| What it does | AI security agent and hosted model API for authorized testing
| Real-time steering and guardrails for AI agents
|
|---|
| Stage | Not given
| Not given
|
|---|
| Founded | Not given
| Not given
|
|---|
| Based in | Not given
| Not given
|
|---|
| 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
| Team: Free per organization, unlimited users, 200 session-hours per month. Enterprise and Gateway: Custom pricing, billed annually.
|
|---|
| 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
| - Reads every tool call agents make and blocks unsafe ones before they run
- Catches stalled and runaway sessions while they run
- Steers agents back when they go past what was asked
- Tracks every session's tokens against usual usage
- Stops credential and data leaks before they leave the machine
- Inventories all agents, MCP servers and skills in use
- Blocks dangerous calls before they run in agent hooks and at the gateway
- Sends every finding to Slack, webhook or SIEM
- Verifies each agent's identity before access
- Keeps audit-grade masked records of every action and decision
|
|---|
| 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
| - Works with Claude Code, Codex, Cursor, Devin and more
- Runs on your machines, gateways and in the cloud
- Active steering corrects or stops drifting runs
- One policy applied across all MCP servers, plugins and skills
- Continuously monitors components for known vulnerabilities
|
|---|
| Community votes | 0 | 0 |
|---|
| DR (Domain Rating by Ahrefs) | 15 ▼ −1 (down) since last check | 3 ▲ +2 (up) since last check |
|---|
| Trust Flow (Majestic) | 0 | 13 |
|---|
| Citation Flow (Majestic) | 0 | 25 |
|---|
| Referring domains (Majestic) | 0 | 23 |
|---|
Excession Labs
Stacktrace