Back to home
Updates & insights

Shipping in the open.

mex is open source and moving fast. Here's what's new in the CLI, and how we think about memory for AI coding teams.

Latest releases
v0.8.3Latest

Faster graphs, more reliable grounding

September 2026

Graph refresh reuses unchanged files, grounding survives fresh clones and small renames, and FastAPI, Flask and NestJS routes join the graph. npx mex-agent@0.8.3 setup

v0.8.2

Set up in the Hub

September 2026

Setup starts in the local browser Hub. Terminal setup remains available.

View full changelog on GitHub
Blog posts
BlogBenchmarksmex

When memory goes stale: benchmarking mex against nine tools

After 367 commits of real code changes, memory tools with no link to code served 90 to 100% of outdated facts as current in their no-LLM modes. mex served 20%, and we measured what its warnings cost.

Read more
LinkedInAgent memoryArchit Dhamija

Agent Beliefs Need a Compile Step

There is a kind of sentence that sounds like knowledge but does not point at anything, and a name can survive the thing it named.

Read on LinkedIn
LinkedInAgent memoryAkshat Dhamija

Extended mind, badly

Thoughts on agent memory. Clark and Chalmers’ Extended Mind Thesis holds up for this space as well.

Read on LinkedIn
BlogBenchmarksmex

90% less noise, up to 70% fewer tokens: the numbers behind mex

On a set of retrieval tasks, mex returned answers that were 10x more compact than a grep-based baseline, while still finding everything it needed to find.

Read more
LinkedInContextmex

A million-token context window is not a million-token brain

Every few months, a new model arrives with a larger context window. But being present is not the same as being used.

Read on LinkedIn
XAgent memoryDaksh Jaitly

Your AI Agent Has Amnesia. Here's the Fix.

Why every session starts cold, and the case for persistent, structured memory over giant context files.

Read on X