Morph @morphllm

The Fastest, Flawless AI Code Edits. Better coding agents in 8 lines. 10,500 tok/sec on NVIDIA. https://t.co/6R3uBeyZ10 | https://t.co/dBQjovGya3 morphllm.com San Francisco, CA Joined May 2025

Tweets

157
Followers

441
Following

112
Likes

417

Morph @morphllm

6 days ago

the latency of most legit Morph requests is now faster than throwing a model not found error when the model name is invalid

0 0 1 280 0

Morph @morphllm

7 days ago

Morph fast apply at pass 1: 98% Search and replace takes 40% longer on average

Aiden Bai @aidenybai

a week ago

Morph fast apply at pass 1: 98% Search and replace takes 40% longer on average

15 1 192 18K 8

Download Image

0 0 3 318 0

Morph @morphllm

a week ago

codegen is the defacto non text way models will express themselves

0 0 2 170 0

Morph @morphllm

a week ago

Morph is accelerating faster than any inference engine in history. One month ago: 4,200 tokens per second. Today: 10,000 tokens per second. This is just the beginning

1 0 5 256 0

Let’s be clear. apply() loops and diff timeouts are not solutions. They’re bandaids on a broken foundation. You’ve seen the screenshots: “Thought for 1s. Edit failed because of a diff timeout.” “String to replace not found” Morph was engineered differently. It doesn’t choke…

1 0 6 540 0

Download Image

Morph @morphllm

2 weeks ago

🔥 gpus do indeed go brrrrrr

0 0 3 143 0

Download Image

Tejas Bhakta @tejasybhakta

2 weeks ago

We're hitting 10,542 tokens/sec per request on Nvidia B200s Batch size=1. P95 latency: 384ms. 8k input/8k output. Single-request throughput—no batching tricks.

3 4 12 776 0

Download Image

Vasek Mlejnsky @mlejva

3 weeks ago

We added support for @morphllm to our Fragments repo from @e2b. Morph's LLM is specialized fast apply and codegen model. Instead of generating the whole file from scratch every time you want to change something, you can just use Morph to generate the actual changes and have…

5 5 23 4K 4

Download Video

Morph @morphllm

3 weeks ago

The best sandboxes deserve the best code gen experience. The e2b product and developer experience is amazing and we’re thrilled to work together!

Vasek Mlejnsky @mlejva

3 weeks ago

The best sandboxes deserve the best code gen experience. The e2b product and developer experience is amazing and we’re thrilled to work together!

5 5 23 4K 4

Download Video

1 0 7 484 1

Kilo Code @kilocode

4 weeks ago

Want to speed up file changes in large code based? Try @morphllm inside Kilo Code

2 3 22 4K 2

Download Image

Askar Yusupov @pyoner

a month ago

6/7 The numbers are impressive: MorphLLM's Apply API processes over 4,500 tokens per second, achieving 98% accuracy in approximately 6 seconds per file. This dramatically outperforms traditional search-and-replace systems, which take 35 seconds with only 86% accuracy. Files up to…

1 1 3 330 1

Download Image

Jon Hulsinger @jhallsinger

a month ago

Just discovered @morphllm not a plug, just a heads-up: pair it with any base model (e.g., GPT-5 Medium) and you can achieve better than Claude Code–level research depth or blistering code-app performance (~4,500 tok/s) at roughly 80% lower cost than Claude Sonnet alone.

2 1 7 542 1

Kjerstin Erickson (KJ) @Kjer

2 months ago

$33/year + usage. 15% transparent markup. Owned by the people who grow it. With this pricing, we're making it impossible not to give @SoftgenAI a try. Announcing Softgen 2.0 → the world's first selling-selling tech co. Live now at Softgen.ai

1 1 12 2K 3

Download Video

Ben @Ben3adi3

2 months ago

When I read the base description for @morphllm for the @ycombinator hackathon, I wasn't sure it would be useful. I was wrong. This tool is awesome and genuinely expanded my ideas on what is possible to build right now with AI. The potential is huge

2 1 5 1K 2

0x_SiliconValley Podcast @0X_CryptoValley

2 months ago

attend @ycombinator AI Coding Agents Hackathon, thanks to @OpenAI @AnthropicAI @aidenybai @samedotdev @tejasybhakta @morphllm @benswerd freestyle.sh We built an YC investment agent project using those fantastic tools. Pitched to judges. High energy vibe in the space!!

0 2 7 1K 2

Download Image

Morph @morphllm

2 months ago

incredible team! thanks for coming out

jia @jia_seed

2 months ago

incredible team! thanks for coming out

54 6 284 23K 27

Download Image

2 0 5 1K 0

Diana @sdianahu

2 months ago

saw some impressive projects built in <8 hrs at the ai coding hackathon today hosted by @samedotdev @morphllm @benswerd from game engines to JIT agents here are the finalists

37 27 347 73K 53

Download Image

Morph @morphllm

2 months ago

May the best hacker win...

0 2 12 625 0

Download Video

Aiden Bai @aidenybai

2 months ago

hey! if you're interested in coding agents, and have ideas on making them better: come to the YC hackathon. aug 9, 9am

22 9 191 25K 34

Download Image

Tejas Bhakta @tejasybhakta

2 months ago

come build that idea everyone says is stupid @ycombinator on aug 9 at 9am just in time software dynamic AI UI anything that codes by @morphllm @AnthropicAI @samedotdev @benswerd