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.
Ask your agent to explain a flow as a statechart, with optional TLA+/TLC checking and a Hub viewer. Setup runs in parallel and survives interruption, and large TypeScript graphs build with less memory. npx mex-agent@0.8.5 setup
Terminal setup is the default, with a native agent handoff. Knowledge checks share fact-aware verdicts, and new grounding fingerprints are much smaller.
Graph refresh reuses unchanged files, grounding survives fresh clones and small renames, and FastAPI, Flask and NestJS routes join the graph.
Your coding agent can now explain a complicated flow as a checked statechart. Setup runs in parallel and resumes after interruptions, and large TypeScript graphs build with less memory.
Read moreAfter 367 commits of real code changes, memory tools with no link to code served 90 to 100% of outdated facts as current in their no-LLM modes.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 moreThere 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 LinkedInThoughts on agent memory. Clark and Chalmers’ Extended Mind Thesis holds up for this space as well.
Read on LinkedInOn 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 moreEvery few months, a new model arrives with a larger context window. But being present is not the same as being used.
Read on LinkedInWhy every session starts cold, and the case for persistent, structured memory over giant context files.
Read on X