Build a knowledge base with Claude Code — using your existing subscription

Lattice turns your markdown documentation into a searchable knowledge graph. Unlike other GraphRAG tools that require separate LLM APIs, Lattice uses Claude Code for entity extraction — so you're already paying for it.

/research "knowledge graphs"   # Find existing docs, create new research, auto-sync
lattice search "your query"    # Semantic search your knowledge base

That's it. One command to build a knowledge base.

• Claude Code (you probably already have it)
• Voyage AI API key (get one here - embeddings only, ~$0.01/1M tokens)

bun add -g @zabaca/lattice          # Install CLI
export VOYAGE_API_KEY=your-key-here  # Set API key
lattice init --global                # Install Claude Code commands

That's it. No Docker. No containers. DuckDB is embedded.

claude                        # Launch Claude Code
/research "your topic"        # Find or create documentation (auto-syncs)
lattice search "your query"   # Semantic search

The /research command will:

• Search your existing docs for related content
• Ask if you need new research
• Create organized documentation with AI assistance
• Automatically sync to the knowledge graph

The /research command provides an AI-assisted research workflow.

/research "semantic search"

Claude will:

1. Search your docs using semantic similarity
2. Read and summarize relevant findings
3. Ask if existing research answers your question

/research "new topic to explore"

If no existing docs match, Claude will:

1. Perform web research
2. Create a new topic directory (~/.lattice/docs/new-topic/)
3. Generate README.md index and research document
4. Automatically sync to the knowledge graph

Track research questions and link them to answers in your knowledge base.

lattice question:add "How does X work?"           # Track a question
lattice question:link "How does X work?" --doc ~/.lattice/docs/topic/answer.md  # Link to answer
lattice question:unanswered                       # Find unanswered questions

Questions become searchable entities with ANSWERED_BY relationships to documents.

Share your research with others via encrypted peer-to-peer transfer.

# Sender
lattice share duckdb                    # Share the duckdb topic
# Output: 5443-madam-bandit-river

# Receiver
lattice receive 5443-madam-bandit-river # Receive and auto-sync to graph

Uses croc for secure transfers. The binary is auto-downloaded on first use.

Generate a browsable documentation site from your knowledge base.

lattice site              # Build and serve at localhost:4321
lattice site --build      # Build only (output to .lattice/site/)

Uses Astro with a clean documentation theme. Your entities and relationships become navigable pages.

The Lattice CLI runs behind the scenes. You typically won't use it directly — the Claude Code slash commands handle everything.

lattice init              # Install to .claude/commands/ (current project)
lattice init --global     # Install to ~/.claude/commands/ (all projects)

lattice sync [paths...]         # Sync specified paths or current directory
lattice sync --force            # Force re-sync (rebuilds entire graph)
lattice sync --dry-run          # Preview changes without applying

lattice status                  # Show new/changed documents

lattice search "query"          # Search all entity types
lattice search "query" -l Tool  # Filter by label

lattice sql "SELECT * FROM nodes LIMIT 10"
lattice sql "SELECT label, COUNT(*) FROM nodes GROUP BY label"

lattice rels "TypeScript"       # Show all relationships for an entity

lattice ontology                # Show entity types and relationship types

lattice site                    # Build and serve at localhost:4321
lattice site --build            # Build only (output to .lattice/site/)

lattice share <path>            # Share docs, outputs a receive code

lattice receive <code>          # Receive and auto-sync to graph
lattice receive <code> --no-sync  # Receive without syncing

lattice question:add "question"                    # Create question entity
lattice question:add "question" --answered-by path # Create and link

lattice question:link "question" --doc path

lattice question:unanswered

Lattice stores its knowledge graph in ~/.lattice/lattice.duckdb. This file contains:

• All extracted entities (nodes)
• Relationships between entities
• Vector embeddings for semantic search

You can back up, copy, or version control this file like any other.

-- Nodes (entities)
CREATE TABLE nodes (
    label VARCHAR NOT NULL,      -- Entity type: Document, Technology, etc.
    name VARCHAR NOT NULL,       -- Unique identifier
    properties JSON,             -- Additional metadata
    embedding FLOAT[512],        -- Vector for semantic search
    PRIMARY KEY(label, name)
);

-- Relationships
CREATE TABLE relationships (
    source_label VARCHAR NOT NULL,
    source_name VARCHAR NOT NULL,
    relation_type VARCHAR NOT NULL,
    target_label VARCHAR NOT NULL,
    target_name VARCHAR NOT NULL,
    properties JSON,
    PRIMARY KEY(source_label, source_name, relation_type, target_label, target_name)
);

git clone https://github.com/Zabaca/lattice.git
cd lattice
bun install
cp .env.example .env

bun run dev              # Development mode
bun test                 # Run tests
bun run build            # Build for production

import { NestFactory } from '@nestjs/core';
import { AppModule } from '@zabaca/lattice';

async function main() {
  const app = await NestFactory.createApplicationContext(AppModule);
  const syncService = app.get(SyncService);

  const result = await syncService.sync({
    paths: ['./docs'],
    force: false
  });

  console.log(`Synced ${result.added} new documents`);

  await app.close();
}

Contributions are welcome! Please feel free to submit a Pull Request.

MIT License - see LICENSE for details.

Built with DuckDB, Voyage AI, and Claude Code