agent-manager

MCP server · GitHub · ★ 625 · graded 2026-10-27Source linked

The fastest developer workflow for every AI coding agent. Live status, quick prompts, worktrees, and diff review from one tmux TUI. Discord: discord.gg/ecS88An7pF

No outside reports on file

This tool has broad access to your code files and agent commands, so only use it in trusted environments and be cautious of suspicious diffs or file contents.

Based on public adoption and transparency signals as of Oct 27, 2026. Our opinion, not a code audit or security guarantee.

Was this verdict for Agent Manager helpful?

What it can access

Local filesNo local folder access notedLOW
Command executionRuns shell or system commandsREVIEW
Network reachConnects to outside service APINOTED
CredentialsNo API token requiredLOW
Package sourceGitHub (YoanWai/agent-manager)PUBLIC

Inferred from this listing’s public package details and description. Check the project’s source before installing.

Install

No npm or PyPI package is listed. Install from source: github.com/YoanWai/agent-manager ↗

All setup options ↓

Check this skill Watch it in my stack Compare README badge View project

Everything known

We found nothing about this project in the sources we read (last checked 2026-10-30). That does not mean it has no problems.

0 incidents · 0 advisories · 0 news articles · 0 community threads · checked 2026-10-30

Popularity grade: C (from public signals such as stars and downloads, not a code review). Graded 2026-10-27.

Sources we read: OSV, GitHub Advisory Database, CISA Known Exploited Vulnerabilities, 44 security news feeds and our incident library. Last checked 2026-10-30.

Check a specific version →

About Agent Manager

Agent-manager is a terminal interface (TUI) tool that helps developers manage AI coding agents. It provides live status updates, quick prompts, workspace management (worktrees), and diff review tools all in one tmux-based dashboard.

Who it’s for

This tool is for developers who work with multiple AI coding agents and want a centralized control panel. It's designed to speed up workflows by putting common agent management tasks in one place.

Alternatives

Aider: AI pair programming tool with built-in git and editor integration
GitHub Copilot CLI: GitHub's native agent for terminal workflows
Continue.dev: IDE extension providing agent management within your editor

Setup

Check these steps against the project’s own instructions before running anything.

Follow the project's README at https://github.com/YoanWai/agent-manager (opens external site) for installation and configuration instructions specific to your setup.

Why this grade

CC — Moderate risk signals

Signal-based grade (3/7 points): well starred on GitHub, public source code. This reflects adoption and transparency, not a code review.

Popularity and upkeep

31/100

GitHub stars: 625
Listing last refreshed: 2026-10-29

These are public popularity signals, not a maintenance check. Look at the repository’s commit history and open issues.

Risks to watch for

File system access: Can read and modify code files and diffs on your machine, potentially including sensitive project data or API keys embedded in code
Prompt injection: Malicious diffs or file contents displayed in the UI could contain instructions disguised as code to trick you or the AI
Agent command execution: If connected to external AI agents, could relay commands that perform unintended actions
Tmux interaction: Runs within tmux sessions, so anyone with shell access to your terminal can see or control agent workflows
Discord community links: External community link in description is not part of the tool itself but should be verified before joining

How to lower the risk

Least-privilege permissions

Run only on projects you trust; avoid connecting to untrusted AI agents
Review code diffs carefully before approving agent actions

Network isolation

Use only on machines where you control network access
Be aware if the tool communicates with external services (check documentation)

Monitoring

Watch tmux session logs for unexpected agent commands or file modifications
Check your project files after agent runs to spot unauthorized changes

Red flags to watch for

Diffs that include suspicious instructions or commands in comments
Unexpected file modifications outside your project's normal scope
Agent responses that don't match what you prompted for

Questions

How do I install Agent Manager?

Agent Manager does not publish a standalone npm or PyPI package. Clone or follow the setup instructions in its source repository at github.com/YoanWai/agent-manager.

Are there security reports about Agent Manager?

No reports found for this package in our research (last checked 2026-10-30). Agent Manager currently holds Grade C (Moderate risk signals) based on public adoption and transparency signals. Key risk areas to watch include file system access, prompt injection, agent command execution.

Is Agent Manager actively maintained?

Agent Manager has 625 GitHub stars. Our directory data was last refreshed on 2026-10-29. Check recent commit activity, release tags, and open issues at github.com/YoanWai/agent-manager before pinning it in production.

What are alternatives to Agent Manager?

Notable alternatives to Agent Manager include Aider (AI pair programming tool with built-in git and editor integration), GitHub Copilot CLI (GitHub's native agent for terminal workflows), Continue.dev (IDE extension providing agent management within your editor). You can also compare Agent Manager side by side with other MCP servers in the Related tools section on this page.

Maintain or use Agent Manager? Show its live grade in your GitHub README, docs site, or run a check from the terminal before you install.

AgentArmorHQ Risk Grade C for Agent Manager

GitHub README Markdown:

markdown

[![AgentArmorHQ Risk Grade for Agent Manager](https://agentarmorhq.com/api/badge/yoanwai-agent-manager)](https://agentarmorhq.com/skills/yoanwai-agent-manager)

HTML embed:

html

<a href="https://agentarmorhq.com/skills/yoanwai-agent-manager"><img src="https://agentarmorhq.com/api/badge/yoanwai-agent-manager" alt="AgentArmorHQ Risk Grade for Agent Manager" height="20" /></a>

Terminal check:

terminal

curl -fsSL https://agentarmorhq.com/api/cli | node --input-type=module - check "yoanwai-agent-manager"

Share with your security lead

Need sign-off to use agent-manager? Copy this note for Slack, a ticket or a pull request.

### AgentArmorHQ Security Review Memo: agent-manager
- **Listing URL:** https://agentarmorhq.com/skills/yoanwai-agent-manager
- **Type:** App connector
- **Risk Grade:** Grade C (Moderate risk signals)
- **Outside Security Advisories on File:** 0
- **Public Adoption:** 625 GitHub stars

#### Permission & Blast-Radius Signals
- **Local files:** No local folder access noted
- **Command execution:** Runs shell or system commands
- **Network reach:** Connects to outside service API
- **Credentials:** No API token required
- **Package source:** GitHub (YoanWai/agent-manager)

#### Recommended Hardened Setup
- **Source Repo:** https://github.com/YoanWai/agent-manager
- **Controls:** Pin an exact version in `.mcp.json`, scope access to a single workspace folder, and use a least-privilege read-only token where supported.

_Based on public adoption and transparency signals as of Oct 27, 2026. Our opinion, not a code audit or security guarantee._

Key facts

Type: App connector
Publisher: YoanWai
Source code: github.com/YoanWai/agent-manager
Est. context load: ~700 tokens / turn (~4 tool schemas, 0.35% of 200k context)
Popularity: 625 GitHub stars
Last updated: 2026-10-29
Last graded: 2026-10-27

Community

Discussions for Agent Manager

Ask questions or share configuration tips. Governed by our Community Rules & Terms.

No posts match this filter yet.

Be the first to ask a question or share a working tip.

Was this listing for Agent Manager helpful?

Check before you install, in Claude

Your assistant answers Block, Review or No known issues for any package before it installs it.

Get this check inside Claude