Self-hosted, OpenAI-compatible RAG API + MCP server that plugs local knowledge into existing LLM clients.
Latest release v1.2.0 · 13 Oct 2026
5 files for GitHub Copilot: ragtime debugging.instructions.md, ragtime frontend.instructions.md, ragtime ragtime.instructions.md, ragtime testing.instructions.md and 1 more — 11,079 tokens loaded in every session.
.github/instructions/debugging.instructions.md A 1,084 tok .github/instructions/frontend.instructions.md A 2,790 tok .github/instructions/ragtime.instructions.md A 1,536 tok .github/instructions/testing.instructions.md A 644 tok .github/instructions/userspace-spec.instructions.md C 5,025 tok These files are mattv8/ragtime's own configuration — they tell GitHub Copilot 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.