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.

cognee
80
Verified
memlayer
65
Established
Maintenance 25/25
Adoption 10/25
Maturity 25/25
Community 20/25
Maintenance 10/25
Adoption 17/25
Maturity 22/25
Community 16/25
Stars: 13,204
Forks: 1,336
Downloads: —
Commits (30d): 372
Language: Python
License: Apache-2.0
Stars: 261
Forks: 32
Downloads: 875
Commits (30d): 0
Language: Python
License: MIT
No risk flags
No risk flags

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.

Scores updated daily from GitHub, PyPI, and npm data. How scores work