LLM workflowsOpen AGENTS.mdRecipesInteractive demos
Built for coding agents
Point your agent at AGENTS.md and the JSON recipes. Discover once; query forever.
Step 1
User prompt
Natural language — “what breaks if I change checkout?”
Step 2
Tool call
Agent runs rg-build -f json … instead of dumping files into context.
Step 3
Graph facts
schema_version JSON — blast, GQL rows, semantic hits, CPG mutations.
Step 4
Reason + edit
LLM plans the change from facts, then verifies with check when needed.
Minimal agent loop
export REPO=/path/to/repo$ rg-build -r "$REPO" discover .$ rg-build -r "$REPO" -f json gql --macro-name all_functions unused | jq '.count'$ rg-build -r "$REPO" -f json blast-radius "ShoppingCartService" --depth 3 \| jq '{score: .metrics.score, callers: .metrics.direct_callers_count}'