
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

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

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

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

Use for Azure AI Search, Foundry IQ, document-grounded agents and graphs built over documents

Process academic PDFs into structured Obsidian literature notes and 9-node critical-thinking canvases

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

Run TAO Data Services image embedding to turn a parquet of image filepaths into an embedding parquet using CLIP, SigLIP, or a TAO checkpoint
See every kind of AI for knowledge and memory: tools, agents, MCP servers and skills.Ranked: the best AI for knowledge and memory.