Unverified50% confidenceFactExact time
Compared with a pure vector-retrieval knowledge base, the LLM Wiki retains readable, editable written entries rather than fragmented embedding vectors.
1
Sources
50%
Confidence
Long-term
Relevance
10/28/2026
First Seen
Sources
From Bookmarks to Second Brain: Auto-Building a Knowledge Base with Feishu + AI
bilibili不吃辣的Chris10/28/2026
Related Entities
Related Claims
UnverifiedAn LLM Wiki is a type of knowledge base whose core function is to collect and compile scattered materials into structured knowledge and then support question answering through retrieval augmentation.77% similarUnverifiedTowards AI团队采用LLM Wiki方案，将内容切分为块并交叉链接，模型只看一个约450 token的极小索引，按需逐层检索65% similarUnverifiedAndrej Karpathy proposed the LLM Wiki pattern, which uses Markdown pages plus YAML metadata to organize knowledge, allowing humans and AI agents to maintain it together and query it on demand.65% similarUnverifiedThis automated bookkeeping solution can be completed using only Gmail reading and Google Sheets writing, without relying on API keys or large language models (LLMs).61% similarUnverifiedDMOZ (the Open Directory Project) and Yahoo Directory were the primary gateways for internet navigation during the Web 2.0 era, relying on human editorial curation to maintain quality.61% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1107671API
curl https://kongchang.com/api/v1/knowledge/claims/1107671MCP
get_claim(id=1107671)