Watch what Claude Code or OpenCode agents are doing across multiple sessions at once.
Use the kanban board to see which agent sessions need your attention.
Track nested sub-agent activity when one agent spawns another to handle a subtask.
Build a multi-step agent workflow that runs automatically on a schedule.
| ovsec/crewview | 0xradioac7iv/tempfs | 7vignesh/pgpulse | |
|---|---|---|---|
| Stars | 0 | 0 | 0 |
| Language | TypeScript | TypeScript | TypeScript |
| Setup difficulty | easy | moderate | moderate |
| Complexity | 2/5 | 3/5 | 4/5 |
| Audience | developer | developer | developer |
Figures from each repo's GitHub metadata at analysis time.
Ships as a single binary, no separate install required.
CrewView is a local dashboard for monitoring AI agent activity. If you run AI coding assistants like Claude Code or OpenCode, each conversation creates a session, a record of what the agent was asked and what it did. CrewView watches those sessions and displays them in a browser based interface, giving you a single place to see what all your agents are doing. The dashboard has several views. The sessions list shows every conversation with its status (running, done, or failed), how long it ran, and a preview of the prompt. A kanban board organizes sessions into columns based on whether they need your attention. The live view shows agent activity in real time, including sub-agents: when one agent spawns another to handle a subtask, the child appears nested under its parent. There is also a workflow builder for defining multi-step agent pipelines that can run on a schedule. CrewView connects to Claude Code by reading the local log files that Claude Code writes to your home directory, checking for new entries every few seconds. It connects to OpenCode via its HTTP API. You can run both at the same time, and add more sources from the UI without restarting. All data is stored locally in a SQLite database on your machine. Nothing is sent to external servers except optional anonymous usage statistics, which can be turned off. The tool ships as a single binary that includes the dashboard frontend, so there is nothing to install separately. It supports Linux, macOS, and Windows. The tool is written in Go with a React frontend, and is released under the MIT license. The full README is longer than what was shown.
A local dashboard that shows what your AI coding agents like Claude Code and OpenCode are doing in real time, including sub-agent activity.
Mainly TypeScript. The stack also includes Go, React, SQLite.
Use freely for any purpose, including commercial use, as long as you keep the copyright notice.
Setup difficulty is rated easy, with roughly 5min to a first successful run.
Mainly developer.
This repo across BitVibe Labs
double-check against the repo, no cap.