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 🔥

Relace Apply 3 is here -- we now support 128k input tokens and have 4x fewer errors on hard merges!

Relace Apply 3 is live on OpenRouter! openrouter.ai/relace/relace-…

🚀 New Model Launch - Relace'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.

GPUs go brrrr

Great to see Preston Zh is on TBPN talking about Relace and everything codegen related 🕹️🕹️

Relace Repos is here! It's GitHub for agents with semantic search out-of-the-box. Just use standard git operations without worrying about rate limits. After each push, we auto-index the updated files and use a reranker to make sure each search tool call is fresh. Retrieval is

Link to the blog post: relace.ai/blog/relace-re…

Cool to see Relace on Product Hunt 😸 today! Now this is all your coding agent has to do to preserve repo state: client.git('./repo_path').add('.') .commit('msg').push() Github repos are for humans. Relace repos are for agents generating code

We just released the krabby patty formula...

With Repos, semantic search is as easy as: