feat: Add AgentMemory as memory_manager_backend option

[zhenai1314521]

Summary This PR adds AgentMemory as an optional memory_manager_backend for QwenPaw, enabling high-precision triple retrieval (vector + BM25 + knowledge graph). ## Changes - Add `AgentMemoryManager` class implementing `BaseMemoryManager` - Add `AgentMemoryMCPClient` for MCP protocol communication - Support `memory_recall`, `memory_save`, `memory_patterns`, `memory_relations` - Add 'agentmemory' option to `memory_manager_backend` config - Enable high-precision triple retrieval (vector + BM25 + knowledge graph) ## Configuration To use AgentMemory as the memory backend, set in config.json: ```json { "memory_manager_backend": "agentmemory" } ``` ## Requirements - Node.js >= 18 - npm - npx @agentmemory/mcp ## Testing All tests passed: - MCP client connection: OK - memory_save: OK - memory_recall: OK - memory_patterns: OK - memory_relations: OK - AgentMemoryManager initialization: OK ## Files Changed | File | Change | |------|--------| | src/qwenpaw/agents/memory/init.py | Export new classes | | src/qwenpaw/agents/memory/agent_memory_manager.py | New file | | src/qwenpaw/agents/memory/agent_memory_mcp_client.py | New file | | src/qwenpaw/app/workspace/workspace.py | Add agentmemory backend | | src/qwenpaw/config/config.py | Add agentmemory option | ## Related - AgentMemory: https://github.com/agentmemory/agentmemory - MCP Protocol: https://modelcontextprotocol.io

[github-actions]

Welcome to QwenPaw! 🐾

Hi @zhenai1314521, thank you for your first Pull Request! 🎉

📋 About PR Template

To help maintainers review your PR faster, please make sure to include:

• ✅ Description - What this PR does and why
• ✅ Type of Change - Bug fix / Feature / Breaking change / Documentation / Refactoring
• ✅ Component(s) Affected - Core / Console / Channels / Skills / CLI / Documentation / Tests / CI/CD / Scripts
• ✅ Checklist:
  • Run and pass pre-commit run --all-files
  • Run and pass relevant tests (pytest or as applicable)
  • Update documentation if needed
• ✅ Testing - How to test these changes
• ✅ Local Verification Evidence:

  pre-commit run --all-files
  # paste summary result
  
  pytest
  # paste summary result

Complete PR information helps speed up the review process. You can edit the PR description to add these details.

🙌 Join Developer Community

Thanks so much for your contribution! We'd love to invite you to join the official QwenPaw developer group! You can find the Discord and DingTalk group links under the "Developer Community" section on our docs page:
https://qwenpaw.agentscope.io/docs/community

We truly appreciate your enthusiasm—and look forward to your future contributions! 😊

We'll review your PR soon.

[jinliyl]

@zhenai1314521
Thank you very much for your code feedback.
Due to the recent refactoring of the memory interface, please reorganize your code according to the new memory interface and format.

https://github.com/agentscope-ai/QwenPaw/blob/main/src/qwenpaw/agents/memory/base_memory_manager.py