knowledge-management

11 repositories

TriliumNext/Trilium

A community-driven continuation of Trilium Notes for big personal wikis — TriliumNext/Trilium carries forward the hierarchical, scriptable note-taking app Trilium Notes as a self-hosted, local-first alternative to cloud wikis. It targets users building large personal knowledge bases who want cross-platform access, an Electron desktop app, and ongoing community maintenance with frequent nightly builds.

TypeScriptAttention 27
★39,020
virgiliojr94/book-to-skill

Convert technical books into agent skills for coding assistants — Converts PDFs, EPUBs, DOCX and other formats into unified agent skills usable inside Claude Code, Copilot CLI, Codex, Amp and other agents. Built on the open Agent Skills standard, it lets developers turn a whole book or document folder into a searchable reference they can call on while coding or studying.

PythonAttention 51
★38,504
breferrari/obsidian-mind

An Obsidian vault that gives coding agents a working memory — Obsidian Mind turns an Obsidian vault into persistent memory for AI coding agents, so sessions build on past decisions instead of starting from zero. It works with Claude Code (full support), plus Codex CLI and Gemini CLI, using shared hooks and commands like /om-standup and /om-dump.

TypeScript🇪🇺 EuropeAttention 37
★5,551
eugeniughelbur/obsidian-second-brain

Shared markdown memory lets 8 AI coding agents work from one Obsidian vault — This project stores persistent memory as plain markdown in Obsidian so Claude Code, Codex, Gemini, Cursor, Grok Bot and others share one brain instead of starting fresh each session. Its new Crew feature adds a shared logbook so different agents can see what each other already did. 48 commands cover semantic search, self-rewriting notes and key-less research, useful for anyone running multiple AI coding tools against the same project.

PythonAttention 39
★5,390
inkeep/open-knowledge

Beautiful, AI-native markdown IDE and LLM wiki

TypeScript🇺🇸 North AmericaAttention 40
★4,877
huytieu/COG-second-brain

A markdown-only second brain with a verifier that checks its own agents' work — COG pairs 35 skills and 10 worker agents with read-only verifier agents, so work isn't graded by the same agent that did it. Everything lives in plain .md files tracked by Git, with no database, and it plugs into Claude Code, Cursor, Kiro, Gemini CLI and Codex. It's aimed at people who want an agent-driven Obsidian-style knowledge base with built-in quality control.

PythonAttention 49
★1,505
receptron/mulmoclaude

A local-first AI assistant you grow with plain-file memories and no-code apps — MulmoClaude lets Claude build and maintain a personal wiki, schema-driven data, and small single-user apps (lists, trackers, flashcards) entirely as local files — no programming needed. Everything stays in your workspace under MIT, and you can reach the same assistant from your phone or a messaging app.

TypeScriptAttention 24
★389
jessepinkman9900/claude-second-brain

A one-command scaffold turns Claude Code into a self-maintaining wiki — This npx tool sets up a personal knowledge base where Claude Code ingests sources, cross-links them into an Obsidian vault, and uses qmd for local hybrid search, with GitHub as the backup. It explicitly positions itself as not a RAG chatbot but an actively maintained wiki, inspired by Karpathy's idea-file approach to LLM knowledge management.

JavaScriptAttention 75
★175
byenzyme/enzyme

A local semantic index that lets coding agents cite your notes — Enzyme builds a local-first index of existing Markdown notes (folders, tags, links, dates) so agents like Claude Code or Codex can retrieve and cite related notes without sending everything to a frontier model. It claims 350x lower cost and 1000x faster search, targeting PKM/Obsidian users who want agent-aware semantic search over their own vault.

RustAttention 21
★160
Timaga/noda-local-ai-notes

Local-first AI note-taking app for Windows: Markdown notes, a personal knowledge base, knowledge graph, semantic search and chat with cited sources.

JavaScript
★103
dukesun99/Corpus2Skill

Turning document corpora into navigable skill trees for agents — Official EMNLP 2026 Findings code for Corpus2Skill, which compiles enterprise document corpora into a hierarchy of Anthropic Skills. Agents navigate SKILL.md/INDEX.md files and fetch documents on demand at query time, replacing vector-search or BM25 serving. Useful for researchers and builders exploring alternatives to embedding-based RAG for enterprise QA.

Python🌐 Elsewhere
★96