Blog
Insights on AI code transformation, speculative decoding, and building faster developer tools.
Claude Code MCP: Fix the 2 Things That Kill Your Flow
Stop waiting 15 seconds for edits. Stop searching the same files over and over.
Bringing FastApply Back to Cursor with MCP
How Morph MCP Server restores 10,500 tok/sec edits to Cursor and adds Warp-Grep for better context retrieval
WarpGrep: Fast, Parallel Code Retrieval with RL
How we trained WarpGrep, a fast context model specialized in doing the dirty work of code search, using highly parallel code retrieval that matches frontier coding models while taking 5x less time
Fast Apply Makes Faster Agents
How Morph Fast Apply is our first step building the sub-agent future. Small, specialized models that escape the valley of death.
We Hit 10,500 Tokens/Sec on B200
Technical deep-dive: custom CUDA kernels + speculative execution for 2.3x speedup
What is Morph Fast Apply?
Understanding Morph: The fastest way to apply code updates from AI
Morph Gets Faster: 10,500+ Tokens Per Second
We were already the fastest way to apply AI code edits. Now we're ~35% faster end-to-end compared to search-and-replace.
LLMs Are Bad at Being Forced
The further you push language models from their natural output patterns, the worse they perform. Understanding why reveals fundamental truths about how these systems actually work.
Diffs vs Fast Apply
Why Fast Apply aligns with the bitter lesson by letting models code naturally
Morph ❤️ Continue
How Morph powers lightning-fast code edits in Continue
Why You Should Build Your Own Coding Agents
Public IDEs are built for consumer metrics, not enterprise reliability. Here's why you should build your own.
Morph: Enable Faster Coding Agents
A deep dive into how we get morph to be so fast.
Everything is Model[s]
Why the future of AI isn't one superintelligent model doing everything, but a hierarchy of specialized models—just like human organizations.
Best Practices for Building Coding Agents with Morph
A guide to building coding agents with Morph, including system prompt best practices, tool calling, and debugging strategies.
How Cursor Apply Works
An analysis of Cursor's breakthrough in achieving 1000 tokens per second for code edits through specialized models and inference methods.