Terminal dashboard that monitors your local AI tooling ecosystem — coding agents, MCP servers, LLM models, and token metrics.
Terminal dashboard that monitors your local AI tooling ecosystem — coding agents, MCP servers, LLM models, and token metrics. One unified view.
Features • Installation • Usage • Scoring • Privacy
agentradar is a Node.js TUI that scans your local machine to give you a live picture of your AI tooling landscape. It detects running AI processes as active agents, discovers installed MCP servers/skills, tallies model usage from history, and measures token burn rates — all locally, with zero outbound network requests.
[!NOTE] agentradar runs entirely locally. It reads the process table, configuration directories, and local log files on your machine to render the results in your terminal. No telemetry, no network calls.
Toolsmith, Multi-Provider, or High Throughput based on your setup.You can run and install agentradar using the following methods:
npx agentradar
npm install -g agentradar
Once installed, start the TUI dashboard by typing:
agentradar
git clone https://github.com/shafiqimtiaz/aiscope.git
cd aiscope
npm install
npm run build
npm start
# Run with demo mock data
node dist/index.js --demo
# Start TUI dashboard with live local scans
agentradar
# Start TUI dashboard in demo mode (with realistic mock data)
agentradar --demo
# Export scanned data in raw JSON format
agentradar --json
| Key | Action |
|---|---|
q | Quit agentradar |
r | Force an immediate scan refresh |
Your agents, MCP servers, models, and token usage get scored up to 1000 points:
| Dimension | Max Points | How |
|---|---|---|
| Agents Running | 350 pts | 75 pts per active agent (cap 4) + 50 pts bonus for 3+ simultaneous |
| MCP Servers & Skills | 200 pts | 10 pts per server (cap 15) + 1 pt per tool/move (cap 50) |
| Model Diversity | 200 pts | 30 pts per unique model (cap 5) + 50 pts for using 3+ providers |
| Token Velocity + Sessions | 250 pts | Velocity levels + session count |
| Platform | Process keyword | Config path |
|---|---|---|
| Claude Code | claude* | ~/.claude |
| Codex | codex* | ~/.codex |
| GitHub Copilot CLI | copilot* | ~/.copilot |
| Gemini CLI | gemini* | ~/.gemini |
| Cursor | cursor | ~/.cursor |
| Amp | amp* | ~/.amp |
| Cline | — | ~/.cline |
| Roo Code | roo* | ~/.roo |
| Kilo Code | kilo* | ~/.kilo |
| Kiro | kiro | ~/.kiro |
| Crush | — | ~/.crush |
| OpenCode | opencode | ~/.opencode |
| Factory Droid | factory-droid | ~/.factory-droid |
| Antigravity | antigravity* | ~/.antigravity |
| Kimi CLI | kimi* | ~/.kimi |
| Qwen Code | qwen* | ~/.qwen |
Scans for occurrences of the following model families in your local history and logs:
claude-4-opus, claude-4-sonnet, claude-3.7-sonnet, claude-3.5-sonnet, claude-3-haikugpt-4.1, gpt-4o, gpt-4-turbo, o4-mini, o3, o3-mini, o3-progemini-2.5-pro, gemini-2.5-flash, gemini-2.0-flashdeepseek-v3, deepseek-r1, qwen-3, llama-4agentradar runs 100% locally. No data leaves your machine. No telemetry. No analytics. No outbound network requests are made during scanning. All log file parsing, process checking, and configuration scans happen entirely on your computer.
FAQs
CLI to check whether a site is visible and usable to AI agents.
The npm package agentradar receives a total of 5 weekly downloads. As such, agentradar popularity was classified as not popular.
We found that agentradar demonstrated a healthy version release cadence and project activity because the last version was released less than a year ago. It has 1 open source maintainer collaborating on the project.
Security News
An OpenCode user faced harassment after reporting a free AI usage loophole, drawing a bitter backlash in a GitHub thread that has since been deleted.
Threat Research
/Security News
319 browser extensions installed by 13.4 million users hijack searches, capture queries, and collect referral payments from Yahoo and Bing.
Threat Research
Malicious Firefox extensions mimic Phantom, Jupiter, and Bitget wallets to steal recovery phrases and private keys, with one fetching its payload remotely.