Agentes de IA
OpenViking
A self-evolving context database unifying agent memory, RAG, and skills.
★ 39,4 mil estrelasAGPL-3.0
Ver o guia →LibreAI / Agentes de IA / Agent_Memory_Techniques
// agents · NirDiamant/Agent_Memory_Techniques
Agent_Memory_Techniques
Agent_Memory_Techniques é um projeto de agentes de IA de código aberto de NirDiamant (NirDiamant/Agent_Memory_Techniques no GitHub). Tem 1.090 estrelas no GitHub e 141 forks, é publicado sob a licença Apache-2.0 e foi atualizado pela última vez no GitHub em 21 de setembro de 2026.
30 runnable notebooks teaching everything about agent memory.
★ 1,1 mil estrelas⑂ 141 forksApache-2.0atualizado set 2026
▦ visual: o README deste projeto não inclui nenhuma captura incorporável,
então aqui vai um marcador. O guia abaixo está completo mesmo assim.
então aqui vai um marcador. O guia abaixo está completo mesmo assim.
// dados do projeto
Dados do projeto
- Repositório
- NirDiamant/Agent_Memory_Techniques
- Estrelas no GitHub
- 1.090
- Forks
- 141
- Licença
- Apache-2.0
- Última atualização no GitHub
- 21 de setembro de 2026
- Categoria
- Agentes de IA
- Tipo de ficha
- Guia de instalação completo
// como funciona
Como funciona
- Clarify your goal
Decide what you want the project to do before installing anything.
- Clone the repo
Grab the source and skim the README for setup requirements.
- Install and configure
Install dependencies and add any API keys or settings it needs.
- Run your first task
Launch it and follow the example workflow from the docs.
// recursos
Por que as pessoas gostam tanto
30 notebooks
A full curriculum, runnable top to bottom.
Major systems covered
MemGPT, Mem0, Letta, Zep, Graphiti, and more.
Benchmarks included
LoCoMo evaluations hands-on.
Production patterns
Beyond theory: how teams ship it.
Runnable code
Learn by executing, not just reading.
Free course-quality
A class worth paying for, at no cost.
Advertisement
// execute você mesmo
Execute você mesmo
- Step 1 — Clone the repo
Download the notebooks and move into the folder.
git clone https://github.com/NirDiamant/Agent_Memory_Techniques.git cd Agent_Memory_Techniques - Step 2 — Install Jupyter
Get JupyterLab plus the repo's Python requirements.
pip install jupyterlab pip install -r requirements.txt - Step 3 — Open the notebooks
Launch JupyterLab and work through the notebooks in order.
jupyter lab
// casos de uso
O que você pode criar
- Learn agent memory hands-on.
- Compare Mem0 vs Zep vs Graphiti yourself.
- Study LoCoMo benchmarks.
- Teach a team agent memory.
Advertisement
// perguntas frequentes
Perguntas frequentes
Who maintains Agent_Memory_Techniques?
It is an open-source project at NirDiamant/Agent_Memory_Techniques with 141 forks. Check the contributors tab and recent commits to judge how active maintenance is.
Is Agent_Memory_Techniques free to use?
Yes — Apache 2.0 allows commercial use and modification. Keep the license and notice files, and note it includes a patent grant.
Do I need a GPU?
No — these are notebooks about memory techniques; a laptop with Python and Jupyter is enough.
Beginner friendly?
Yes — it's structured as a course, from buffers to production patterns.
How do I get started?
Clone the repo and follow the README quickstart — the README is the best starting point.
// continue explorando
Ferramentas semelhantes
Agentes de IA
memanto
A memory agent for your agent fleet: it curates, reconciles, and expires shared memories across tools.
★ 2,3 mil estrelasMIT
Ver o guia →Agentes de IA
agent-memory-benchmark
A benchmark for comparing AI agent memory systems head-to-head.
★ 144 estrelasNOASSERTION
Ver o guia →Agentes de IA
deepseek-harness
DeepSeek's plugin-based agent harness where everything is a plugin.
★ 245,5 mil estrelasMIT
Ver o guia →Agentes de IA
hindsight
Agent memory that learns — so your agents get smarter over time.
★ 47,0 mil estrelasMIT
Ver o guia →Agentes de IA
ChatDev
ChatDev — zero-code multi-agent platform (DevAll) for developing everything, from software to research, Apache-2.0
★ 34,6 mil estrelasApache-2.0
Ver o guia →// alternativas
Alternativas em Agentes de IA
Os outros projetos de Agentes de IA com mais estrelas no catálogo do LibreAI — a lista realista de alternativas se Agent_Memory_Techniques não for o ideal para você.
- openclaw★ 391,6 mil
A personal AI that really does things — on any OS, with your data staying yours.
- superpowers★ 294,9 mil
An agentic skills framework & software development methodology that works.
- ECC★ 275,2 mil
Agent harness optimization system with skills, memory and security for Claude Code, Codex and more
- hermes-agent★ 252,0 mil
The agent that grows with you — a Python framework for adaptive AI agents.
- deepseek-harness★ 245,5 mil
DeepSeek's plugin-based agent harness where everything is a plugin.
// mais em agents
Mais em Agentes de IA
Projetos de Agentes de IA próximos no catálogo, os mais próximos em estrelas de Agent_Memory_Techniques: continue explorando dos dois lados dele.
- Talorys★ 1,1 mil
Talorys — your personal AI agent in your own Cloudflare account: chat, memory, tasks, notes and scheduled routines, deployed with one command
- SandboxFusion★ 1,1 mil
ByteDance's SandboxFusion: a secure sandbox for running and judging LLM-generated code in 20+ languages.
- weave★ 1,1 mil
A toolkit for developing AI-powered apps, from the Weights & Biases team.
- langsmith-sdk★ 1,1 mil
Official SDKs for tracing with LangSmith.
- labs-molt★ 1,2 mil
A lean, HuggingFace-native RL framework for agentic research.
- autoevals★ 1,1 mil
Fast, best-practice evaluations for AI model outputs.
Baixe o Agent_Memory_Techniques
Grátis e aberto: pegue o código-fonte, dê uma estrela no repositório e comece a criar.