Introducing WarpGrep, a fast context subagent that improves coding agent performance. WarpGrep speeds up coding tasks 40% and reduces context rot by 70% on long horizon tasks by treating context retrieval as its own RL trained system. Inspired by Cognition’s SWE-Grep - we’re opening access to Claude Code, Codex, OpenCode or any coding agent via MCP (or through our SDK)

Morph is Fast Apply applies code edits FAST - 1600+ tokens/sec. It takes original files and LLM-generated code snippets, merges them for clean, ready-to-use code. Patches and full rewrites = poor UX Morph is the "write" layer for AI agents.