๋ฅผ ์ ์ํ๊ฒ ์ต๋๋ค...
# ... ์์ธํ ๋ฐฑ์๋ ๋
ผ์ ๊ณ์ ...
# === 2์ผ์ฐจ: ๋ฐ์ดํฐ๋ฒ ์ด์ค ์ค๊ณ ์ปจํ
์คํธ ===
q chat
> start_session(description="DBA")
# ๋๋ ์์ฐ์ด: "๋ฐ์ดํฐ๋ฒ ์ด์ค ๊ด๋ฆฌ์ ์ปจํ
์คํธ๋ก ์์ํด์ค"
โ
'DBA' ์ปจํ
์คํธ๊ฐ ์์๋์์ต๋๋ค
> "๋๋ ์ด์ ๋ถํฐ ๋ฐ์ดํฐ๋ฒ ์ด์ค ๊ด๋ฆฌ์ ํ๋ฅด์๋์ผ. ์ฌ์ฉ์ ์๋น์ค ๋ฐ์ดํฐ๋ฒ ์ด์ค ์ต์ ํ๋ฅผ ๋์์ค"
๐ฏ ๋ฐ์ดํฐ๋ฒ ์ด์ค ๊ด๋ฆฌ์: ๋ฐ์ดํฐ๋ฒ ์ด์ค ์ค๊ณ ์ต์ ํ๋ฅผ ๋์๋๋ฆฌ๊ฒ ์ต๋๋ค...
> "์ฌ์ฉ์ ์กฐํ๋ฅผ ์ํ ์ต์ ์ ์ธ๋ฑ์ฑ ์ ๋ต์ ๋ญ์ผ?"
๐ฏ ๋ฐ์ดํฐ๋ฒ ์ด์ค ๊ด๋ฆฌ์: ์ต์ ์ ์ฌ์ฉ์ ์กฐํ ์ฑ๋ฅ์ ์ํด ๋ค์ ์ธ๋ฑ์ฑ ์ ๋ต์ ๊ณ ๋ คํ์ธ์...
# ... ์์ธํ ๋ฐ์ดํฐ๋ฒ ์ด์ค ๋
ผ์ ๊ณ์ ...
# === 3์ผ์ฐจ: ๋งค๋๋ฌ์ด ์ปจํ
์คํธ ์ ํ ===
q chat
> list_sessions()
# ๋๋ ์์ฐ์ด: "๋ชจ๋ ์ปจํ
์คํธ ๋ณด์ฌ์ค"
๐ ์ปจํ
์คํธ ๋ชฉ๋ก:
1. ๋ฐฑ์๋๊ฐ๋ฐ (15๊ฐ ๋ํ) - ๋ฐฑ์๋ ๊ฐ๋ฐ ๋ฐ API ์ค๊ณ
2. DBA (8๊ฐ ๋ํ) - ๋ฐ์ดํฐ๋ฒ ์ด์ค ์ต์ ํ ๋ฐ ์ธ๋ฑ์ฑ
> resume_session(context_id="๋ฐฑ์๋๊ฐ๋ฐ")
# ๋๋ ์์ฐ์ด: "๋ฐฑ์๋๊ฐ๋ฐ ์ปจํ
์คํธ๋ก ์ฌ๊ฐํด์ค"
๐ '๋ฐฑ์๋๊ฐ๋ฐ' ์ปจํ
์คํธ๊ฐ ์ ์ฒด ์ปจํ
์คํธ์ ํจ๊ป ์ฌ๊ฐ๋์์ต๋๋ค
๐ฏ ๋ฐฑ์๋ ๊ฐ๋ฐ์: ๋ค์ ์ค์
จ๊ตฐ์! JWT ์ธ์ฆ ์๋น์ค์ ๋ํด ๋
ผ์ํ๊ณ ์์์ฃ ...
> "๋ด PyPI ํค ๊ธฐ์ตํ์ง? ์ฐ๋ฆฌ๊ฐ ์ค๊ณํ ์ธ์ฆ ์๋น์ค๋ฅผ ๋ฐฐํฌํด์ผ ํด"
๐ฏ ๋ฐฑ์๋ ๊ฐ๋ฐ์: ๋ค! ์ ์ฅ๋ PyPI ํค๋ฅผ ์ฌ์ฉํฉ๋๋ค: pypi-AgEI...
โ
q_auth_service v1.0.0์ PyPI์ ๋ฐฐํฌ ์ค...
> "์ด์ DBA ์ปจํ
์คํธ๋ก ์ ํํด์ ์ฐ๋ฆฌ ๋ฐ์ดํฐ๋ฒ ์ด์ค ์ค๊ณ๊ฐ ์ด ๋ฐฐํฌ๋ฅผ ์ง์ํ๋์ง ํ์ธํด์ค"
> resume_session(context_id="DBA")
# ๋๋ ์์ฐ์ด: "๋ฐ์ดํฐ๋ฒ ์ด์ค ๊ด๋ฆฌ์ ์ปจํ
์คํธ๋ก ์ ํํด์ค"
๐ 'DBA' ์ปจํ
์คํธ๊ฐ ์ ์ฒด ์ปจํ
์คํธ์ ํจ๊ป ์ฌ๊ฐ๋์์ต๋๋ค
๐ฏ ๋ฐ์ดํฐ๋ฒ ์ด์ค ๊ด๋ฆฌ์: ์ธ์ฆ ์๋น์ค๋ฅผ ์ํด ๋
ผ์ํ๋ ์ธ๋ฑ์ฑ ์ ๋ต์ ํ์ธํ๊ฒ ์ต๋๋ค...
