proactive-agent/workbench
App
Can I trust it?
No red flags in our checks.
Stars from real accounts No data
We haven't checked its stars for fakes yet.
Active OK
Last change today.
Licence OK
MIT: you can use it for free, also in a commercial product. Keep the licence notice.
Quick checks from public data. They help, but they are no guarantee.
What it is
Desktop app that manages project tasks on a kanban board and runs each one as a Claude Code agent session in its own git worktree. Sessions triage the model and effort, plan, implement, run project checks, review their diff, and commit, leaving changes for manual review and…
Who it's for
Developers using Claude Code who want to run several agent tasks in parallel on a project with git worktrees
How to use it
Ready-made installers, when the project publishes them, are on its latest release.
Ask your AI to set it up
Paste this into Claude, ChatGPT or your coding assistant.
Help me install and set up proactive-agent/workbench in my project. Follow its README: https://github.com/proactive-agent/workbench. Explain each step and check it is safe before running anything.
Star curve
Get alerts for repos like this
We'll email you when something in Apps & desktop starts rising. Free, once a week, only what matches.
19,777 GitHub repos watched and ranked every hour. Figures as of 24 October 2026.
What arrives: one email on Mondays with the repos that match, never more. See last week's. Privacy
For maintainers
Add this badge to your README. It shows the repo's place on the radar, updates every hour and links back to this page.
[](https://repoalerts.com/repo/proactive-agent/workbench?ref=badge)Similar repos
- 721AndrewWang/VibeCrew
A desktop app that runs a team of AI agents on your computer for web development. Each agent works inside your project folder, with a live preview, file tree, terminal and change history. Agents are p
- tomtomsatnav/agent-orchestration-standard
A local-first dashboard for Claude Code sessions. It shows a live project graph of agents with tokens, a tool feed, replay and alerts, delivered as a plugin, a terminal UI and an MCP server. The repos
- iha2/superlite
A Claude Code plugin that plans a software build, splits it into tasks that run in parallel, assigns each task to a model by difficulty, checks the seams between parts and reviews the result. The user
- parthh01/sphinx
A Git hook for agent-assisted development that pauses pushes to protected branches and asks the user to predict the behavior of their change. A separate reviewer model reads the committed diff through
- dagoSte/squadra
A local, MIT-licensed coordination toolkit for Claude Code, Codex and Cursor windows. It shares tasks and acknowledgements, runs prechecks and parallel tests, records source-bound proofs and independe
- wangmiaozero/pi-harness
A desktop workspace built on Pi Coding Agent for macOS, Windows and Linux. It adds run tracing, replay, budgets, tool policies, checkpoints, recovery, evaluation, and multi-agent task orchestration wi