HomeProjectsArticlesPK BoardAbout
Explore Projects

Cognee

Active
GitHub Python Apache-2.0

Description

A knowledge engine for AI agent memory that builds knowledge graphs and memory layers in 6 lines of code, supporting graph databases, vector stores, and more for knowledge extraction and retrieval.

Key Features

  • Build knowledge graphs and memory layers in 6 lines of code
  • Core API: remember, recall, forget, improve operations
  • Session memory and permanent knowledge graph dual-mode
  • Auto-routing for optimal search strategy selection
  • Claude Code plugin support for cross-session persistent memory
  • Multiple backends: graph databases, vector stores, multiple LLM providers

Use Cases

💡 Adding cross-session persistent memory to AI agents
💡 Building enterprise knowledge graphs for semantic search and reasoning
💡 Sharing knowledge and context across multiple agents
💡 Transforming unstructured documents into queryable structured knowledge

Strengths & Limitations

✅ Strengths

  • • Actively maintained, recent updates
  • • High community interest (30.1k stars)
  • • Permissive open-source license (Apache-2.0)
  • • Established track record (3 years in production)

Tags

agent-memory knowledge-graph vector-store reasoning python

Categories

📚 RAG Tools 🧩 Agent Memory

Quick Start

Install: uv pip install cognee, set your LLM API key, use cognee.remember() to store data, cognee.recall() to query, cognee.forget() to clean up.
Visit GitHub Visit Website

Related Projects

HippoRAG

3.9k · Python
Active A+

NeurIPS 2024 RAG framework inspired by human long-term memory, combining knowledge graphs with personalized PageRank for continuous knowledge integration in LLMs.

ragknowledge-graphlong-term-memory +2
  • · Neurobiologically inspired RAG framework modeled after human hippocampal memory system
  • · Knowledge graph construction with personalized PageRank for associative multi-hop retrieval
  • · Continuous non-parametric learning that integrates new knowledge without retraining
View on GitHub

MCP Memory Service

1.9k · Python
Normal A

Open-source persistent memory service for AI agents, supporting LangGraph, CrewAI, and AutoGen with REST API, knowledge graph, and autonomous memory consolidation.

agent-memorymcpknowledge-graph +2
  • · Open-source persistent memory service for AI agents — provides long-term memory storage and retrieval via REST API for any MCP-compatible framework
  • · Knowledge graph-backed memory with autonomous consolidation — agents organize and merge memories into structured knowledge representations over time
  • · Multi-framework compatibility — works with LangGraph, CrewAI, AutoGen, and other popular agent frameworks out of the box
View on GitHub

MemAgent

1.1k · Python
Stale B

A MemAgent framework that can extrapolate to 3.5M context tokens, along with a training framework for RL training of any agent workflow.

memoryagentrag +2
  • · Ultra-Long Context Processing: Extrapolate from 8K training context to 3.5M tokens with performance loss under 5%
  • · Reinforcement Learning Driven: Trained with RLVR (Reinforcement Learning from Verifiable Rewards), extends DAPO algorithm for end-to-end multi-turn conversation optimization
  • · Linear Time Complexity: Breaks through computational bottlenecks in long-text processing with linear resource scaling
View on GitHub

Related Articles

GraphRAGLightRAGRAG

GraphRAG vs LightRAG: Deep Comparison of Two Engineering Routes for Graph-Enhanced RAG

Systematic comparison of Microsoft GraphRAG (community detection + global summarization) and HKUDS LightRAG (dual-layer graph + incremental update) across index construction, retrieval paradigm, cost structure, query quality, and use cases. Includes a decision tree by data scale, query type, and ops budget.

Read more →