Skip to content

Agent skills for knowledge and memory

113 agent skills that give AI long-term memory, knowledge bases, notes and retrieval over your content. Each one shows what it can run and how to install it in Claude Code, Codex, Cursor and other agents.
  1. 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
  2. Build production RAG pipelines and persistent agent memory using Pinecone as the vector database backend

    • Open source
    • 41.3K GitHub stars
    • Knowledge and memory
  3. Qdrant provides client SDKs for various programming languages, allowing easy integration with Qdrant deployments.

    • Open source
    • 41.3K GitHub stars
    • Knowledge and memory
  4. Turn tickets, PRDs or git logs into user-facing release notes grouped by change type

    • Open source
    • 28.1K GitHub stars
    • Knowledge and memory
  5. Look up Google developer docs through the Developer Knowledge MCP server or REST fallback

    • Open source
    • 24.4K GitHub stars
    • Developer tools
  6. Train or fine-tune sentence-transformers models across `SentenceTransformer` (bi-encoder, dense or static embedding model for retrieval, sim

    • Open source
    • 11.4K GitHub stars
    • Knowledge and memory
  7. Mutation-driven test vector generation

    • Open source
    • 8.2K GitHub stars
    • Knowledge and memory
  8. NVIDIA RAG Blueprint — deploy, configure, troubleshoot, and manage

    • Open source
    • 4K GitHub stars
    • Knowledge and memory
  9. Filesystem RAG benchmarks: corpus/, train.json, evaluate_rag.py (RAGAS quality)

    • Open source
    • 4K GitHub stars
    • Knowledge and memory
  10. Performance benchmarking for a deployed NVIDIA RAG Blueprint server: profiling pass + aiperf load test driven by a single YAML config

    • Open source
    • 4K GitHub stars
    • Knowledge and memory
  11. Run TAO Data Services image embedding to turn a parquet of image filepaths into an embedding parquet using CLIP, SigLIP, or a TAO checkpoint

    • Open source
    • 4K GitHub stars
    • Design and media
  12. Measure Jetson DRAM/NvMap usage and verify before/after memory reclamation with live audit data.

    • Open source
    • 4K GitHub stars
    • Knowledge and memory
  13. Reclaim DRAM by disabling unused subsystems across MB1 BCT, MB2 BCT, kernel reserved-memory, and SWIOTLB

    • Open source
    • 4K GitHub stars
    • Knowledge and memory
  14. Techniques for reducing peak GPU memory in Megatron Bridge — expandable segments, PEFT + SP input re-gather, parallelism resizing, activatio

    • Open source
    • 4K GitHub stars
    • Knowledge and memory
  15. Manage durable working-session memory for coding agents

    • Open source
    • 4K GitHub stars
    • Knowledge and memory
  16. Use when planning, debugging, tuning, evaluating, exporting, or deploying public Nemotron `embed`/`rerank` retrieval recipes.

    • Open source
    • 4K GitHub stars
    • Knowledge and memory
  17. Build search applications using Azure AI Search SDK for JavaScript (@azure/search-documents)

    • Open source
    • 3.2K GitHub stars
    • Cloud and infrastructure
  18. Converts VitePress/GFM wiki markdown to Azure DevOps Wiki-compatible format

    • Open source
    • 3.2K GitHub stars
    • Knowledge and memory
  19. Generates AGENTS.md files for repository folders — coding agent context files with build commands, testing instructions, code style, project

    • Open source
    • 3.2K GitHub stars
    • Knowledge and memory
  20. Analyzes code repositories and generates hierarchical documentation structures with onboarding guides

    • Open source
    • 3.2K GitHub stars
    • Knowledge and memory
  21. Analyzes git commit history and generates structured changelogs categorized by change type

    • Open source
    • 3.2K GitHub stars
    • Developer tools
  22. Generates llms.txt and llms-full.txt files for LLM-friendly project documentation following the llms.txt specification

    • Open source
    • 3.2K GitHub stars
    • AI models and LLM tooling
  23. Generates four audience-tailored onboarding guides in an onboarding/ folder — Contributor, Staff Engineer, Executive, and Product Manager

    • Open source
    • 3.2K GitHub stars
    • Knowledge and memory
  24. Generates rich technical documentation pages with dark-mode Mermaid diagrams, source code citations, and first-principles depth

    • Open source
    • 3.2K GitHub stars
    • Knowledge and memory
  25. Answers questions about a code repository using source file analysis

    • Open source
    • 3.2K GitHub stars
    • Knowledge and memory
  26. Conducts multi-turn iterative deep research on specific topics within a codebase with zero tolerance for shallow analysis

    • Open source
    • 3.2K GitHub stars
    • Knowledge and memory
  27. Packages generated wiki Markdown into a VitePress static site with dark theme, dark-mode Mermaid diagrams with click-to-zoom, and production

    • Open source
    • 3.2K GitHub stars
    • Knowledge and memory

See every kind of AI for knowledge and memory: tools, agents, MCP servers and skills.Ranked: the best AI for knowledge and memory.