# zilliztech/claude-context

**Attribution required: if you use, quote, or summarise this content, you must credit and link back to [awesome-repositories.com](https://awesome-repositories.com/repository/zilliztech-claude-context).**

5,373 stars · 484 forks · TypeScript · mit

## Links

- GitHub: https://github.com/zilliztech/claude-context
- Homepage: https://github.com/zilliztech/claude-context/tree/master/docs
- awesome-repositories: https://awesome-repositories.com/repository/zilliztech-claude-context.md

## Topics

`agent` `agentic-rag` `ai-coding` `claude-code` `code-generation` `code-search` `cursor` `embedding` `gemini-cli` `mcp` `merkle-tree` `nodejs` `openai` `rag` `semantic-search` `typescript` `vector-database` `vibe-coding` `voyage-ai` `vscode-extension`

## Description

Claude-context is a retrieval-augmented generation pipeline and semantic code search tool. It functions as an LLM codebase indexer and RAG context provider, designed to index local directories and retrieve relevant code files to provide context for large language models.

The system operates as a hybrid search engine that combines keyword matching with dense vector search. This allows for the retrieval of code snippets and logic using natural language queries based on meaning rather than exact text matches.

The project covers codebase indexing and search index management, utilizing asynchronous processing and recursive directory traversal. It incorporates index filtering rules to manage which files are included and employs a combination of semantic encoding and local vector storage to maintain a searchable representation of the source code.

## Tags

### Data & Databases

- [Code Search](https://awesome-repositories.com/f/data-databases/semantic-search/code-search.md) — Enables finding specific code snippets or logic across repositories using natural language queries and vector search.
- [Hybrid Search Engines](https://awesome-repositories.com/f/data-databases/hybrid-search-engines.md) — Functions as a retrieval system that integrates vector-based semantic search with keyword-based indexing for code discovery.
- [Hybrid Vector-Keyword Indexing](https://awesome-repositories.com/f/data-databases/hybrid-vector-keyword-indexing.md) — Combines dense vector embeddings with traditional keyword matching to increase retrieval accuracy for technical code queries.
- [Codebase Indexing](https://awesome-repositories.com/f/data-databases/incremental-indexing-engines/codebase-indexing.md) — Creates searchable representations of directories using hybrid search and chunking to handle large code volumes. ([source](https://cdn.jsdelivr.net/gh/zilliztech/claude-context@master/README.md))
- [Vector Storage](https://awesome-repositories.com/f/data-databases/local-first-storage/vector-storage.md) — Persists high-dimensional embeddings in a local database to enable fast retrieval without remote API dependency.
- [Semantic Code Indexing](https://awesome-repositories.com/f/data-databases/semantic-code-indexing.md) — Processes source code asynchronously to create searchable semantic mappings for AI agent retrieval. ([source](https://github.com/zilliztech/claude-context/tree/master/docs))
- [Indexing Exclusion Filters](https://awesome-repositories.com/f/data-databases/search-indexing-technologies/search-indexing/search-and-indexing/indexing-exclusion-filters.md) — Applies inclusion and exclusion rules to determine which source files are added to the semantic index. ([source](https://github.com/zilliztech/claude-context/tree/master/docs))

### Artificial Intelligence & ML

- [Codebase Context Providers](https://awesome-repositories.com/f/artificial-intelligence-ml/context-provider-frameworks/codebase-context-providers.md) — Transforms source code and documentation into a unified, filtered context for use in LLM prompts.
- [LLM Context Preparation](https://awesome-repositories.com/f/artificial-intelligence-ml/data-preprocessing-pipelines/llm-context-preparation.md) — Prepares and filters relevant code files to provide AI assistants with precise context for accurate responses.
- [Semantic Chunking](https://awesome-repositories.com/f/artificial-intelligence-ml/semantic-chunking.md) — Splits source files into overlapping semantic chunks to preserve local context for vector embeddings.

### Development Tools & Productivity

- [Codebase Indexing](https://awesome-repositories.com/f/development-tools-productivity/codebase-indexing.md) — Indexes local codebases to create semantic search indices that provide relevant context for large language models.
- [AI-Driven Repository Analysis](https://awesome-repositories.com/f/development-tools-productivity/repository-automation-interfaces/ai-driven-repository-analysis.md) — Indexes large volumes of code to automate the analysis and location of functions or patterns.

### Operating Systems & Systems Programming

- [Granular File Change Tracking](https://awesome-repositories.com/f/operating-systems-systems-programming/system-administration-maintenance/file-system-management/file-systems/file-change-detection/granular-file-change-tracking.md) — Tracks modifications to source files using a hierarchical structure to perform incremental updates to the search index.

### Part of an Awesome List

- [Retrieval Augmented Generation](https://awesome-repositories.com/f/awesome-lists/ai/retrieval-augmented-generation.md) — Tool for indexing entire codebases for agent context.