Lat.md: Agent Lattice: a knowledge graph for your codebase, written in Markdown

A knowledge graph for your codebase, written in markdown.

AGENTS.md doesn't scale. A single flat file can describe a small project, but as a codebase grows, maintaining one monolithic document becomes impractical. Key design decisions get buried, business logic goes undocumented, and agents hallucinate context they should be able to look up.

Compress the knowledge about your program domain into a graph — a set of interconnected markdown files that live in a lat.md/ directory at the root of your project. Sections link to each other with [[wiki links]], source files link back with // @lat: comments, and lat check ensures nothing drifts out of sync.

The result is a structured knowledge base that:

• Scales— split knowledge across as many files and sections as you need
• Cross-references— wiki links ([[cli#search#Indexing]]) connect concepts into a navigable graph
• Stays in sync—lat check validates that all links resolve and that required code references exist
• Is searchable— exact, fuzzy, and semantic (vector) search across all sections
• Works for humans and machines— readable in any editor (or Obsidian), queryable by agents via the lat CLI

npm install -g lat.md

Then run lat init in the repo you want to use lat in.

Run lat init to scaffold a lat.md/ directory, then write markdown files describing your architecture, business logic, test specs — whatever matters. Link between sections using [[file#Section#Subsection]] syntax. Link to source code symbols with [[src/auth.ts#validateToken]]. Annotate source code with // @lat: [[section-id]] (or # @lat: [[section-id]] in Python) comments to tie implementation back to concepts.

my-project/
├── lat.md/
│ ├── architecture.md # system design, key decisions
│ ├── auth.md # authentication & authorization logic
│ └── tests.md # test specs (require-code-mention: true)
├── src/
│ ├── auth.ts # // @lat: [[auth#OAuth Flow]]
│ └── server.ts # // @lat: [[architecture#Request Pipeline]]
└── ...

lat init # scaffold a lat.md/ directory
lat check # validate all wiki links and code refs
lat locate "OAuth Flow" # find sections by name (exact, fuzzy)
lat section "auth#OAuth Flow" # show a section with its links and refs
lat refs "auth#OAuth Flow" # find what references a section
lat search "how do we auth?" # semantic search via embeddings
lat expand "fix [[OAuth Flow]]" # expand [[refs]] in a prompt for agents
lat mcp # start MCP server for editor integration

Semantic search (lat search) requires an OpenAI (sk-...) or Vercel AI Gateway (vck_...) API key. The key is resolved in order:

• LAT_LLM_KEY env var — direct value
• LAT_LLM_KEY_FILE env var — path to a file containing the key
• LAT_LLM_KEY_HELPER env var — shell command that prints the key (10s timeout)
• Config file — saved by lat init. Run lat config to see its location.

Requires Node.js 22+ and pnpm.

pnpm install
pnpm build
pnpm test