Unverified50% confidenceOpinionExact time
For small, well-organized internal corpora (a few hundred files rather than millions), plain Markdown with grep search is faster and easier to understand than building retrieval infrastructure.
1
Sources
50%
Confidence
Long-term
Relevance
10/14/2026
First Seen
Sources
Related Entities
Related Claims
Unverified在文件数量不过千的个人知识库场景下，结构化Markdown索引比向量数据库检索更稳定、可解释性更强74% similarUnverifiedgrep excels at fast, fuzzy, exploratory searches, while LSP excels at precise, semantics-aware queries; the two serve different purposes.71% similarUnverifiedThe biggest bottleneck when scaling context is historical tool outputs, including text chunks from past retrievals, tool call and result pairs, and file search records.67% similarUnverified结构化的AGENTS.md文件比分散在角落里的注释更有效，因为更容易被RAG管道检索命中66% similarUnverifiedParagraph-level retrieval splits documents into chunks of around a few hundred characters, each chunk being vectorized separately and indexed, in order to improve recall precision and directly locate specific content.65% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1025064API
curl https://kongchang.com/api/v1/knowledge/claims/1025064MCP
get_claim(id=1025064)