snyvi 1.5.0

A fast, beautiful viewer for the documents your agents produce
snyvi-1.5.0 is not a library.

https://github.com/user-attachments/assets/fb6ee0de-a5ce-437c-b2a3-d354081ca727

You have more passion projects than hours in the day. With coding agents, you can finally build them all, at the same time.

But the work scatters. Plans get lost in terminal scrollback. What's left to do lives in your head. And every project pulls you away from the last.

snyvi keeps it all in order. One desk for each project, its agents side by side, and everything they write kept where you can read it. It runs on your machine, with no account and nothing to configure.

Install

curl -fsSL https://raw.githubusercontent.com/snymrova/snyvi/main/install.sh | sh

Linux and macOS. It checks every download against its checksum and connects Claude Code if it finds it. Read it first; run it again to update.

Windows: scoop bucket add snyvi https://github.com/snymrova/scoop-snyvi then scoop install snyvi, or the installer.

Homebrew, .deb, cargo install snyvi and the rest: install guide.

One desk for each project

A project's folder with up to four real shells in it: Claude Code, Codex, your tests, a git log. Every agent on the project works in view.

Nothing scrolls away

Plans and reviews land as clean pages, filed under their project and kept with every earlier version. c shows what changed.

Out of your head

Each desk keeps its own notes, so what's left to do stays with the project. The agents at that desk can read them too, and only read them.

Just as you left it

Switch projects and each desk is exactly as you left it. The agents you walked away from keep working. ⌘K searches everything any agent ever sent.

Any agent

snyvi init-claude --auto   # Claude Code
snyvi init codex           # also cursor, claude-desktop, gemini, windsurf, vscode, zed

Private, and fast

One static binary, listening on 127.0.0.1 only. No account, no telemetry. Up in 11 ms, and every budget is checked on every push.


Guide · Desks · Roadmap · The film · MIT