CocoIndex Code is an AST-based tool designed to provide continuously updated coding context for AI agents and developers working with codebases. Its core function is to turn code repositories and related data sources—such as meeting notes, pull request reviews, and Slack messages—into live, incrementally processed context that agents can use for reasoning and automation. The platform emphasizes sub-second freshness and minimal incremental processing, ensuring that updates to source code or data are rapidly reflected in the indexed context.
Key features include the generation and maintenance of call graphs, symbol tables, hierarchies, and semantic indexes, all of which are kept current as repositories evolve. CocoIndex Code supports incremental reindexing, meaning only the changes (deltas) are processed when source files are edited, which allows for efficient scaling to large codebases. The tool enables semantic search, letting users find functions, patterns, and intent beyond simple string matches. It also provides a global architectural view, helping users spot duplicates and understand the structure of entire repositories. The call graph feature allows for tracing callers and callees, offering insight into the impact of code changes before they are shipped, which is useful for code review and quality assurance.
The platform is designed to integrate with coding and code-review agents, supplying them with structured, always-fresh data rather than raw text. It can also process meeting notes into knowledge graphs, extracting people, topics, decisions, and action items for agent queries. CocoIndex Code supports multi-repository summaries, where it can extract structure and generate LLM-based summaries across multiple Git repositories, refreshing these summaries with every push.
CocoIndex Code is delivered as a framework that can be cloned and configured with various data sources, supporting real-time indexing and integration with different storage backends. It is aimed at engineers and organizations building or operating AI-powered agents that require up-to-date, explainable data pipelines.
CocoIndex Code is a Developer Tools product. It focuses on finding relevant code snippets and understanding codebases efficiently using semantic search. CocoIndex Code is an open-source project aimed at developers. The project is open source (Apache-2.0). The product ships for the web and the command line, and it can be self-hosted.
Behind CocoIndex Code is CocoIndex Open Source Maintainers, and the product first shipped in 2026. The project is developed in the open on GitHub with 1.9k stars and 75 commits in the last 90 days. Among its 8 catalogued features are semantic code search, AST-based analysis, and CLI tool. The interface is available in 9 languages, including English, German, and Spanish. It exposes integrations via an MCP server.
Latest indexed changes and source events
Other apps tracked under the same category.
