OpenCodeRAG is a RAG (Retrieval-Augmented Generation) plugin for semantic code search powered by locally-hosted embedding models. It features a seamless integration with OpenCode and other AI tools via MCP and offers a CLI interface for external usage. It offers hybrid search, image description, persistent memory and local decision model usage.
Latest release v2.13.3 — Version v2.13.3 · 4 Nov 2026
1 file for Codex and OpenCode: opencode-rag — 8,568 tokens loaded in every session.
AGENTS.md C 8,568 tok These files are MrDoe/OpenCodeRAG's own configuration — they tell Codex and OpenCode how to work on this repository, so they are not mods to install elsewhere. Copy one as a starting point and replace the parts that are about this project.