The pentester's agent, in your terminal

Recon. Exploit.
Reverse. Report.

Q: Can I use it for penetration testing and red teaming?

Yes. Labs, CTFs, bug bounties, internal pentests and live engagements are the intended use. Only use it on devices and software you have the rights to.

Q: How does billing work?

Pay with crypto for credits and spend them per task. Credits never expire; when they run out the agent pauses until you top up.

RedWatch is an AI agent for pentesters, red teams and bug hunters. It enumerates, finds and exploits, writes payloads and PoCs, reverses binaries, reviews code and drafts the report, asking you before anything changes.

$

Get your API key

Requires Node.js 18+. Pay as you go with crypto. Credits never expire.

~/acme-api · redwatch

Windows, macOS & Linux Works on any target Approval before every edit & command One API key, no setup

What it does

A red-teamer that never gets tired of reading code.

Point RedWatch at a target, a repo or a binary. It works with real tools, not guesses, and shows its reasoning and every command it runs.

Secure code review

Injection, auth flaws, unsafe deserialization, secrets in source. Every finding gets a severity, a location and a working fix.

Exploit dev & PoCs

Payloads, shellcode, C2 plumbing and working proof-of-concepts, then the notes to reproduce them. Build it, fire it, fix the crash loop.

Reverse engineering

Disassembly, strings, control flow and lifted pseudocode. Run samples, trace behaviour and pull out IOCs, encrypted configs and detection logic.

Hardening & config review

Dockerfiles, Kubernetes manifests, Terraform, CI pipelines, sshd and nginx configs. It finds the weak defaults and fixes them.

Dependency & secrets audit

Scans lockfiles and history for vulnerable packages and leaked credentials, and tells you exactly what to rotate.

Recon & enumeration

Subdomains, ports, endpoints, users, shares, cloud metadata. It maps the surface, spots the odd one out and drives the next step.

You stay in control

Nothing changes until you say so.

RedWatch reads freely, but every file edit and shell command stops for your approval, with the exact diff or command in front of you.

See every diff before it's written.
Approve, deny or auto-approve for the session.
Ctrl+C interrupts the agent instantly, mid-command.
Runs locally: your files stay on your machine except what the agent reads for the task.

● edit_file deploy/nginx.conf - server_tokens on; - ssl_protocols TLSv1 TLSv1.1 TLSv1.2; + server_tokens off; + ssl_protocols TLSv1.2 TLSv1.3; + add_header Strict-Transport-Security "max-age=63072000" always; ? Allow edit_file? [y]es / [n]o / [a]lways this session

How it works

Running in under a minute.

No containers, no config files, no infrastructure. One key and one command.

Get a key

Create an account, add credits, and copy your API key from the dashboard.

Open dashboard →

Install & log in

Run the installer for your OS, open a new terminal, and paste your key once.

redwatch login

Point it at a problem

Start it in any project folder and describe the job in plain English.

cd my-app && redwatch

Pricing

Pay for what you use.

Buy credits with crypto, spend them per task. No subscription, no seat fees. Credits never expire.

Starter

$10

For trying it on a side project

$10 of agent credits
All features included
Pay with BTC, ETH, USDT & more

Get started

Pro

$30

For daily security work

$30 of agent credits
All features included
Unlimited API keys
Pay with BTC, ETH, USDT & more

Get Pro

Team

$100

For security teams

$100 of agent credits
Unlimited API keys
Per-request usage logs
Pay with BTC, ETH, USDT & more

Get Team

A typical code review of a small service uses well under $1 of credits. See your live balance anytime with redwatch usage.

FAQ

Questions, answered.

What data leaves my machine?

RedWatch runs on your computer. Only the content the agent reads for your task (file excerpts, command output, your messages) is sent to the RedWatch API to be processed. Nothing is uploaded in bulk, and you can see every file it opens in the session log. See the privacy policy.

Can it break things on my computer?

Not without you. Reading and searching are automatic; writing files and running commands always ask first, showing the exact change. You can deny any step or interrupt with Ctrl+C.

Can I use it for penetration testing and red teaming?

That is what it is for. Labs, CTFs, bug bounties, internal pentests and live engagements. Only use it on devices and software you have the rights to — scope is on you, not the model. See the acceptable use policy.

How does billing work?

Sign in to the dashboard, pick an amount and pay with crypto (BTC, ETH, USDT and more). Credit is added automatically once the payment confirms. Each request the agent makes deducts a small amount based on how much text it processes. When credits run out the agent pauses; top up and it continues. Credits never expire.

What do I need to install it?

Node.js 18 or newer on Windows, macOS or Linux. The installer drops a single file in your home folder and adds the redwatch command. See the docs for details.

Start your first engagement today.

Get a key, install in one line, and point RedWatch at the target you're most worried about.

Get your API key Read the docs

Recon. Exploit.Reverse. Report.