I'm a sw engineer and I work daily on different repos and for the same repo in different workspaces and parallelize work.
I've started feeling the terminal apps to be too constrained and every ui for coding not very efficient to work on parallel things.
So i started my own app and now it's been 3 months since I haven't used any ide/terminal app.
it's called vipershell.
open source
runs locally
access via browser
access phone->laptop via tailscale
for each pane, you have terminal, git and files view
If you've been following agent memory evaluation, you know LoComo and LongMemEval. They're solid datasets. The problem isn't their quality; it's when they were designed.
Both come from an era of 32K context windows. Back then, you physically couldn't fit a long conversation into a single model call, so needing a memory system to retrieve the right facts selectively was the premise. That made those benchmarks meaningful.
That era is over.
State-of-the-art models now have million-token context windows. On most LoComo and LongMemEval instances today, a naive "dump everything into context" approach scores competitively, not because it's a good architecture, but because the window is large enough to hold the whole dataset. These benchmarks can no longer distinguish a real memory system from a context stuffer. A score on them no longer tells you much.
So i started my own app and now it's been 3 months since I haven't used any ide/terminal app.
it's called vipershell.
open source
runs locally
access via browser
access phone->laptop via tailscale
for each pane, you have terminal, git and files view
Claude Code, Codex, Hermes first class support
persistent terminal sessions
let me know if you like it