Product analytics (and evals) for agent sessions on your MCP

I Repurposed Unit Tests to Show How Much Coding Agents "Improvise"

As someone who is using agents to code for me a lot lately, I was starting to feel more and more like I'm losing touch with the code I write--it's starting to f

Isolade, a local-first coding agent workbench with secretless microVMs

I built Isolade because I could not find an open-source, local-first workbench that runs coding agents in microVMs.The two pieces already exist individually. Th

MicroCodex Coding Agent

OpenAI/codex reimplemented in C++ <1MB binary

Entangle, hand a live AI coding session to anyone with three words

The agent-to-codebase interface is broken. I tried to fix it

I’d be glad to hear what you think, including where you disagree, and answer any questions