Articles
-
wcode 13 min read
wcode: Rebuilding the Coding Agent Runtime Around Jev
I do not want wcode to become another Claude Code. After reading Why yet another agent, I am even more convinced that Jev / TypeSafe ideas belong in the runtime beneath coding agents: context, state, action routing, verification, and background intelligence. -
wcode 10 min read
wcode 0.8: I Started Treating the Repository as an Engineering Digital Twin
In 0.8 I stopped adding isolated agent tools and started pulling architecture, code relationships, the Decision Plane, Engineering Fitness, and verification into one evidence-aware engineering view. The current release is 0.8.1. -
wcode 24 min read
Using Jev in wcode and Scopwis
I wired Jev into wcode and Scopwis and ran several rounds of live API tests. This is what changed when I narrowed the questions, where the numbers held up, and where I finally gave Jev authority in each system. -
wcode 9 min read
How wcode Grew Past the MCP Bridge I Started With
wcode started because I wanted browser-based models to work on local code. The project changed once I started using it for real edits and had to deal with repository context, safe changes, and proof. -
wcode 7 min read
wcode 0.6.2: What 32 Tool Slots Were Hiding
I split tool slots, CPU, file I/O, and child processes into separate budgets, then fixed a few places where wcode looked healthier or busier than it really was. -
wcode 5 min read
Why “Tests Passed” Wasn't Enough for wcode
I wanted more than a green line at the end of an agent run, so wcode keeps verification tied to the exact repository revision and records what is still unknown. -
wcode 6 min read
wcode: How I Connected Web AI to a Local Repository
I built wcode so browser-based models could work on a repository on my machine without turning the machine into an open remote shell.