CLOUDM0N
Repository intelligence

Eskeeet/frieren-agent-monitor

GitHub

An open-source macOS desktop companion that floats above the screen to monitor local and remote AI agent sessions.

CLOUDM0N decision
REVIEW BEFORE ADOPTION
Trust REVIEW · 90/100
Good fit if

macOS developers running local or SSH-based AI coding agents who need non-intrusive visibility into active session lifecycles

Watch out for

Remote host monitoring requires Python 3 to be installed on target machines

Practical intelligence

What matters before you adopt it

Problem it solves

The lack of clear, non-intrusive visibility into the running, waiting, and idle states of AI coding agents, which often pause silently on terminals or background processes awaiting user input or tool permissions.

Best for
macOS developers running local or SSH-based AI coding agents who need non-intrusive visibility into active session lifecycles
Main trade-offs
Remote host monitoring requires Python 3 to be installed on target machines
Does not support interactive password prompts for SSH, necessitating pre-configured keys or ssh-agent
Automatic hook configuration is limited to pre-existing agent settings directories
Why it stands out
Tracks session states and lifecycle events for Claude Code, Codex, Cursor, and Pi across local and remote environments
Provides a non-intrusive, interactive desktop pet interface with custom drag-and-drop support and click animations
Highly customizable with support for custom-imported local characters via sprite sheets or custom animation manifests
Trust & CVEs

Security evidence without the noise

Trust remains a decision signal; CVEs and scanner evidence explain what is driving the risk.

Security findings
1
CLOUDM0N scanner findings
Critical
0
High
0
Medium
1
Low
0
View trust evidence & security findings▼
Why this score
No trust rationale was stored for this scan.
CLOUDM0N findings
MEDIUM
The project can spawn operating-system processes; review command construction and input handling. 1 sample match(es) found.
Architecture from code4 modules · 0 edges▼
Structural evidence

Modules and dependency edges extracted from repository code. This is code evidence, not README inference.

Code files
3
Modules
4
Dependency edges
0
Core modules
scripts
3 files
Dependency flow
No dependency edges were extracted.
Detected languages
Swift · Shell · Python · TypeScript
Detected frameworks
—
Architecture evidence details
flowchart TD
    %% repo — high-level architecture (DRAFT, refine me)
    n0["scripts · scripts · 3 files"]
    class n0 infra
    classDef infra fill:#b35c00,color:#ffffff,stroke:#8f4a00
Evidence, security & integrations▼
Integrations
Claude CodeCodexCursorPimacOSOpenSSHPython 3Swift
Security notes
• All session data remains strictly local on your Mac and remote hosts; nothing is uploaded to external cloud services
• SSH connections explicitly reject changed remote host keys to protect against man-in-the-middle attacks
• The collector transferred to remote machines is read-only and runs non-privileged
Still unknown
• The README does not provide the exact terminal build commands to compile the Swift project
• Does not specify CPU or memory overhead figures for polling multiple concurrent remote hosts every eight seconds
• Lacks detailed format specifications for structuring custom character.json animation manifests manually
Adoption guidance▼
Adopt if
+ You are a macOS developer frequently running Claude Code, Codex, Cursor, or Pi and want a visual way to know when an agent is stalled awaiting input
+ You want a highly customizable, offline-first companion application that keeps session logs entirely local
Avoid if
– You do not use macOS as your primary operating workstation
– You require monitoring of remote SSH hosts but cannot configure key-based SSH authentication or do not have Python 3 on those hosts
How it works & getting started▼
How it works
1.The companion app is built and launched locally on a macOS desktop
2.Harness event hooks are installed on the local Mac to report lifecycle events to a local script
3.For remote setups, Frieren copies a read-only collector to ~/.frieren-monitor on the target machine
4.The app detects local processes from metadata and polls remote SSH hosts concurrently every eight seconds
5.The companion visualizes agent states with specific waifu animations and notification bubbles
Getting started
→ Clone the repository to build and launch the app locally on your Mac
→ Run the hook installer to configure event scripts in ~/.frieren-monitor/hook.sh to improve agent state detection
→ Alternatively, use the single-step build-and-install option to compile, move the app to ~/Applications, install hooks, and launch
→ Restart any active agent sessions after installing hooks to ensure lifecycle reporting is active
Agent handoff
Use with any agent
JSON API
Alternatives

Nearby repositories worth comparing before adoption.

Compare top options →
Claude-Code-Agent-Monitor
hoangsonww/Claude-Code-Agent-Monitor
54
Fit

🚀 A real-time monitoring dashboard for Claude Code & Codex, built with SQLite3, Node.js, Express, React, Vite, TailwindCSS, & WebSockets. It tracks sessions, agent activity, tool usage, and subagent orchestration, providing live analytics, a Kanban status board, status notifications, a cute buddy, & an interactive web UI/MacOS/Windows native app.

Trust REVIEW · 20
Compare →
velpos
Jxin-Cai/velpos
40
Fit

Rapidly build a multi-Agent management dashboard based on Claude Code, integrating daily work and remote IM collaboration. It includes Claude Code monitoring, channel configuration and message notifications, with a Codex GUI optimized for non-technical users.

Trust REVIEW · 65
Compare →
signoz
SigNoz/signoz
62
Fit

SigNoz is an open-source, OpenTelemetry-native observability platform for your team and their AI agents. Get logs, metrics, and traces in one tool with features like APM, distributed tracing, log management, infra monitoring, etc. Combined with SigNoz MCP and a native AI teammate (in SigNoz Cloud) it helps you build more resilient apps.

Trust REVIEW · 90
Compare →