docir compiles Git-backed Markdown documentation into a verifiable, read-optimized index for AI coding agents. It supports documentation-as-code workflows, semantic retrieval, and Model Context Protocol integrations for agent access.
In the RAG, search & retrieval space, docir takes a focused approach. It focuses on making version-controlled Markdown documentation searchable and reliably accessible to AI coding agents. It is built as an open-source project for developers building AI coding agents and documentation systems. docir is open source under the MIT license. docir is available on the command line, and it can be self-hosted.
It is developed by l0kifs, and it first shipped in 2026. Development happens publicly on GitHub with 167 commits in the last 90 days. Among its 6 catalogued features are git-backed indexing, markdown compilation, and semantic search. It exposes integrations via an MCP server.
Summary written by a language model from the project’s public pages.
What PulseGate has recorded for this listing
Same category — not a similarity match