> "๋ฐฑ์๋ ํ์ด JWT ์๋น์ค๋ฅผ ๋ฐฐํฌํ์ด. ์ฐ๋ฆฌ ์ธ๋ฑ์ค ์ค๊ณ๊ฐ ์์ ๋ถํ๋ฅผ ์ฒ๋ฆฌํ ์ ์์๊น?"
๐ฏ ๋ฐ์ดํฐ๋ฒ ์ด์ค ๊ด๋ฆฌ์: ์ด์ ์ต์ ํ ๋
ผ์๋ฅผ ๋ฐํ์ผ๋ก, (user_id, created_at) ๋ณตํฉ ์ธ๋ฑ์ค๊ฐ JWT ๊ฒ์ฆ ์ฟผ๋ฆฌ๋ฅผ ํจ์จ์ ์ผ๋ก ์ฒ๋ฆฌํ ๊ฒ์
๋๋ค...
# === 4์ผ์ฐจ: ์ปจํ
์คํธ ๊ฐ ์ง์ ํตํฉ ===
> search_memory_by_context(context_id="๋ฐฑ์๋๊ฐ๋ฐ", query="JWT ํ ํฐ ๋ง๋ฃ")
# ๋๋ ์์ฐ์ด: "๋ฐฑ์๋๊ฐ๋ฐ ์ปจํ
์คํธ์์ JWT ํ ํฐ ๋ง๋ฃ ๊ฒ์ํด์ค"
๐ '๋ฐฑ์๋๊ฐ๋ฐ' ์ปจํ
์คํธ์์ ๋ฐ๊ฒฌ:
- "๋ณด์์ ์ํด JWT ํ ํฐ์ 15๋ถ ํ ๋ง๋ฃ๋์ด์ผ ํจ"
- "๋ฆฌํ๋ ์ ํ ํฐ์ 7์ผ๊ฐ ์ ํจ"
- "๋น ๋ฅธ ์กฐํ๋ฅผ ์ํด ๋ฆฌํ๋ ์ ํ ํฐ์ Redis์ ์ ์ฅ"
> resume_session(context_id="DBA")
# ๋๋ ์์ฐ์ด: "๋ฐ์ดํฐ๋ฒ ์ด์ค ์ปจํ
์คํธ๋ก ๋ค์ ์ ํํด์ค"
๐ฏ ๋ฐ์ดํฐ๋ฒ ์ด์ค ๊ด๋ฆฌ์: JWT ๋ฆฌํ๋ ์ ํ ํฐ ์ ์ฅ์ ์ํ ์ต์ ํ๊ฐ ํ์ํ๋ค๊ณ ๊ธฐ์ตํฉ๋๋ค...
> "๋ฐฑ์๋ ์ปจํ
์คํธ ๊ธฐ๋ฐ์ผ๋ก, 7์ผ๊ฐ ์ ํจํ ๋ฆฌํ๋ ์ ํ ํฐ์ ์ํ Redis ์ต์ ํ๊ฐ ํ์ํด"
๐ฏ ๋ฐ์ดํฐ๋ฒ ์ด์ค ๊ด๋ฆฌ์: ์๋ฒฝํฉ๋๋ค! ๊ณ ๊ฐ์ฉ์ฑ ๋ฆฌํ๋ ์ ํ ํฐ ์ ์ฅ์ ์ํ Redis ํด๋ฌ์คํฐ๋ง ์ ๋ต์ ์ค๊ณํ๊ฒ ์ต๋๋ค...
