Vault-Centric Compilers and Local Managers
Compilers and management layers tailored specifically for personal markdown vaults (Obsidian, Logseq, MkDocs), featuring interactive terminal review wizards, visual graphs, and vault curation engines.
browzy.aigithub.comAn open-source, self-hosted TypeScript knowledge compiler designed to ingest messy digital data streams and compile them into a structured, self-organizing personal memory layer.
jackwu321/Quant_LLM_Wikigithub.comA specialized implementation of the Karpathy LLM Wiki pattern engineered specifically for quantitative finance research. Features multi-source ingestion of trading PDFs, web links, and financial articles into a local Markdown vault using strict domain-specific metadata schemas, inline LaTeX mathematical formatting, and a dedicated "Rethink Layer" for continuous strategy auditing, validation tracking, and post-mortem charting.
LLM Wiki Newsroom (alfadur7)github.comA multi-agent, local-first knowledge base framework implementing Karpathy's LLM Wiki pattern as a five-role newsroom. Features separated authoring and review gates, an interactive D3 knowledge graph, cascading note updates, and a self-improving meta-loop where recurrent mistakes refine the system's own authoring rules.
LLM Wikidgithub.comA multi-phase shell compilation framework for Obsidian vaults that implements automatic inbound media extraction, programmatic categorization routing, and mandatory cognitive bias countermeasure modules.
llm-wiki (hellohejinyu)github.comA Node.js-based CLI personal wiki manager. Scaffolds directories into a structured Markdown wiki, processes raw files into interlinked pages using LLM patches, runs questions through a multi-step ReAct agent, and performs static and semantic linting checks (orphans, dead links, contradictions) with automated stub creation.
LLM-Wiki (NiharShrotri)github.comA Python-based CLI knowledge compiler and local web server implementing the Karpathy LLM Wiki pattern on Ollama (Qwen3-14B). Features automated structure ingestion, hybrid text retrieval (BM25 + vectors + reranking via QMD), a streaming Web UI chat interface, and a D3 force-directed knowledge graph visualization.
llm-wiki-starter (eleven-net-cn)github.comA one-command CLI scaffolding tool and agent skill implementing the Karpathy LLM Wiki pattern. Generates a three-layer directory structure (raw/, wiki/, templates/), pre-configures AGENTS.md and CLAUDE.md guidelines, auto-configures 17 essential Obsidian plugins and themes, and installs companion agent skills.
llmwiki (Lucas Astorian)github.comAn open-source Python engine and local web dashboard that indexes directories into a local SQLite repository, serving a specialized MCP adapter to automate Claude-driven wiki compilation and citation tracking.
obsidian-llm-wiki-local (kytmanov)github.comAn open-source, 100% local CLI compiler (succeeded by Synto) that parses Markdown notes using Ollama to extract entities and automatically compile interlinked Obsidian concept wikis.
Oh My Wikipypi.orgA local-first Python package and CLI utility implementing an interactive management layer for Karpathy-style markdown vaults. It pairs a multi-vault SQLite registry with an interactive Socratic terminal wizard that prompts users to evaluate, refine, or reject agentic knowledge extractions before they are written to disk, preventing unstructured data corruption.
quicky-wiki (anzal1)github.comA Node.js-based CLI and dashboard server that compiles document vaults into confidence-scored, self-maintaining LLM wikis. Automatically extracts facts, detects contradictions, structures timelines, and serves an interactive D3 force-directed knowledge graph and Ask Wiki chat interface.
Tome (chicken-noodle-chris)github.comA Claude Code plugin and CLI utility that enforces vault directory contracts, runs linting, and serves Quartz views.
vault-curatorgithub.comA local, Python-based knowledge system compiler that transforms massive Markdown vaults into self-organizing environments for AI agents. It processes flat-file directories to automatically inject structural frontmatter metadata, compute semantic connection links, and compile persistent Maps of Content (MOCs) to optimize downstream agent retrieval.
