NirDiamant

Agent_Memory_Techniques

Recently maintained

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.

Stars
1,132

Community interest

Forks
141

Community forks

7-day growth
+10

Observed snapshot change

Language
Jupyter Notebook

Repository metadata

Star history & growth

Observed snapshots only. Missing observations are not invented.

1,132 ★49 observations
2026-08-102026-11-03
Inspect recent observations
DateStars
2026-10-051,078
2026-10-061,082
2026-10-071,084
2026-10-081,086
2026-10-091,093
2026-10-101,095
2026-10-111,095
2026-10-121,095
2026-10-131,096
2026-10-141,101
2026-10-151,102
2026-10-161,102
2026-10-171,102
2026-10-181,104
2026-10-191,111
2026-10-201,112
2026-10-211,115
2026-10-221,117
2026-10-231,117
2026-10-241,119
2026-10-251,121
2026-10-261,121
2026-10-271,123
2026-10-281,125
2026-10-291,127
2026-10-301,127
2026-10-311,127
2026-11-011,130
2026-11-021,131
2026-11-031,132

Get the source & start here

Cloning downloads source; follow official setup and dependency instructions.

git clone https://github.com/NirDiamant/Agent_Memory_Techniques.git
READMEgithub.dev

About this project

What is Agent_Memory_Techniques?

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.

How do I get started?

Clone with git clone https://github.com/NirDiamant/Agent_Memory_Techniques.git. Cloning is not a complete installation; follow the official README for dependencies, hosts and usage.

Can I use it commercially?

Current license information: Apache-2.0. Review the original terms, dependencies and your intended use.

What do maintenance and growth indicate?

Current status: Recently maintained. Activity is not a security audit. Growth uses collected snapshots; missing baselines are not estimated.