๐ ์ ์ด๊ฒ์ด ํ์ ์ ์ธ๊ฐ
- ์ง์์ ์ธ ์ ๋ฌธ์ฑ: ๊ฐ ์ธ์ ์ด ์ ๋ฌธ ์ง์๊ณผ ์ปจํ ์คํธ๋ฅผ ์ ์ง
- ๋งค๋๋ฌ์ด ์ ํ: ๋ํ ํ๋ฆ์ ์์ง ์๊ณ ์ ๋ฌธ๊ฐ ํ๋ฅด์๋ ๊ฐ ์ด๋
- ์ธ์ ๊ฐ ์ง๋ฅ: ์๋ก ๋ค๋ฅธ ์ ๋ฌธ๊ฐ ์ปจํ ์คํธ ๊ฐ ์ง์ ๊ฒ์ ๋ฐ ์ฐธ์กฐ
- ๋ณด์ ์๊ฒฉ์ฆ๋ช ์ ์ฅ: API ํค์ ๋ฏผ๊ฐํ ๋ฐ์ดํฐ๊ฐ ์ธ์ ๊ฐ ์ง์
- ์์ฐ์ค๋ฌ์ด ์ํฌํ๋ก์ฐ: ์ค์ ๋ค์ํ ์ ๋ฌธ๊ฐ ๊ฐ ํ์ ์ ๋ฐ์
๐ฏ ์ค์ ํ์ฉ ์ฌ๋ก
- DevOps ํ: ๊ฐ๋ฐ์, DBA, ์ธํ๋ผ ํ๋ฅด์๋ ๊ฐ ์ ํ
- ํ์คํ ํ๋ก์ ํธ: ํ๋ก ํธ์๋, ๋ฐฑ์๋, ๋ฐ์ดํฐ๋ฒ ์ด์ค ์ ๋ฌธ๊ฐ ์ปจํ ์คํธ
- ํ์ต ๊ฒฝ๋ก: ๋ค์ํ ๊ธฐ์ ์ด๋ ๊ฐ๋ ๋ณ ๋ณ๋ ์ปจํ ์คํธ
- ํด๋ผ์ด์ธํธ ํ๋ก์ ํธ: ํด๋ผ์ด์ธํธ๋ณ ์ ์ฉ ์ปจํ ์คํธ์ ์ง์์ ์ธ ์ปจํ ์คํธ
- ์ฝ๋ ๋ฆฌ๋ทฐ: ๋ค์ํ ์ ๋ฌธ๊ฐ ํ๋ฅด์๋์ ์๋ก ๋ค๋ฅธ ๊ด์
๐ก ์ฌ์ฉ ํ
- ์ปจํ ์คํธ ์ ๋ฆฌ: ์ฃผ์ , ์ญํ , ํ๋ก์ ํธ๋ณ๋ก ๋ํ ๋ถ๋ฆฌ
- ์๋ฏธ ๊ฒ์: ์ ํํ ํค์๋๋ณด๋ค ์์ฐ์ด ์ฌ์ฉ
- ์ปจํ
์คํธ ํ์ฉ: ์์ ํ ๋ํ ๋ณต์์ ์ํด
resume_session์ฌ์ฉ - ์ ๊ธฐ ์ ๋ฆฌ: ์ฑ๋ฅ ์ ์ง๋ฅผ ์ํด ๋ถํ์ํ ์ปจํ ์คํธ ์ญ์
- ์ปจํ
์คํธ ๊ฐ ์ฐธ์กฐ:
search_memory_by_context๋ฅผ ์ฌ์ฉํด ํ๋ฅด์๋ ๊ฐ ๊ด๋ จ ์ ๋ณด ์ฐพ๊ธฐ - ์์ฐ์ด ์ง์: "๋ฐฑ์๋๊ฐ๋ฐ ์ปจํ ์คํธ๋ก ์์ํด์ค" ๊ฐ์ ์์ฐ์ด ๋ช ๋ น ์ฌ์ฉ
๋ฉ๋ชจ๋ฆฌ ๊ด๋ฆฌ
# ์ค๋๋ ์ปจํ
์คํธ ์ ๋ฆฌ
cleanup_old_contexts(days=30, confirm=true)
# ๋๋ ์์ฐ์ด: "์ค๋๋ ์ปจํ
์คํธ ์ญ์ ํด์ค"
# ํน์ ์ปจํ
์คํธ ์ญ์
delete_context(context_id="์ปจํ
์คํธ์ด๋ฆ", confirm=true)
# ๋๋ ์์ฐ์ด: "์ปจํ
์คํธ์ด๋ฆ ์ปจํ
์คํธ ์ญ์ ํด์ค"
๐ ๋ผ์ด์ ์ค
MIT License
๐ ๋งํฌ
Project details
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
Built Distribution
Filter files by name, interpreter, ABI, and platform.
If you're not sure about the file name format, learn more about wheel file names.
Copy a direct link to the current filters
File details
Details for the file q_mem_mcp_server-1.0.7.tar.gz.
File metadata
- Download URL: q_mem_mcp_server-1.0.7.tar.gz
- Upload date:
- Size: 28.6 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/6.1.0 CPython/3.12.9
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
2d8bc5e0dc9b197e1352616a2c55ef5539567730b6f1ea1b6501da224747256c
|
|
| MD5 |
18ef5ad415ea9bbe7714ab5d9de3bacb
|
|
| BLAKE2b-256 |
ab93844f498c65ce16007dcc5f7b519fe3567cfd3b4b9220d4843147820847f9
|
File details
Details for the file q_mem_mcp_server-1.0.7-py3-none-any.whl.
File metadata
- Download URL: q_mem_mcp_server-1.0.7-py3-none-any.whl
- Upload date:
- Size: 30.9 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/6.1.0 CPython/3.12.9
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
679fbf750fff769bbbcc451bf9648742ae3ba08d3b65239eda62cd026fb2303c
|
|
| MD5 |
f0596d84a1f47f4b58cd1c9cd7db11a1
|
|
| BLAKE2b-256 |
eb58ddfaa7fb51ca0a026c85de046b968f43b5386061f7a99ced1dc1cdcebc9d
|