cognee and memlayer
These are **competitors** addressing the same problem space of persistent memory for LLMs, with cognee offering a more comprehensive knowledge graph-based engine while memlayer provides a lighter-weight abstraction layer for memory injection.
About cognee
topoteretes/cognee
Knowledge Engine for AI Agent Memory in 6 lines of code
Combines vector search with graph databases to index documents by semantic meaning and learned entity relationships, enabling hybrid retrieval that improves context relevance for agents. Supports multimodal ingestion across arbitrary data formats and structures while maintaining local execution, ontology grounding, and audit trails for trustworthy agent isolation. Integrates with multiple LLM providers and includes CLI tooling and web UI for pipeline management alongside programmatic Python APIs.
About memlayer
divagr18/memlayer
Plug-and-play memory for LLMs in 3 lines of code. Add persistent, intelligent, human-like memory and recall to any model in minutes.
Implements a hybrid vector + knowledge graph architecture using ChromaDB and NetworkX to enable fast semantic search combined with entity relationship traversal. Supports three operation modes (LOCAL/ONLINE/LIGHTWEIGHT) that trade off accuracy, startup time, and cost by varying the salience filtering approach—from ML-based sentence transformers to LLM embeddings to lightweight keyword extraction. Works across all major LLM providers (OpenAI, Claude, Gemini, Ollama, LMStudio) with intelligent multi-tier search (Fast/Balanced/Deep) that automatically adjusts retrieval depth based on query complexity.
Related comparisons
Scores updated daily from GitHub, PyPI, and npm data. How scores work