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
v0.7.3Latest

Graph performance and recovery

latest · August 2026

mex 0.7.3 makes the code graph affordable to keep. Graph builds hold one compiler program at a time, stores are roughly 40% smaller, and interrupted builds can be repaired.

v0.7.2

Source-backed graph retrieval

August 2026

mex 0.7.2 makes the code graph useful as a first-response retrieval system. `mex graph scope` now returns the most relevant source declarations and execution flows under a hard token budget.

v0.7.0

Code-aware project memory

July 2026

mex 0.7.0 adds a deterministic code knowledge graph beneath the existing markdown scaffold. Memory can now ground itself to exact code nodes instead of relying only on file paths.

View full changelog on GitHub
Blog posts

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

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

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