import { morph } from 'morph'Intelligent code search with WarpGrep
"WarpGrep lets us search giant codebases in seconds without blowing context windows."
"We switched from embeddings to WarpGrep—faster searches, simpler infra."
"WarpGrep keeps retrieval fast, precise, and easy to deploy across our codebase."
Subagent-powered search
WarpGrep operates in its own context window. Your main agent receives only relevant results.
const result = await morph.warpGrep.execute({ query: 'Find where billing invoices are emailed', repoRoot: './my-project',}) // Clean results, no context pollutionconsole.log(result.contexts) // Relevant code onlyconsole.log(result.summary) // Search findingsSearch codebases without
blowing context
Isolated context window
WarpGrep is a specialized AI model that searches your codebase in a separate context window. Instead of your main agent running grep and accumulating context, WarpGrep does intelligent multi-step searching and returns clean results.
import { morph } from 'morph' // WarpGrep searches in isolationconst result = await morph.warpGrep.execute({ query: 'Find where billing invoices are generated', repoRoot: '.', excludes: ['node_modules', '.git'], includes: ['src/**/*.ts']}) // Returns only relevant code sectionsfor (const ctx of result.contexts) { console.log(ctx.file, ctx.content)}Multi-turn reasoning
Your agent calls WarpGrep with a natural language query. WarpGrep reasons about what to search, runs up to 24 tool calls (grep, read, list_dir) across 4 turns in under 6 seconds, and returns the relevant code sections.
Best-in-class F1 score
WarpGrep achieves 0.73 F1 in just 3.8 steps—3x fewer than comparable agentic approaches. Deep logic queries show 2x-6x better performance.
Warp Grep achieves 0.73 F1 in just 3.8 steps—3x fewer than comparable agentic approaches
Built for every deployment pattern
Parallel breadth-first search
