
A persistent, compounding knowledge base combining Karpathy's LLM Wiki pattern with a structured knowledge graph
- Open source
- 41.3K GitHub stars
- Knowledge and memory

A persistent, compounding knowledge base combining Karpathy's LLM Wiki pattern with a structured knowledge graph

Build production RAG pipelines and persistent agent memory using Pinecone as the vector database backend

Qdrant provides client SDKs for various programming languages, allowing easy integration with Qdrant deployments.

Turn tickets, PRDs or git logs into user-facing release notes grouped by change type

Look up Google developer docs through the Developer Knowledge MCP server or REST fallback

List, inspect and query Agent Platform RAG Engine corpora and ground Gemini answers

Discovers requirements, and generates architectural, design, and deployment guidance for a retrieval-augmented generation (RAG)-capable ente

Train or fine-tune sentence-transformers models across `SentenceTransformer` (bi-encoder, dense or static embedding model for retrieval, sim


NVIDIA RAG Blueprint — deploy, configure, troubleshoot, and manage

Filesystem RAG benchmarks: corpus/, train.json, evaluate_rag.py (RAGAS quality)

Performance benchmarking for a deployed NVIDIA RAG Blueprint server: profiling pass + aiperf load test driven by a single YAML config

Run TAO Data Services image embedding to turn a parquet of image filepaths into an embedding parquet using CLIP, SigLIP, or a TAO checkpoint

NVIDIA CDF curation and retrieval

Measure Jetson DRAM/NvMap usage and verify before/after memory reclamation with live audit data.

Reclaim DRAM by disabling unused subsystems across MB1 BCT, MB2 BCT, kernel reserved-memory, and SWIOTLB

Techniques for reducing peak GPU memory in Megatron Bridge — expandable segments, PEFT + SP input re-gather, parallelism resizing, activatio

Manage durable working-session memory for coding agents

Use when planning, debugging, tuning, evaluating, exporting, or deploying public Nemotron `embed`/`rerank` retrieval recipes.

Build search applications using Azure AI Search SDK for JavaScript (@azure/search-documents)

Converts VitePress/GFM wiki markdown to Azure DevOps Wiki-compatible format

Generates AGENTS.md files for repository folders — coding agent context files with build commands, testing instructions, code style, project

Analyzes code repositories and generates hierarchical documentation structures with onboarding guides

Analyzes git commit history and generates structured changelogs categorized by change type

Generates llms.txt and llms-full.txt files for LLM-friendly project documentation following the llms.txt specification

Generates four audience-tailored onboarding guides in an onboarding/ folder — Contributor, Staff Engineer, Executive, and Product Manager

Generates rich technical documentation pages with dark-mode Mermaid diagrams, source code citations, and first-principles depth

Answers questions about a code repository using source file analysis

Conducts multi-turn iterative deep research on specific topics within a codebase with zero tolerance for shallow analysis

Packages generated wiki Markdown into a VitePress static site with dark theme, dark-mode Mermaid diagrams with click-to-zoom, and production
See every kind of AI for knowledge and memory: tools, agents, MCP servers and skills.Ranked: the best AI for knowledge and memory.