Skip to content

Agent skills for knowledge and memory

7 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. Use before reporting any cosine similarity computed over embeddings or transformer hidden states, whether the agent computed the vectors or

    • Open source
    • 41.3K GitHub stars
    • Knowledge and memory
  2. 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
  3. 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
  4. Use for Azure AI Search, Foundry IQ, document-grounded agents and graphs built over documents

    • Open source
    • 3.2K GitHub stars
    • Knowledge and memory
  5. Process academic PDFs into structured Obsidian literature notes and 9-node critical-thinking canvases

    • Open source
    • 66 GitHub stars
    • Knowledge and memory
  6. Measure Jetson DRAM/NvMap usage and verify before/after memory reclamation with live audit data.

    • Open source
    • 4K GitHub stars
    • Knowledge and memory
  7. 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

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