convez.ai
MCP ServerDados & AnalyticsIntermediário
abservicesground

AI Knowledge Hub

abservicesground/ai-knowledge-hub

Repositório curado de recursos LLM, RAG, agentes e engenharia de IA

Ver no GitHub
InicialPluginScore · de 0 a 100

Repositório comunitário curado com os melhores recursos open-source para engenharia de IA e LLMs. Organiza conteúdo sobre RAG, agentes, fine-tuning, prompt engineering, bancos de dados vetoriais e infraestrutura, com guias originais e frameworks de decisão.

Instalação

$npx convez-ai abservicesground/ai-knowledge-hub

1 comando no terminal: detecta o formato do repositório (marketplace ou plugin avulso) e instala via Claude Code. Requer Node 18+ e o Claude Code instalado.

Métricas

Estrelas
2
Forks
1
Acompanhando
0
Saúde
71%
Último commit
há 5 meses
Versão
—
Issues abertas
1
Contribuidores
1

Casos de uso

  • Aprender fundamentos de LLMs e transformers com curva estruturada
  • Implementar RAG com matriz de decisão e padrões de produção
  • Desenhar sistemas multi-agentes com playbook de padrões

Veredito

Base de conhecimento sólida com curadoria editorial e artefatos originais (matrizes de decisão, playbooks, comparadores). Mais útil como referência de aprendizado contínuo do que como MCP server ativo — funciona melhor como repositório de consulta do que ferramenta integrada.

README

A tradução para o português deste README ainda está na fila.

🧠 AI Knowledge Hub

The world's best open-source AI & LLM engineering resources — curated, annotated, and organized into one living repository.

Maintenance Contributions Welcome GitHub Stars License: MIT

A curated collection of the best GitHub repositories, papers, and resources for LLM engineering, RAG, AI agents, fine-tuning, prompt engineering, vector databases, and ML fundamentals — with original guides, decision frameworks, and learning paths built on top.

Stop searching. Start learning.


📚 What's Inside

#SectionWhat It Covers
01ML & DL FoundationsMath, algorithms, deep learning from scratch
02Large Language ModelsHow LLMs work, training, inference, open-source models
03Transformers & ArchitecturesAttention, BERT, GPT, ViT, Mamba, MoE — full lineage
04RAGRetrieval-Augmented Generation, production patterns
05AI AgentsAgent design patterns, multi-agent systems, frameworks
06Model Context ProtocolMCP spec, servers, SDKs, quick-start template
07Vector DatabasesEmbeddings, FAISS, Qdrant, Chroma, Weaviate, Milvus
08Fine-Tuning & PEFTLoRA, QLoRA, DPO, RLHF, SFT — with decision guide
09Prompt EngineeringCoT, few-shot, ReAct, libraries, pattern catalog
10Tools & InfrastructureLangChain, vLLM, Ollama, Dify, serving, observability
11Coding & ML InterviewsDSA, ML system design, 30-day AI interview track
12Data ScienceStats, SQL, EDA, feature engineering, daily practice
13Must-Read PapersSeminal research with TL;DRs and implementations
14Learning PathsRole-specific roadmaps: LLM engineer, researcher, DS
15Newsletter PicksEditorial intake queue — new additions land here first

⭐ Original Value-Add Artifacts

These are our proof of work — original guides built on top of the curated resources:

ArtifactSectionWhat It Is
RAG Decision Matrix04-ragChoose chunking strategy, retriever, and reranker by use case
Agent Pattern Playbook05-agents10 agent design patterns with code sketches
MCP Quick-Start Template06-mcpProduction-ready FastMCP server skeleton
Prompt Pattern Catalog09-promptsPrompting patterns by use case with templates and failure modes
Vector DB Comparison07-vector-databasesFeature + latency comparison across Qdrant, Chroma, Weaviate, etc.
When to Fine-Tune08-fine-tuningRAG vs. fine-tune vs. prompt engineering decision flowchart
AI Stack Guide10-tools-and-infraStack decisions by team size
30-Day Interview Track11-coding-and-interviewsAI engineering interview prep plan
Paper TL;DR Index13-papers10 seminal papers, each with 3-sentence summary + implementation
Architecture Family Tree03-transformersModel architecture lineage from 2017 to 2026
Foundations Roadmap01-foundationsBeginner → Practitioner → Researcher learning path
State of LLMs02-llmsMonthly open-source model landscape snapshot

🧱 How This Repo Works

Curation → Annotation → Synthesis. We never claim authorship of curated content. Every resource is linked to its original author with full attribution. Our proof of work is the layer we build on top: decision guides, learning paths, templates, and original artifacts that make the curated content immediately actionable.

The intake pipeline: New resources from our newsletter or community land in 15-newsletter-picks/ first. Each month, the best ones graduate to their permanent section. This keeps the repo living and tied to our editorial work.


🚀 Quick Start by Goal

"I want to build a RAG system" → 04-rag/ → RAG Decision Matrix → 07-vector-databases/

"I want to fine-tune an open-source LLM" → When to Fine-Tune → 08-fine-tuning/

"I want to build an AI agent" → Agent Pattern Playbook → 05-agents/ → 06-mcp/

"I want to prep for an AI engineering interview" → 30-Day Interview Track

"I'm new to ML/AI" → Foundations Roadmap → 14-learning-paths/


🤝 Contributing

See CONTRIBUTING.md. You can add a new resource in under 5 minutes by opening a PR targeting 15-newsletter-picks/README.md.


📎 Attribution

All curated repos belong to their original authors. See CREDITS.md for the full attribution log. We link, layer, and synthesize — we never claim ownership of others' work.


📄 License

MIT — see LICENSE. Original content (guides, templates, decision frameworks) is freely usable with attribution.


Updated monthly · v1.0 · June 2026

Ver o original no GitHub

Bom para

Relacionados