Agentic Tools

IWE provides CLI commands specifically designed for AI agents and LLM integrations. These tools enable programmatic access to your knowledge graph with structured output formats and relationship-aware retrieval.

Why agentic tools?

AI agents need efficient ways to:

Discover relevant documents without knowing exact names
Retrieve content with appropriate context and relationships
Navigate the knowledge graph following connections
Process output in structured formats (JSON, keys)

Available commands

iwe find

Search and discover documents with fuzzy matching

iwe retrieve

Retrieve documents with graph expansion and context

Typical agent workflow

iwe find "authentication" --roots -f keys

iwe retrieve -k authentication -d 2 -c 1

iwe retrieve -k login-flow -e authentication

Find entry points using iwe find with fuzzy search
Retrieve content with appropriate depth and context
Follow relationships by retrieving linked documents
Exclude known content to avoid duplication

Output formats

Both commands support multiple output formats:

Format	Flag	Use case
Markdown	`-f markdown`	Human-readable output with full content
Keys	`-f keys`	Piping to other commands
JSON	`-f json`	Programmatic processing and parsing

Integration examples

Claude Code / MCP integration

iwe find --roots -f json | jq '.results[].key'

iwe retrieve -k "$KEY" -d 1 -c 1

Building context for LLMs

iwe find "$QUERY" -l 5 -f keys | while read key; do
  iwe retrieve -k "$key" -d 0 -c 0 --dry-run
done

iwe retrieve -k "$SELECTED_KEY" -d 2 -c 1