
Agent_Memory_Techniques
by NirDiamant (personal account)
Agent memory for LLMs: 30 runnable Jupyter notebooks covering conversation buffers, vector stores, knowledge graphs, episodic and semantic memory, MemGPT, Mem0, Letta, Zep, Graphiti, LoCoMo benchmarks, and production patterns. (description from the project’s GitHub page)
Repository facts
- Stars
- 1,108
- Forks
- 142
- Open issues and pull requests
- 2
- Primary language
- Jupyter Notebook
- License
- Apache License 2.0 (Apache-2.0)
- Owner
- NirDiamant · Personal account
- Created
- May 5, 2026
- Last push
- Oct 17, 2026
Topics
Related projects
Projects that share this one’s GitHub topics.
Rank 21: langchain-ai/langchain
The agent engineering platform.
148,026 starsPythonMITLast push Oct 18, 2026
Rank 9,477: caura-ai/caura
Caura (formerly MemClaw) — governed shared memory for AI agent fleets. Multi-agent, multi-tenant, MCP-native. Trust tiers, keystone policies, audit trails, knowledge graph, self-i…
502 starsPythonApache-2.0Last push Oct 18, 2026
Rank 1,777: FlowElement-xinliuyuansu/m_flow
A bio-inspired cognitive memory engine — a new paradigm for Graph RAG.
4,511 starsPythonApache-2.0Last push Sep 1, 2026
Rank 3,619: doobidoo/mcp-memory-service
Open-source persistent memory for AI agent pipelines (LangGraph, CrewAI, AutoGen) and Claude. REST API + knowledge graph + autonomous consolidation.
2,021 starsPythonApache-2.0Last push Oct 18, 2026