agentsview

last_edited: 2026-10-31

agentsview

Browse, search, and track costs across your AI coding agents. Your session
archive stays on your machine unless you choose a feature that shares it.

This README and the documentation follow main.
The latest release is v0.46.1. Check the
changelog for what it includes.

Version 0.46.1 fixes Antigravity transcripts and read-only mounts, preserves
repeated prompts, and restores container builds.

Version 0.46.0 adds
Claude.ai Sync through Chrome,
opt-in
Codex cloud chats, and
Muse Code and fx sessions. Preserve a retired machine's history with
local archives, or
sync a remote machine over
SSH without
installing a daemon. Find work by label or linked pull request, narrow cost
charts by project, and inspect tool effectiveness with transcript evidence.
Connected assistants gain eight read-only MCP tools for the same archive.

Install

macOS and Linux:

Windows (PowerShell):

Or download the desktop app (macOS / Windows) from
GitHub Releases or via
homebrew: brew install --cask agentsview

On macOS, see
Use the bundled CLI
for terminal setup and the required first launch. For Macs managed over SSH, use
the standalone CLI installer above.

Or run the published Docker image:

Quick Start

On first run, agentsview discovers sessions from every supported agent on your
machine, syncs them into a local SQLite database, and serves a web UI at
http://127.0.0.1:8080.

The daemon is the server: the web UI, API, session sync, and file watchers share
one process. Choose serve for a foreground process or daemon start for a
background process. Running serve when a compatible daemon is already running
reports its URL and exits with an error (status 1) in the foreground.
daemon stop and serve stop both stop that writable server, including sync;
serve…