relace_ai Profile Banner
Relace Profile
Relace

@relace_ai

Followers
356
Following
16
Media
5
Statuses
12

Models and infra for AI code generation.

Joined September 2025
Don't wanna be here? Send us removal request.
@stuffyokodraws
Yoko
2 days
Great to see @pfactorialz is on @tbpn talking about Relace and everything codegen related 🕹️🕹️
3
3
29
@relace_ai
Relace
3 days
Repos is also designed to integrate with our task-specific agentic models we’re training at Relace and plan to release in the coming months. Utility functions like agentic search, automatic merge conflict resolution, and refactoring will be as easy as https://t.co/hZe5eD9VCf(),
0
0
4
@relace_ai
Relace
3 days
As agents work for longer over bigger codebases, accurate retrieval is critical for reliability. Repos has built in semantic search that stays fresh even with high frequency updates to the codebase. We handle all the indexing behind the scenes and use two-stage retrieval to get
1
0
4
@relace_ai
Relace
3 days
GitHub is optimized for humans. Assumptions are made about frequency of clone, push, pull, and branching operations that break down for agents. If you’ve built agents on GitHub at scale, you’ve probably hit rate limits that you’re forced to build around. Repos is designed for
1
0
3
@relace_ai
Relace
3 days
As the cost of producing code goes down, more and more of it will be generated. All of this code must be stored in a way where it can be easily deployed and continually edited by AI agents. Repos is the first in our line of products to co-optimize infrastructure with the
@pfactorialz
Preston Zh
3 days
.@relace_ai has raised $23M to build the rails for AI code generation. This round is led by @a16z, with participation from @matrixvc and @ycombinator. LLMs have proven they can write code—but scaling that code into production still needs better infrastructure. Relace is
7
0
26
@OpenRouterAI
OpenRouter
14 days
🚀 New Model Launch - @relace_ai's "Relace Apply 3" is here. It's a specialized code-patching LLM that merges AI-suggested edits straight into your source files. And it is ZDR enabled.
9
14
282
@relace_ai
Relace
14 days
GPUs go brrrr
0
0
5
@relace_ai
Relace
16 days
Relace Apply 3 is here -- we now support 128k input tokens and have 4x fewer errors on hard merges!
0
2
9
@jahooma
James Grugett
1 month
We beat Claude Code in our evals: 61% to 53%. Yes, evals are actually important haha And now we’re open-sourcing our entire codebase and launching an agent framework! Now you can build custom agents for your project and get better results 🔥
80
146
2K