llm_wiki vs WeKnora
Desktop app implementing Karpathy's LLM Wiki pattern: an LLM ingests your documents into a persistent, interlinked wiki with a knowledge graph, hybrid search, deep research and an MCP server. — versus — Tencent's enterprise knowledge platform: one set of document bases served three ways, as RAG search, a reasoning agent with sandboxed skills, and a self-maintaining LLM wiki.
Both implement the LLM wiki pattern, where an LLM keeps a persistent wiki over your documents. llm_wiki is a personal desktop app; WeKnora a multi-user server.
| llm_wiki | WeKnora | |
|---|---|---|
| Stars | 21k | 37k |
| Forks | 2.4k | 5.0k |
| Language | TypeScript | Go |
| License | NOASSERTION | NOASSERTION |
| Last activity | 16 days ago | 3 days ago |
| Topics | rag, knowledge-graphs | rag, agents |
| Curated connections | 6 | 5 |
llm_wiki — the curator's take
Pick LLM Wiki if you like Karpathy's 'compile knowledge once instead of re-retrieving it every query' idea but don't want to wire it up yourself: drop in PDFs, Office docs, EPUBs or web clips and an LLM writes and maintains source-traced wiki pages, with Louvain clusters, gap-finding and deep research on top, plus an MCP server and a skill so Claude Code or Codex can query it. It's a personal, single-user desktop app — not a team knowledge service (see arkon) — and every ingest spends LLM tokens on a two-step analyse-then-write pass, so big corpora cost real money. Licence is GPL-3.0 (the GitHub API reports NOASSERTION): fine to use, copyleft if you fork and redistribute.
WeKnora — the curator's take
Use it for a self-hosted team knowledge base with real operations: RBAC, audit logs, auto-sync from Feishu, Confluence, Notion and GitLab, and IM bots (WeCom, Feishu, Slack). Strongest inside the Chinese enterprise stack. Skip it if you want a library to embed rather than a platform to run, or for a single user's notes. The license is custom (NOASSERTION on GitHub), so check it before commercial use.