Productivity · Web app
Ars Umbris
Local-first IDE and framework for building typed, agentic knowledge graphs
Ars Umbris is an open-source, local-first workspace and framework for structuring personal or company knowledge in plain files. It adds YAML-based typing and diagnostics to Markdown documents, providing an interactive graph and MCP-compatible harness for AI agents to navigate and update your notes.
What it's for
- Build a structured company or personal knowledge base that AI agents can navigate
- Define custom schemas and validation rules for Markdown notes
- Connect coding agents like Claude Code to a typed local note graph via MCP
- Inspect relationships, broken links, and metadata diagnostics across linked files
Features
- au-engine: Live typed graph that indexes files, resolves references, and catches structural errors
- au-host: Malleable IDE interface with customizable projections, graph views, and editors
- au-mcp: Agent meta-harness offering typed tools, profiles, and Claude Code adapters
- YAML-based note schemas supporting validation constraints and custom fields
- Interactive graph visualization with note previews and backlink tracking
- Local-first architecture that runs entirely on plain local files
Pricing
Open source. Free and open source on GitHub
Details
- Type
- Web app
- Category
- Productivity
- Topic
- Knowledge Management
- Open source
- Yes
- Platforms
- macOS, Linux, Windows, Self-hosted
- For
- Developers, researchers, and technical knowledge workers structuring documentation for AI agents
- Alternative to
- Obsidian, Logseq, Anytype
- Tags
- knowledge graph, pkm, agents, mcp, markdown, local first
Why it was saved
- @arscontexta: A real product embodying the article's thesis: browse a note graph, hover nodes for note previews, search notes and chat with an agent about them ('Ask about your notes…').
Compare
Related
Connected workspace for notes, docs, databases, and AI automation.
A workflow for using LLMs to compile and maintain personal wikis
Ad-free platform for saving, organizing, and connecting ideas into channels
Architecture framework for building an LLM-maintained markdown wiki that compounds knowledge
A design pattern for building LLM-maintained personal knowledge bases in markdown
Turn Twitter bookmarks into a searchable AI knowledge base with citations
Updated