Skip to main content

Get your API key

Sign up and start building in 30 seconds

Fast Apply

Code merging at 10,500 tok/s, 98% accuracy

WarpGrep

RL-trained code search subagent, #1 on SWE-Bench Pro

Compact

Drop filler from chat history at 33,000 tok/s

MCP Integration

Drop into Claude Code, Cursor, Codex

What is Morph?

Specialized models for the mechanical parts of coding agents — file editing, code search, and context compression. OpenAI-compatible API, drop-in with any model or framework. Fast Apply — merges edit snippets into files at 10,500 tok/s with 98% accuracy. Your agent describes changes; Fast Apply produces the merged file. WarpGrep — RL-trained search subagent that runs in its own context, issues 8 parallel tool calls per turn, and finds code in ~3.8 steps. Returns precise file/line-range spans. Paired with Opus, Codex, or MiniMax, it reaches #1 on SWE-Bench Pro — 15.6% cheaper and 28% faster. Compact — shrinks chat history and code context at 33,000 tok/s. 1M token context window. Every surviving line is byte-for-byte identical to the original — no rewriting, no paraphrasing. 50-70% reduction.

How It Works

File edits: Your agent outputs a lazy edit snippet → call Fast Apply to merge it → write the result. Code search: Your agent needs context → call WarpGrep with a natural language query → get back ranked file/line-range spans. Context compression: Chat history growing → call Compact with a relevance query → get back shorter history with filler removed.

Performance

SpeedAccuracy
Fast Apply10,500 tok/s98%
Compact33,000 tok/sverbatim output

Next Steps

Fast Apply Quickstart

Sub-second code merging

WarpGrep Guide

Isolated code search that protects your model’s context

Compact Guide

Compress chat history and code context

MCP Integration

Plug into Claude Code, Cursor, or Codex

Morph SDK

Full toolkit: Fast Apply, WarpGrep, Compact, context management

API Playground

Test with live examples

Enterprise

Dedicated instances, self-hosted deployments, and zero data retention. 99.9% uptime SLA, SOC2, SSO.

Talk to Sales

Custom deployments and volume pricing