feat(memory): add Agent memory module #904
Open
+3,323
−0
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
implement short-term memory (InMemoryMemory) with in-memory storage implement long-term memory (Mem0LongTermMemory) using mem0 for vector retrieval add MemoryManager for unified short/long-term orchestration and diagnostics provide MemoryToolkit and register_memory_tools for ToolRegistry integration add YAML-based configuration and loader (env + file), with ModelFactory support embedding dimension adaptation (config.dimensions → vector store)
![gemini-code-assist[bot]](https://avatars.githubusercontent.com/in/956858?s=60&v=4){kind=small}
Contributor
There was a problem hiding this comment.
Code Review
This pull request introduces a comprehensive memory module for the agent, including short-term (in-memory) and long-term (vector-based via mem0) capabilities, along with configuration management and tool integration. The overall structure is well-designed. However, I've identified a critical issue in the custom adapters for mem0 where asyncio.run() is used unsafely, which could lead to runtime crashes. I've also found an incorrect value in the example YAML configuration that would cause API errors. My review includes suggestions to fix these issues to ensure the stability and correctness of the new memory module.
…dding dimensions to 1536 per review (PR flagos-ai#904)
Teeeio
changed the title
|
|
Teeeio
requested review from
Caozhou1995,
aoyulong,
cyber-pioneer and
zhaoyinglia
as code owners
Teeeio
force-pushed
the
main
branch
3 times, most recently
from
f7c8b01 to
2f63594
Compare
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
PR Category
Core
PR Types
New Features
Improvements
PR Description
implement short-term memory (InMemoryMemory) with in-memory storage
implement long-term memory (Mem0LongTermMemory) using mem0 for vector retrieval
add MemoryManager for unified short/long-term orchestration and diagnostics
provide MemoryToolkit and register_memory_tools for ToolRegistry integration
add YAML-based configuration and loader (env + file), with ModelFactory
support embedding dimension adaptation (config.dimensions → vector store)