# cocoindex-io/cocoindex-code **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/cocoindex-io-cocoindex-code).** _How this analysis was created: the description and tags below were written by an AI model that read this project's README and public documentation pages; stars, license and language come straight from the GitHub API. The model does not read the source code._ 1,962 stars · 153 forks · Python · Apache-2.0 ## Links - GitHub: https://github.com/cocoindex-io/cocoindex-code - Homepage: https://cocoindex.io/ - awesome-repositories: https://awesome-repositories.com/repository/cocoindex-io-cocoindex-code.md ## Topics `agents` `ast` `cocoindex` `code-search` `coding-agent` `context-engineering` `indexing` `mcp` `python` `tree-sitter` ## Description Cocoindex is a command-line code search engine and indexing tool that combines abstract syntax tree pattern matching and semantic vector embeddings for precise code discovery. It functions locally and integrates with AI coding assistants to automatically retrieve necessary codebase context through standardized communication protocols and persistent background daemon services. The platform employs an asymmetric embedding architecture that generates vector representations using separate parameters for document indexing and search queries. It supports incremental index maintenance by tracking file deltas, alongside automated codebase summarization, knowledge graph extraction from unstructured notes, and call graph tracing to evaluate the impact of proposed modifications. Data transformation pipelines are defined using standard programming scripts, supported by hierarchical project discovery, embedding provider selection, containerized deployment, and traffic management controls for rate limits and batching. ## Tags ### Development Tools & Productivity - [Abstract Syntax Tree Search Tools](https://awesome-repositories.com/f/development-tools-productivity/code-search-tools/abstract-syntax-tree-search-tools.md) — Matches source code by syntax tree patterns locally without requiring a pre-built index or embedding model. - [AST Pattern Matching](https://awesome-repositories.com/f/development-tools-productivity/code-quality-analysis/static-analysis-engines/static-analysis-tools/ast-pattern-matching.md) — Searches codebases by syntax tree patterns rather than literal text so formatting differences do not affect matches. - [Codebase Indexing](https://awesome-repositories.com/f/development-tools-productivity/codebase-indexing.md) — Initializes repositories, builds and updates indices with streaming progress, checks health status, and resets database storage. ([source](https://github.com/cocoindex-io/cocoindex-code/blob/main/README.md)) ### Artificial Intelligence & ML - [Code Context Servers](https://awesome-repositories.com/f/artificial-intelligence-ml/agentic-systems-frameworks/integration-deployment/ai-agent-tooling/coding-agents/code-context-servers.md) — Connects directly to AI coding assistants through Model Context Protocol servers so agents retrieve necessary codebase context automatically. ([source](https://github.com/cocoindex-io/cocoindex-code/blob/main/README.md)) - [Model Context Protocol Integrations](https://awesome-repositories.com/f/artificial-intelligence-ml/ai-assistant-integrations/model-context-protocol-integrations.md) — Connects code search engines to AI assistants through standardized protocols so agents automatically retrieve necessary codebase context. - [Model Context Protocol Servers](https://awesome-repositories.com/f/artificial-intelligence-ml/model-context-protocol-servers.md) — Publishes search and indexing capabilities over standard input and output to integrate directly with compatible coding assistants. ([source](https://github.com/cocoindex-io/cocoindex-code#readme)) - [Automated Codebase Summarizers](https://awesome-repositories.com/f/artificial-intelligence-ml/automated-codebase-summarizers.md) — Extracts and aggregates structure across multiple repositories to produce synchronized summaries that refresh on push. ([source](https://cocoindex.io/)) - [Knowledge Graph Extraction](https://awesome-repositories.com/f/artificial-intelligence-ml/knowledge-graph-extraction.md) — Parses unstructured notes to capture people, topics, decisions, and action items into a live queryable graph. ([source](https://cocoindex.io/)) ### Data & Databases - [Incremental Document Indexers](https://awesome-repositories.com/f/data-databases/data-integration-synchronization/local-document-indexing/document-indexing/incremental-document-indexers.md) — Automatically reindexes only changed file deltas or processes added, modified, and deleted items to keep search targets fresh. ([source](https://cocoindex.io/)) - [Codebase Indexing](https://awesome-repositories.com/f/data-databases/incremental-indexing-engines/codebase-indexing.md) — Maintains incremental file indexes that update automatically on every commit to keep search targets fresh without full recomputes. - [Structural Search Indexes](https://awesome-repositories.com/f/data-databases/search-indexing/structural-search-indexes.md) — Searches codebases by matching abstract syntax tree patterns against source files locally without requiring a pre-built index. ([source](https://github.com/cocoindex-io/cocoindex-code#readme)) - [Code Search](https://awesome-repositories.com/f/data-databases/semantic-search/code-search.md) — Finds relevant code snippets across codebases using natural language queries and vector similarity for efficient context retrieval. ([source](https://cocoindex.io/)) - [Semantic Code Search Engines](https://awesome-repositories.com/f/data-databases/semantic-search/semantic-code-search-engines.md) — Provides a command-line code search engine that uses abstract syntax trees and vector embeddings to help coding agents find relevant snippets. - [Python Data Pipeline Frameworks](https://awesome-repositories.com/f/data-databases/python-data-pipeline-frameworks.md) — Builds data transformation pipelines using standard programming scripts from which the engine automatically derives execution graphs. ([source](https://cocoindex.io/)) - [Vector Embedding Indexes](https://awesome-repositories.com/f/data-databases/vector-search/vector-embedding-indexes.md) — Generates vector representations using separate parameters for document indexing and search queries to accommodate specialized model requirements. ([source](https://github.com/cocoindex-io/cocoindex-code/blob/main/CLAUDE.md)) ### Software Engineering & Architecture - [Asymmetric Embedding Architectures](https://awesome-repositories.com/f/software-engineering-architecture/asymmetric-embedding-architectures.md) — Employs an asymmetric embedding architecture generating vector representations using separate parameters for document indexing and search queries. ### System Administration & Monitoring - [Call Graph Tracers](https://awesome-repositories.com/f/system-administration-monitoring/call-graph-tracers.md) — Maps callers and callees across the codebase to evaluate the blast radius of proposed changes before shipping. ([source](https://cocoindex.io/))