unalome-ai

unalome-ai / unalome-firewall

Public

Unalome Agent Firewall is a free, open-source desktop app that gives you complete visibility into what your AI agents are doing on your machine — in plain language anyone can understand.

unalome.ai ai-agents claude-code openclaw
19
1
100% credibility
Found Mar 20, 2026 at 19 stars -- GitGems finds repos before they trend. Get early access to the next one.
Sign Up Free
AI Analysis
Rust
AI Summary

Unalome Agent Firewall is a free open-source desktop app that monitors AI coding agents for risks, tracks costs and usage, detects sensitive data exposure, backs up files automatically, watches network activity, and generates insightful reports.

How It Works

1
📱 Discover Unalome

You hear about this free app that watches your AI coding helpers to keep them safe and track their spending.

2
⬇️ Download and install

Grab the app from the website, double-click to install, and open it up – it's ready in seconds.

3
🔍 It spots your helpers

A quick welcome tour automatically finds your AI tools like Claude or Cursor and lights them up on screen.

4
📊 Check your overview

See a beautiful dashboard showing actions taken, money spent, and safety scores at a glance.

5
⏱️ Follow the action feed

Watch every move your helpers make in real-time, with color-coded risks and full details.

6
🛡️ Use safety tools

Backup files before changes, block data leaks, pause helpers, or scan for worries.

📈 Enjoy weekly recaps

Get shareable reports celebrating your secure week, smarter spending, and full peace of mind.

Sign up to see the full architecture

5 more

Sign Up Free

Star Growth

See how this repo grew from 19 to 19 stars Sign Up Free
Repurpose This Repo

Repurpose is a Pro feature

Generate ready-to-use prompts for X threads, LinkedIn posts, blog posts, YouTube scripts, and more -- with full repo context baked in.

Unlock Repurpose
AI-Generated Review

What is unalome-firewall?

Unalome Agent Firewall is a free, open-source desktop app built in Rust that gives you complete visibility into what your AI agents are doing on your machine—in plain language anyone can understand. It auto-discovers tools like Claude Code, Cursor, and OpenClaw, tracking tool calls, file changes, network requests, and API costs across 40+ models. Developers get a dashboard with timelines, security scans, PII alerts, and safeguards like file snapshots before overwrites.

Why is it gaining traction?

It stands out by running entirely locally—no cloud or accounts—while packing pro features like real-time cost breakdowns, MCP server vulnerability scans, outbound connection monitoring, and a global kill switch for agents. The plain-language summaries and one-click restores make agent oversight dead simple, unlike scattered logs or paid tools. Early adopters love the weekly HTML reports for sharing activity trends.

Who should use this?

AI-heavy coders relying on Cursor for tab completions, Claude Code for sessions, or OpenClaw for tool calls—especially if you're paranoid about agents leaking API keys, racking up bills, or nuking source files. Solo devs or teams auditing agent permissions before production deploys will find the PII guardian and safety net indispensable.

Verdict

Grab it if you're deep into those agents; the feature density punches above its 19 stars and 1.0% credibility score. Docs are solid and onboarding quick, but it's early—expect rough edges in edge-case parsing. Worth watching as agent adoption explodes.

(198 words)

Sign up to read the full AI review Sign Up Free

Similar repos coming soon.