# Chroma

> We've seen how tool calling and iterative searches over a Chroma collection can build context for an agent. While this works well for individual runs, agents start fresh each time—repeating expensive

## Pages

- [Agentic Memory](guides-build-agentic-memory.md): We've seen how tool calling and iterative searches over a Chroma collection can build context for an agent. While thi...
- [Laura Lojo-Rodríguez](guides-build-agentic-search.md): {% Video link=" title="Framework-less Agentic Search" /%}
- [Building with AI](guides-build-building-with-ai.md): AI is a new type of programming primitive. Large language models (LLMs) let us write software which can process **uns...
- [Chunking](guides-build-chunking.md): Retrieval-Augmented Generation (RAG) lets us ground large language models in our
- [Introduction to Retrieval](guides-build-intro-to-retrieval.md): Large language models like GPT-5, Claude, or Gemini can write code, answer questions, generate content, and solve com...
- [Look at Your Data](guides-build-look-at-your-data.md): Before building our RAG pipelines and inserting data into Chroma collections, it is worth asking ourselves the follow...