Launch HN: Relace (YC W23) – Models for fast and reliable codegen

Hey HN community! We're Preston and Eitan, and we're building Relace (https://relace.ai). We're trying to make building code agents easy and cheap.

Here’s an example of our apply model vs. whole file edits: https://youtu.be/J0-oYyozUZw

Building reliable code agents is hard. Beyond simple prototypes, any app with code generation in production quickly runs into two problems -- how do you reliably apply diffs, and how do you manage codebase context?

We're focused on solving these two problems at order-of-magnitude lower price and latency.

Our first model that we released, in February, is the Fast Apply model -- it merges code snippets with files at 4300 tok/s. It is more reliable (in terms of merge errors) than Sonnet, Qwen, Llama, or any other model at this task. Each file takes ~900ms and gives an instantaneous user experience, as well as saving ~40% on Claude 4 output tokens.

Our second model focuses on retrieval. For both vibe-coded and enterprise codebases, retrieving only the files relevant to a user request saves both on SoTA input token cost and reduces the number of times code agents need to view files. Our reranker (evals below) can scan a million-line codebase in ~1-2s, and our embedding model outperforms any other embedding model for retrieval as evaluated on a corpus of Typescript/React repositories.

There are many different ways to build coding agents, but being able to edit code reliably and retrieve the most relevant parts of the codebase is going to be a foundational issue. We're excited to be building ways to make it more accessible to millions of users who don't want to spend $$$ on Claude.

These models are used in production, millions of times per week. If you've used Lovable, Create.xyz, Magic Patterns, Codebuff, Tempo Labs then you've used us!

Here's a link to try it out: https://app.relace.ai, and here are our docs: https://docs.relace.ai.

We've opened up free access for prototyping on our website to everyone, and the limits should be enough for personal coding use and building small projects (correct us if it’s not). We integrate directly with Open-Source IDE's like Continue.dev. Please try us out, we'd love to hear your feedback!

Good job on the launch - will give it a spin for our coding agent. Having worked a bunch with the agents i see below as the next evolution or leap in agents.

I see 2 big factors to improve ability of coding agents today

- on device model - context (or understanding of modules) - not only retrieving the relevant sections or codebase but creating a version (transforming it) which is readily consumable by a model and used to focus on the problem at hand.

This requires both a macro global context of the codebase and the ability to retrieve the local context of the problem being solved.

Augment context e.g. does a fairly good job of context compression and retrieval among coding agents. Fast indexing & retrieval is a good step forward to enable open context compression

Hey -- good question! We're focused on a narrower task right now that aims to save frontier tokens (both input & output). Our merge + retrieval models are simply smaller LLMs that save you from passing in too much context to Sonnet, and allow you to output fewer tokens. These are cheap for us to run while still maintaining or improving accuracy.

Very interesting. Can these models be used in editors/agents like aider or roo? I can see also see a use case of some sort of plugin or browser extension, to easily apply the patches provided by GPT/Claude on their web interfaces (without having to copy/paste and manually edit the files in the editor)

Also, would love to see more concrete examples of using the Apply model

Reading here: https://docs.relace.ai/docs/instant-apply/quickstart

Is it correct, that first I need to: 1) have some code, 2) create a patch of the code with the changes I want, 3) call the Apply model with the full code + patch to make the changes and provide the result?

Do you have metrics to compare that workflow with just passing the code from 1) with a prompt for the changes to something like gpt/claude?

(Preston, other guy on the team)

Yes, they can -- I actually tried a semantic edit implementation in Aider. It got the "correct edit format" percentage to 100%, but didn't really budge the overall percent correct on SOTA models. I should push it sometime, since it really helps the reliability of these local models like Qwen3. If you reach out to me, I can try to share some of this code with you as well (it needs to be cleaned up).

But yes, 1. have some code, 2. create a patch (semantic, diff, or udiff formats all work), and 3. apply will return it to you very fast. There's roughly a 10-15% merge error rate when we last benchmarked on using Claude 3.7 Sonnet to create diff patches, and with us it was 4%; and you can use the Apply as a backup if the merge fails.