Repos is a source control product co-optimized with our suite of fast, specialized coding models. It's git compatible, high throughput, and has built-in codebase retrieval.
Hey everyone 👋 Preston, Eitan, and Julian here from Relace.
Over the past year, we’ve shipped a suite of models that make AI coding agents fast:
The fastest apply model on the market (10k+ tok/s)
State-of-the-art embedding and reranker models for code retrieval that process huge codebases in seconds.
These models have powered tens of millions of requests from amazing companies like Lovable, Figma, Magic Patterns, and Orchids.
Now we’re taking it a step further. LLMs have proven they can write code — but scaling that code into production still needs better infrastructure.
We're starting with the foundation, source control.
Relace Repos is a new kind of source control system — built for AI agents, not humans. It’s fully git-compatible, designed for high-frequency read/write operations, and deeply integrates with Relace models.
Repos automatically indexes your codebase with our embedding and reranker models. That means your agents can find relevant files instantly instead of crawling the entire project.
This is just the start. Over the next few months we'll be releasing our suite of specialized agents for tasks like quickly searching codebases, automatically merging conflicts, and intelligently refactoring codebases.
These functions will be as easy as repo.search(), repo.merge(), and repo.refactor(). We believe models need to be co-optimized with the best infrastructure to take vibe coding to the next level.
If you’re already building coding agents or want to integrate them into your product, we’d love to collaborate.
Thanks for checking us out — we can’t wait to see what you’ll build with Relace!
Git compatible, high throughput, and built-in codebase retrieval designed for teams pushing the limits of AI-assisted development.
best models on the market. happy customers and couldn't imagine building without the relace models!
This hits a nerve for me @eitan_borgnia@preston_zhou@jthomassie we’ve got a bunch of repos and every new service turns into the same checklist: branch rules, CODEOWNERS, labels, PR templates, secrets… I’ve been keeping a scrappy bash script + gh commands to do it, and it still bites me (last month I “fixed” branch protection and quietly broke two pipelines 🙃).
If Relace Repos can make that stuff boring and consistent, I’m in. Quick question: is there a preview/dry-run so I can see diffs before applying, and can I limit changes to a team’s repos or a tag? Also curious if you surface drift over time (someone tweaks settings later) so I can roll things back. Happy to try it on our next service template and share notes.
now this is the kind of stuff i love to see on product hunt!! true builders right here. never forget relace was first building accounting software and now builds some of the best coding models on the planet!!
This is amazing - congrats on the launch!!
Have been trying out the repos feature for the past couple of days and it made building a coding agent so much easier
Congrats on the launch guys!! I've been using Relace at Line0 for over 6 months and they significantly improved the quality of generated code. Super excited for this next step, it is something I wished I had when I was building Line0 and is something I will definitely integrate into my new products going forward! LFG 🔥🔥
We're using Relace's code apply at Landingsite, "it just works". Huge fan of the team and the product.
We're using Relace's code apply at Landingsite.ai, "it just works". Huge fan of the team and the product.
Developer-first infrastructure for AI agents is the next logical step. Can’t wait to see how collaboration works in practice. Great concept!
We're Relace customers at Landingsite.ai and we're huge fans. The fast apply model has been solid and the Relace team is great!
We’re customers of Relace at Superflex and we love it! @eitan_borgnia and @preston_zhou are cooking 🔥
Incredible work! We've been using Relace models at BuildAI.Space and they've been phenomenal. This new direction with AI-native source control opens up massive possibilities for the entire AI coding arena. Excited to see where you take this! 🚀
Hey everyone 👋 Preston, Eitan, and Julian here from Relace.
Over the past year, we’ve shipped a suite of models that make AI coding agents fast:
The fastest apply model on the market (10k+ tok/s)
State-of-the-art embedding and reranker models for code retrieval that process huge codebases in seconds.
These models have powered tens of millions of requests from amazing companies like Lovable, Figma, Magic Patterns, and Orchids.
Now we’re taking it a step further. LLMs have proven they can write code — but scaling that code into production still needs better infrastructure.
We're starting with the foundation, source control.
Relace Repos is a new kind of source control system — built for AI agents, not humans.
It’s fully git-compatible, designed for high-frequency read/write operations, and deeply integrates with Relace models.
Repos automatically indexes your codebase with our embedding and reranker models. That means your agents can find relevant files instantly instead of crawling the entire project.
This is just the start. Over the next few months we'll be releasing our suite of specialized agents for tasks like quickly searching codebases, automatically merging conflicts, and intelligently refactoring codebases.
These functions will be as easy as repo.search(), repo.merge(), and repo.refactor(). We believe models need to be co-optimized with the best infrastructure to take vibe coding to the next level.
If you’re already building coding agents or want to integrate them into your product, we’d love to collaborate.
Thanks for checking us out — we can’t wait to see what you’ll build with Relace!