Show HN: Plain-text code memory that beats a graph DB at x218 fewer tokens
Category: ai-ml
Tags: ai-memory, code-analysis, plain-text, local-first, llm-tools
Score: 7.5/10 (Innovation: 7, Technical: 8, Documentation: 8, Utility: 7)
DaiDocs introduces a plain-text memory format (.dai for documents/history, .cai for code graphs) that enables AI assistants to store and retrieve context efficiently, beating graph databases with dramatically fewer tokens. It combines a deterministic code graph via tree-sitter with an LLM-based observer for documents, all stored locally as grep-able files. The project provides rigorous benchmarks and a router to direct queries to the appropriate memory tier.
Target audience: backend developers, AI engineers, devops
Repository: https://daidocs.com/results-code.html · Python · Apache-2.0 · 53 stars
View on Hacker News