AI security agent and hosted model API for authorized testing
You shouldn't have to learn AI. It should learn you.
Stage
Not given
MVP
Founded
Not given
Not given
Based in
Not given
US
Pricing model
Not given
Freemium
Pricing
Starter $20/month with $30 credit; Pro $100/month with $175 credit; Max $200/month with $400 credit; Ultra $500/month with $1,250 credit. Pay as you go: add funds from $10 to $1,000, balance never expires. DeepSeek V4.1 Flash: $0.035 input, $0.005 cached input, $0.50 output per 1M tokens. DeepSeek V
Free for individuals. Requires a Claude or ChatGPT subscription for Clanker functionality.
Key features
Terminal AI agent with parallel workers
Per-tool allow, deny and ask rules
Evidence-linked findings with severity and remediation steps
OpenAI and Anthropic SDK-compatible API endpoints
Session save, resume, fork and export
Headless mode with JSONL output and exit codes for CI
Support for MCP servers, skills, AGENTS.md, slash commands and hooks
DeepSeek V4.1 Flash and abliterated variant models
Cross-platform support for macOS, Linux and Windows
Shared account balance between terminal agent and API
Learns work patterns from Mac apps
Offers to automate tasks in notch
Step-by-step guidance on how to do tasks
Works with Claude, ChatGPT, Gemini, and other agents
Integrates with 15+ apps
Local data storage on Mac
Does not record screen
Customized agents for each user
What makes it different
Unified billing for both terminal agent and hosted API
API compatible with OpenAI and Anthropic SDKs
Evidence-based findings with source lines and reproduction steps
Terminal agent with configurable tool rules and headless CI mode
Learns from what you actually do rather than requiring you to explain every decision
Works with the AI agents you already use via MCP
Data stays on your Mac, never shared with the company