It's finally back!

GLM 5.2 made its own GLM 5.2 promotion in Jacq.

More use cases for the Jacq X integration

First class plugins in Jacq are becoming a window into all your daily tools accessible from one place.

We now have deep research powered by @ExaAILabs in Jacq!

Opus 4.8 is live in Jacq!

One of the many first class integrations, we're bringing into Jacq. Try it --> jacquard.dev

You lose a lot of flexibility when a cloud agent is quarantined in its VM until you sync manually. Jacq packages a toolbox binary that turns each device (phone, laptop, desktop) into an API, and the agent dynamically decides what connected device to execute tools on. This means if my laptop goes offline, Jacq can autonomously decide to keep working on other things in the cloud until I'm back. Long term it's always better to give the model more choice.

A lot of coding products treat threads as disposable, and you end up having to get your agent up to speed with the same info over and over. We trained a compaction model for Jacq that runs at 90k tok/s to make resuming with context from other threads instant.

For 18 months, Relace has been training small, specialized models that make autonomous coding products smooth. Jacq is built on everything we've learned and showcases some new models we've worked on recently. It uses a compaction model under the hood that runs at 90k tok/s, fast enough to condense a 250k token thread in 2-3s. This means you can stay on the same thread indefinitely, or instantly fork from the same starting point. Autopilot mode is actually a small classifier model that identifies unsafe tool calls. The agent stops bothering you about routine stuff, and is forced to work around or ask you about things you might regret. Small models are best when they feel invisible and just work. Let us know what you think, and DM us if you want API access to these models!

🚀

For months there’s been debate on RAG vs agentic search for codebase retrieval. RAG is an independent, single-shot classifier of file relevance: each file is scored using only the user query and that file’s contents, with no inter-file reasoning or iteration. Together, these two properties make RAG completely parallelizable. The entire codebase can be scored in ~1-2s if you scale compute enough. Agentic search breaks independence to improve accuracy. File relevance is refined iteratively through tool calls (e.g. grep, file views), where difficult cases are resolved with multi-step reasoning. In early implementations, this reasoning was done serially, with each tool call gating the next, leading to end-to-end latencies over 100s. Fast Agentic Search operates in a Goldilocks regime between RAG and serial agentic search. It preserves inter-file reasoning while parallelizing exploration, resulting in ~4× lower latency with nearly equal accuracy.

You can easily integrate Relace Search as an explore subagent in your product with our MCP server: docs.relace.ai/docs/fast-age… It uses our pre-defined agent harness and executes greps from Relace Search on your local file system in parallel.

Check out the installation instructions here: docs.relace.ai/docs/fast-age…

You can now use Relace Search as a subagent in Claude Code, Cursor, or any coding agent supporting external MCPs.

Fast agentic search is here! Try it out for yourself on our model playground app.relace.ai

With Repos, semantic search is as easy as:

We just released the krabby patty formula...

Cool to see @relace_ai on @ProductHunt 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

Link to the blog post: relace.ai/blog/relace-repos