---
showArticleList: false
title: Retrieval
created: 2026-09-24
visible: true
status: in progress
tags: [agents, retrieval]
readability: 3
---

Feeding agents the right slices of large corpora: chunking libraries, parsing pipelines, the two big frameworks, and the patterns built on them.

- [Chonkie](chonkie/index.md) - the MIT chunking library (token, semantic, and neural chunkers) for RAG pipelines, its commercial arm dead and its maker pivoted to Feyn Labs.
- [Knowhere](knowhere/index.md) - Ontos AI's structure-preserving document parsing and retrieval pipeline, hosted per page or self-hosted, its self-reported benchmark and near-empty HN footprint attached.
- [LangChain](langchain/index.md) - the largest LLM framework, repositioned in 2026 as an agent engineering platform.
- [LlamaIndex](llamaindex/index.md) - the MIT data framework for retrieval pipelines, now the open arm of LlamaParse.
- [Semantic code search](semantic-code-search/index.md) - retrieval by meaning over embedded chunks, shipped as a workspace index.
- [Tree-sitter chunking](tree-sitter-chunking/index.md) - cutting files along syntax boundaries instead of fixed line counts.

Its members are compared on shared rows in the [Retrieval Feature Matrix](retrieval-feature-matrix/index.md).

## Changes

- 2026-08-24 - Added LangChain.
- 2026-08-24 - Added LlamaIndex.
- 2026-08-24 - Added Semantic code search.
- 2026-08-24 - Added Tree-sitter chunking.
- 2026-09-16 - Added Chonkie.
- 2026-09-20 - Added Knowhere.